beyhan/graphify
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix .graphify_python path missing graphify-out/ prefix in skill files

Browse Source 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Safi
2026-05-28 16:55:07 +01:00
co-authored by Claude Sonnet 4.6
parent 7c12499783
commit 8e179736ce
8 changed files with 256 additions and 256 deletions
Download Patch File Download Diff File Expand all files Collapse all files
graphify/skill-aider.md
+32 -32
View File
@@ -78,12 +78,12 @@ mkdir -p graphify-out
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.**
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
@@ -170,7 +170,7 @@ Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is determin
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
@@ -204,7 +204,7 @@ Print: `"Semantic extraction: N files (sequential — Aider)"`
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
@@ -282,7 +282,7 @@ print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens'
Save new results to cache:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
@@ -295,7 +295,7 @@ print(f'Cached {saved} files')
Merge cached + new results into `.graphify_semantic.json`:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -328,7 +328,7 @@ Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphi
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
@@ -363,7 +363,7 @@ print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(s
```bash
mkdir -p graphify-out
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
@@ -416,7 +416,7 @@ Read `.graphify_analysis.json`. For each community key, look at its node labels
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
@@ -456,7 +456,7 @@ Replace INPUT_PATH with the actual path.
If `--obsidian` was given:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
@@ -487,7 +487,7 @@ print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries
Generate the HTML graph (always, unless `--no-viz`):
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
@@ -514,7 +514,7 @@ else:
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
@@ -529,7 +529,7 @@ print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt'
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
@@ -551,7 +551,7 @@ Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default
### Step 7b - SVG export (only if --svg flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
@@ -573,7 +573,7 @@ print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
### Step 7c - GraphML export (only if --graphml flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
@@ -615,7 +615,7 @@ To configure in Claude Desktop, add to `claude_desktop_config.json`:
If `total_words` from `.graphify_detect.json` is greater than 5,000, run:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
@@ -633,7 +633,7 @@ Print the output directly in chat. If `total_words <= 5000`, skip silently - the
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
@@ -707,7 +707,7 @@ The graph is the map. Your job after the pipeline is to be the guide.
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
@@ -730,7 +730,7 @@ if new_total > 0:
If new files exist, first check whether all changed files are code files:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -765,7 +765,7 @@ fi
Then:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
@@ -792,7 +792,7 @@ Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
@@ -826,7 +826,7 @@ Clean up after: `rm -f .graphify_old.json`
Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
@@ -879,7 +879,7 @@ Two traversal modes - choose based on the question:
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -897,7 +897,7 @@ Load `graphify-out/graph.json`, then:
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
@@ -988,7 +988,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
After writing the answer, save it back into the graph so it improves future queries:
```bash
$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1001,7 +1001,7 @@ Find the shortest path between two named concepts in the graph.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1011,7 +1011,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1063,7 +1063,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
@@ -1074,7 +1074,7 @@ Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1084,7 +1084,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1129,7 +1129,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
---
@@ -1139,7 +1139,7 @@ $(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" -
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
graphify/skill-amp.md
+32 -32
View File
@@ -79,12 +79,12 @@ fi
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.**
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
@@ -171,7 +171,7 @@ Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is determin
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
@@ -209,7 +209,7 @@ Before dispatching subagents, print a timing estimate:
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
@@ -337,7 +337,7 @@ print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens'
Save new results to cache:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
@@ -350,7 +350,7 @@ print(f'Cached {saved} files')
Merge cached + new results into `.graphify_semantic.json`:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -383,7 +383,7 @@ Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphi
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
@@ -418,7 +418,7 @@ print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(s
```bash
mkdir -p graphify-out
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
@@ -471,7 +471,7 @@ Read `.graphify_analysis.json`. For each community key, look at its node labels
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
@@ -511,7 +511,7 @@ Replace INPUT_PATH with the actual path.
If `--obsidian` was given:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
@@ -542,7 +542,7 @@ print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries
Generate the HTML graph (always, unless `--no-viz`):
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
@@ -569,7 +569,7 @@ else:
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
@@ -584,7 +584,7 @@ print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt'
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
@@ -606,7 +606,7 @@ Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default
### Step 7b - SVG export (only if --svg flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
@@ -628,7 +628,7 @@ print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
### Step 7c - GraphML export (only if --graphml flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
@@ -670,7 +670,7 @@ To configure in Claude Desktop, add to `claude_desktop_config.json`:
If `total_words` from `.graphify_detect.json` is greater than 5,000, run:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
@@ -688,7 +688,7 @@ Print the output directly in chat. If `total_words <= 5000`, skip silently - the
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
@@ -762,7 +762,7 @@ The graph is the map. Your job after the pipeline is to be the guide.
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
@@ -785,7 +785,7 @@ if new_total > 0:
If new files exist, first check whether all changed files are code files:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -820,7 +820,7 @@ fi
Then:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
@@ -847,7 +847,7 @@ Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
@@ -881,7 +881,7 @@ Clean up after: `rm -f .graphify_old.json`
Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
@@ -934,7 +934,7 @@ Two traversal modes - choose based on the question:
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -952,7 +952,7 @@ Load `graphify-out/graph.json`, then:
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
@@ -1043,7 +1043,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
After writing the answer, save it back into the graph so it improves future queries:
```bash
$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1056,7 +1056,7 @@ Find the shortest path between two named concepts in the graph.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1066,7 +1066,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1118,7 +1118,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
@@ -1129,7 +1129,7 @@ Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1139,7 +1139,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1184,7 +1184,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
---
@@ -1194,7 +1194,7 @@ $(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" -
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
graphify/skill-claw.md
+32 -32
View File
@@ -78,12 +78,12 @@ mkdir -p graphify-out
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.**
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
@@ -170,7 +170,7 @@ Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is determin
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
@@ -204,7 +204,7 @@ Print: `"Semantic extraction: N files (sequential — OpenClaw)"`
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
@@ -282,7 +282,7 @@ print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens'
Save new results to cache:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
@@ -295,7 +295,7 @@ print(f'Cached {saved} files')
Merge cached + new results into `.graphify_semantic.json`:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -328,7 +328,7 @@ Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphi
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
@@ -363,7 +363,7 @@ print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(s
```bash
mkdir -p graphify-out
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
@@ -416,7 +416,7 @@ Read `.graphify_analysis.json`. For each community key, look at its node labels
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
@@ -456,7 +456,7 @@ Replace INPUT_PATH with the actual path.
If `--obsidian` was given:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
@@ -487,7 +487,7 @@ print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries
Generate the HTML graph (always, unless `--no-viz`):
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
@@ -514,7 +514,7 @@ else:
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
@@ -529,7 +529,7 @@ print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt'
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
@@ -551,7 +551,7 @@ Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default
### Step 7b - SVG export (only if --svg flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
@@ -573,7 +573,7 @@ print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
### Step 7c - GraphML export (only if --graphml flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
@@ -615,7 +615,7 @@ To configure in Claude Desktop, add to `claude_desktop_config.json`:
If `total_words` from `.graphify_detect.json` is greater than 5,000, run:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
@@ -633,7 +633,7 @@ Print the output directly in chat. If `total_words <= 5000`, skip silently - the
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
@@ -707,7 +707,7 @@ The graph is the map. Your job after the pipeline is to be the guide.
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
@@ -730,7 +730,7 @@ if new_total > 0:
If new files exist, first check whether all changed files are code files:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -765,7 +765,7 @@ fi
Then:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
@@ -792,7 +792,7 @@ Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
@@ -826,7 +826,7 @@ Clean up after: `rm -f .graphify_old.json`
Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
@@ -879,7 +879,7 @@ Two traversal modes - choose based on the question:
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -897,7 +897,7 @@ Load `graphify-out/graph.json`, then:
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
@@ -988,7 +988,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
After writing the answer, save it back into the graph so it improves future queries:
```bash
$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1001,7 +1001,7 @@ Find the shortest path between two named concepts in the graph.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1011,7 +1011,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1063,7 +1063,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
@@ -1074,7 +1074,7 @@ Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1084,7 +1084,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1129,7 +1129,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
---
@@ -1139,7 +1139,7 @@ $(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" -
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
graphify/skill-codex.md
+32 -32
View File
@@ -79,12 +79,12 @@ fi
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.**
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
@@ -171,7 +171,7 @@ Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is determin
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
@@ -209,7 +209,7 @@ Before dispatching subagents, print a timing estimate:
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
@@ -348,7 +348,7 @@ print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens'
Save new results to cache:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
@@ -361,7 +361,7 @@ print(f'Cached {saved} files')
Merge cached + new results into `.graphify_semantic.json`:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from graphify.semantic_cleanup import sanitize_semantic_fragment
@@ -396,7 +396,7 @@ Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphi
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
from graphify.semantic_cleanup import sanitize_semantic_fragment
@@ -433,7 +433,7 @@ print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(s
```bash
mkdir -p graphify-out
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
@@ -486,7 +486,7 @@ Read `.graphify_analysis.json`. For each community key, look at its node labels
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
@@ -526,7 +526,7 @@ Replace INPUT_PATH with the actual path.
If `--obsidian` was given:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
@@ -557,7 +557,7 @@ print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries
Generate the HTML graph (always, unless `--no-viz`):
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
@@ -584,7 +584,7 @@ else:
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
@@ -599,7 +599,7 @@ print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt'
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
@@ -621,7 +621,7 @@ Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default
### Step 7b - SVG export (only if --svg flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
@@ -643,7 +643,7 @@ print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
### Step 7c - GraphML export (only if --graphml flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
@@ -685,7 +685,7 @@ To configure in Claude Desktop, add to `claude_desktop_config.json`:
If `total_words` from `.graphify_detect.json` is greater than 5,000, run:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
@@ -703,7 +703,7 @@ Print the output directly in chat. If `total_words <= 5000`, skip silently - the
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
@@ -777,7 +777,7 @@ The graph is the map. Your job after the pipeline is to be the guide.
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
@@ -800,7 +800,7 @@ if new_total > 0:
If new files exist, first check whether all changed files are code files:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -835,7 +835,7 @@ fi
Then:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
@@ -862,7 +862,7 @@ Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
@@ -896,7 +896,7 @@ Clean up after: `rm -f .graphify_old.json`
Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
@@ -949,7 +949,7 @@ Two traversal modes - choose based on the question:
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -967,7 +967,7 @@ Load `graphify-out/graph.json`, then:
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
@@ -1058,7 +1058,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
After writing the answer, save it back into the graph so it improves future queries:
```bash
$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1071,7 +1071,7 @@ Find the shortest path between two named concepts in the graph.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1081,7 +1081,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1133,7 +1133,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
@@ -1144,7 +1144,7 @@ Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1154,7 +1154,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1199,7 +1199,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
---
@@ -1209,7 +1209,7 @@ $(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" -
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
graphify/skill-droid.md
+32 -32
View File
@@ -78,12 +78,12 @@ mkdir -p graphify-out
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.**
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
@@ -170,7 +170,7 @@ Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is determin
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
@@ -208,7 +208,7 @@ Before dispatching subagents, print a timing estimate:
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
@@ -338,7 +338,7 @@ print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens'
Save new results to cache:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
@@ -351,7 +351,7 @@ print(f'Cached {saved} files')
Merge cached + new results into `.graphify_semantic.json`:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -384,7 +384,7 @@ Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphi
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
@@ -419,7 +419,7 @@ print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(s
```bash
mkdir -p graphify-out
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
@@ -472,7 +472,7 @@ Read `.graphify_analysis.json`. For each community key, look at its node labels
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
@@ -512,7 +512,7 @@ Replace INPUT_PATH with the actual path.
If `--obsidian` was given:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
@@ -543,7 +543,7 @@ print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries
Generate the HTML graph (always, unless `--no-viz`):
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
@@ -570,7 +570,7 @@ else:
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
@@ -585,7 +585,7 @@ print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt'
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
@@ -607,7 +607,7 @@ Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default
### Step 7b - SVG export (only if --svg flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
@@ -629,7 +629,7 @@ print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
### Step 7c - GraphML export (only if --graphml flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
@@ -671,7 +671,7 @@ To configure in Claude Desktop, add to `claude_desktop_config.json`:
If `total_words` from `.graphify_detect.json` is greater than 5,000, run:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
@@ -689,7 +689,7 @@ Print the output directly in chat. If `total_words <= 5000`, skip silently - the
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
@@ -763,7 +763,7 @@ The graph is the map. Your job after the pipeline is to be the guide.
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
@@ -786,7 +786,7 @@ if new_total > 0:
If new files exist, first check whether all changed files are code files:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -821,7 +821,7 @@ fi
Then:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
@@ -848,7 +848,7 @@ Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
@@ -882,7 +882,7 @@ Clean up after: `rm -f .graphify_old.json`
Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
@@ -935,7 +935,7 @@ Two traversal modes - choose based on the question:
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -953,7 +953,7 @@ Load `graphify-out/graph.json`, then:
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
@@ -1044,7 +1044,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
After writing the answer, save it back into the graph so it improves future queries:
```bash
$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1057,7 +1057,7 @@ Find the shortest path between two named concepts in the graph.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1067,7 +1067,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1119,7 +1119,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
@@ -1130,7 +1130,7 @@ Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1140,7 +1140,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1185,7 +1185,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
---
@@ -1195,7 +1195,7 @@ $(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" -
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
graphify/skill-kiro.md
+32 -32
View File
@@ -77,12 +77,12 @@ mkdir -p graphify-out
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.**
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
@@ -169,7 +169,7 @@ Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is determin
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
@@ -203,7 +203,7 @@ Print: `"Semantic extraction: N files (sequential — OpenClaw)"`
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
@@ -281,7 +281,7 @@ print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens'
Save new results to cache:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
@@ -294,7 +294,7 @@ print(f'Cached {saved} files')
Merge cached + new results into `.graphify_semantic.json`:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -327,7 +327,7 @@ Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphi
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
@@ -362,7 +362,7 @@ print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(s
```bash
mkdir -p graphify-out
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
@@ -415,7 +415,7 @@ Read `.graphify_analysis.json`. For each community key, look at its node labels
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
@@ -455,7 +455,7 @@ Replace INPUT_PATH with the actual path.
If `--obsidian` was given:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
@@ -486,7 +486,7 @@ print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries
Generate the HTML graph (always, unless `--no-viz`):
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
@@ -513,7 +513,7 @@ else:
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
@@ -528,7 +528,7 @@ print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt'
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
@@ -550,7 +550,7 @@ Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default
### Step 7b - SVG export (only if --svg flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
@@ -572,7 +572,7 @@ print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
### Step 7c - GraphML export (only if --graphml flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
@@ -614,7 +614,7 @@ To configure in Claude Desktop, add to `claude_desktop_config.json`:
If `total_words` from `.graphify_detect.json` is greater than 5,000, run:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
@@ -632,7 +632,7 @@ Print the output directly in chat. If `total_words <= 5000`, skip silently - the
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
@@ -706,7 +706,7 @@ The graph is the map. Your job after the pipeline is to be the guide.
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
@@ -729,7 +729,7 @@ if new_total > 0:
If new files exist, first check whether all changed files are code files:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -764,7 +764,7 @@ fi
Then:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
@@ -791,7 +791,7 @@ Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
@@ -825,7 +825,7 @@ Clean up after: `rm -f .graphify_old.json`
Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
@@ -878,7 +878,7 @@ Two traversal modes - choose based on the question:
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -896,7 +896,7 @@ Load `graphify-out/graph.json`, then:
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
@@ -987,7 +987,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
After writing the answer, save it back into the graph so it improves future queries:
```bash
$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1000,7 +1000,7 @@ Find the shortest path between two named concepts in the graph.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1010,7 +1010,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1062,7 +1062,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
@@ -1073,7 +1073,7 @@ Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1083,7 +1083,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1128,7 +1128,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
---
@@ -1138,7 +1138,7 @@ $(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" -
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
graphify/skill-pi.md
+32 -32
View File
@@ -77,12 +77,12 @@ mkdir -p graphify-out
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.**
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
@@ -169,7 +169,7 @@ Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is determin
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
@@ -203,7 +203,7 @@ Print: `"Semantic extraction: N files (sequential — OpenClaw)"`
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
@@ -281,7 +281,7 @@ print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens'
Save new results to cache:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
@@ -294,7 +294,7 @@ print(f'Cached {saved} files')
Merge cached + new results into `.graphify_semantic.json`:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -327,7 +327,7 @@ Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphi
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
@@ -362,7 +362,7 @@ print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(s
```bash
mkdir -p graphify-out
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
@@ -415,7 +415,7 @@ Read `.graphify_analysis.json`. For each community key, look at its node labels
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
@@ -455,7 +455,7 @@ Replace INPUT_PATH with the actual path.
If `--obsidian` was given:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
@@ -486,7 +486,7 @@ print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries
Generate the HTML graph (always, unless `--no-viz`):
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
@@ -513,7 +513,7 @@ else:
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
@@ -528,7 +528,7 @@ print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt'
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
@@ -550,7 +550,7 @@ Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default
### Step 7b - SVG export (only if --svg flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
@@ -572,7 +572,7 @@ print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
### Step 7c - GraphML export (only if --graphml flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
@@ -614,7 +614,7 @@ To configure in Claude Desktop, add to `claude_desktop_config.json`:
If `total_words` from `.graphify_detect.json` is greater than 5,000, run:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
@@ -632,7 +632,7 @@ Print the output directly in chat. If `total_words <= 5000`, skip silently - the
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
@@ -706,7 +706,7 @@ The graph is the map. Your job after the pipeline is to be the guide.
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
@@ -729,7 +729,7 @@ if new_total > 0:
If new files exist, first check whether all changed files are code files:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -764,7 +764,7 @@ fi
Then:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
@@ -791,7 +791,7 @@ Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
@@ -825,7 +825,7 @@ Clean up after: `rm -f .graphify_old.json`
Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
@@ -878,7 +878,7 @@ Two traversal modes - choose based on the question:
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -896,7 +896,7 @@ Load `graphify-out/graph.json`, then:
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
@@ -987,7 +987,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
After writing the answer, save it back into the graph so it improves future queries:
```bash
$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1000,7 +1000,7 @@ Find the shortest path between two named concepts in the graph.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1010,7 +1010,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1062,7 +1062,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
@@ -1073,7 +1073,7 @@ Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1083,7 +1083,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1128,7 +1128,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
---
@@ -1138,7 +1138,7 @@ $(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" -
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
graphify/skill-trae.md
+32 -32
View File
@@ -77,12 +77,12 @@ fi
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.**
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
@@ -169,7 +169,7 @@ Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is determin
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
@@ -207,7 +207,7 @@ Before dispatching subagents, print a timing estimate:
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
@@ -334,7 +334,7 @@ print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens'
Save new results to cache:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
@@ -347,7 +347,7 @@ print(f'Cached {saved} files')
Merge cached + new results into `.graphify_semantic.json`:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -380,7 +380,7 @@ Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphi
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
@@ -414,7 +414,7 @@ print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(s
```bash
mkdir -p graphify-out
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
@@ -466,7 +466,7 @@ Read `.graphify_analysis.json`. For each community key, look at its node labels
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
@@ -504,7 +504,7 @@ Replace INPUT_PATH with the actual path.
If `--obsidian` was given:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
@@ -535,7 +535,7 @@ print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries
Generate the HTML graph (always, unless `--no-viz`):
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
@@ -562,7 +562,7 @@ else:
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
@@ -577,7 +577,7 @@ print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt'
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
@@ -599,7 +599,7 @@ Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default
### Step 7b - SVG export (only if --svg flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
@@ -621,7 +621,7 @@ print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
### Step 7c - GraphML export (only if --graphml flag)
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
@@ -651,7 +651,7 @@ This starts a stdio MCP server that exposes tools: `query_graph`, `get_node`, `g
If `total_words` from `.graphify_detect.json` is greater than 5,000, run:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
@@ -669,7 +669,7 @@ Print the output directly in chat. If `total_words <= 5000`, skip silently - the
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
@@ -741,7 +741,7 @@ The graph is the map. Your job after the pipeline is to be the guide.
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
@@ -764,7 +764,7 @@ if new_total > 0:
If new files exist, first check whether all changed files are code files:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
@@ -799,7 +799,7 @@ fi
Then:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
@@ -823,7 +823,7 @@ Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
@@ -856,7 +856,7 @@ Clean up after: `rm -f .graphify_old.json`
Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
@@ -909,7 +909,7 @@ Two traversal modes - choose based on the question:
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -927,7 +927,7 @@ Load `graphify-out/graph.json`, then:
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
@@ -1012,7 +1012,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
After writing the answer, save it back into the graph so it improves future queries:
```bash
$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1025,7 +1025,7 @@ Find the shortest path between two named concepts in the graph.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1035,7 +1035,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1087,7 +1087,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
@@ -1098,7 +1098,7 @@ Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
@@ -1108,7 +1108,7 @@ if not Path('graphify-out/graph.json').exists():
If it fails, stop and tell the user to run `/graphify <path>` first.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
@@ -1152,7 +1152,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
After writing the explanation, save it back:
```bash
$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
---
@@ -1162,7 +1162,7 @@ $(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" -
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat .graphify_python) -c "
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path