docs-from-code

Name: docs-from-code
Author: Varnan-Tech

26installs59forks

How to install docs-from-code?

varnan-tech/opendirectory/docs-from-code

$npx -y skills add Varnan-Tech/opendirectory --skill docs-from-code

Installs into the current project.

Summary

Generates and updates README.md and API reference docs by reading your codebase's functions, routes, types, schemas, and architecture. Uses graphify to build a knowledge graph first, then writes accurate docs from it. Use when asked to write docs, generate a README, document an A

Files · 1

View on GitHub

SKILL.md

1	# docs-from-code
2
3	You are a technical writer. Your job is to generate accurate, developer-friendly docs by first building a knowledge graph of the codebase with graphify, then using that graph to write docs grounded in what actually exists.
4
5	DO NOT invent code. If you cannot find a clear description for something, write `[Description needed]`. Accurate but sparse docs are better than confident but wrong docs.
6
7	Before starting: Confirm you are inside a codebase directory. If the user pointed you at a remote repo, clone it first. If neither, ask: "Can you point me to the project directory or repository URL?"
8
9	---
10
11	## Workflow
12
13	### Step 1: Install graphify and Build the Knowledge Graph
14
15	graphify uses tree-sitter AST (20 languages, no LLM) for code structure and Claude subagents for semantic understanding of docs and comments.
16
17	```bash
18	pip install graphifyy
19	graphify . --no-viz
20	```
21
22	`--no-viz` skips HTML output. You only need `GRAPH_REPORT.md` and `graph.json`.
23
24	This produces `graphify-out/` in the project root:
25	- `GRAPH_REPORT.md` — god nodes, community clusters, surprising connections, suggested questions
26	- `graph.json` — full queryable knowledge graph (persistent, SHA256-cached)
27
28	QA: Did `graphify-out/GRAPH_REPORT.md` get created? How many nodes and edges? If graphify fails, go to Step 1B.
29
30	#### Step 1B: Fallback (if graphify unavailable)
31
32	```bash
33	# TypeScript/JS projects:
34	cd <skill-directory>/scripts && npm install
35	npx ts-node extract_ts.ts <project-root> <project-root>/.docs-extract.json
36
37	# Python projects:
38	python3 <skill-directory>/scripts/extract_py.py <project-root> <project-root>/.docs-extract.json
39	```
40
41	Read `references/extraction-guide.md` for framework-specific notes on the fallback output.
42
43	---
44
45	### Step 2: Read the Graph Report
46
47	Read `graphify-out/GRAPH_REPORT.md` in full. This gives you:
48	- God nodes — highest-degree concepts (what everything connects through). Use these for the Architecture section.
49	- Community clusters — logical groupings of related code. Use these for module documentation.
50	- Surprising connections — non-obvious cross-file relationships. Note these in Architecture.
51	- Suggested questions — graphify's assessment of what is worth documenting.
52
53	Then run targeted queries for specific doc sections:
54
55	```bash
56	# API routes
57	graphify query "show all API routes and endpoints" --graph graphify-out/graph.json
58
59	# Data models
60	graphify query "what are the main data models and types?" --graph graphify-out/graph.json
61
62	# Auth flow
63	graphify query "how does authentication work?" --graph graphify-out/graph.json
64
65	# Entry points
66	graphify query "what is the entry point and how is the app initialised?" --graph graphify-out/graph.json
67	```
68
69	Each query returns a focused subgraph. Relationships are tagged `EXTRACTED` (found in source) or `INFERRED` (with confidence score). Trust `EXTRACTED` fully. Use `INFERRED` but flag uncertainty.
70
71	QA: Cross-check 2-3 routes from the query against actual source files before writing docs.
72
73	---
74
75	### Step 3: Read Existing Documentation
76
77	Before writing anything new, check what already exists:
78
79	1. Read `README.md` if present. Note which sections exist and which are stale or missing.
80	2. Read `docs/API.md`, `docs/api.md`, or `API.md` if present.
81	3. Read `CHANGELOG.md` for context on recent changes worth noting.
82
83	Decide what to generate:
84	- No README — generate a full README from Template 1 in `references/output-template.md`
85	- README exists, API section stale — update only that section (Template 3)
86	- README exists, fully outdated — ask: "Your README exists but appears outdated. Rewrite fully or update specific sections?"
87
88	QA: List exactly what you will write or update before starting.
89
90	---
91
92	### Step 4: Generate Documentation
93
94	Read `references/output-template.md` for the exact templates to use.
95
96	README — Project Description:
97	From `package.json` or `pyproject.toml` description + god nodes summary from `GRAPH_REPORT.md`.
98
99	README — Architecture Section:
100	Use god nodes and community clusters to write a plain-English architecture overview. Example:
101	> "The system is organised around 3 core modules: `AuthService` (god node, connects to 14 other components), `DatabaseAdapter` (bridges all data access), and `EventBus` (central to async flows). The auth and request-handling modules are

Varnan-TechPublisher · 70 listings

Preview

Varnan-Tech/opendirectory

# docs-from-code

You are a technical writer. Your job is to generate accurate, developer-friendly docs by first building a knowledge graph of the codebase with graphify, then us

**DO NOT invent code.** If you cannot find a clear description for something, write `[Description needed]`. Accurate but sparse docs are better than confident b

**Before starting:** Confirm you are inside a codebase directory. If the user pointed you at a remote repo, clone it first. If neither, ask: "Can you point me t

RepoVarnan-Tech/opendirectory

LicenseMIT

TypeSkills

CategoryDocumentation

UpdatedJul 2026

Repo stars550

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type

docs-from-code

26installs59forks

View on GitHub

How to install docs-from-code?

varnan-tech/opendirectory/docs-from-code

$npx -y skills add Varnan-Tech/opendirectory --skill docs-from-code

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# docs-from-code
2
3	You are a technical writer. Your job is to generate accurate, developer-friendly docs by first building a knowledge graph of the codebase with graphify, then using that graph to write docs grounded in what actually exists.
4
5	DO NOT invent code. If you cannot find a clear description for something, write `[Description needed]`. Accurate but sparse docs are better than confident but wrong docs.
6
7	Before starting: Confirm you are inside a codebase directory. If the user pointed you at a remote repo, clone it first. If neither, ask: "Can you point me to the project directory or repository URL?"
8
9	---
10
11	## Workflow
12
13	### Step 1: Install graphify and Build the Knowledge Graph
14
15	graphify uses tree-sitter AST (20 languages, no LLM) for code structure and Claude subagents for semantic understanding of docs and comments.
16
17	```bash
18	pip install graphifyy
19	graphify . --no-viz
20	```
21
22	`--no-viz` skips HTML output. You only need `GRAPH_REPORT.md` and `graph.json`.
23
24	This produces `graphify-out/` in the project root:
25	- `GRAPH_REPORT.md` — god nodes, community clusters, surprising connections, suggested questions
26	- `graph.json` — full queryable knowledge graph (persistent, SHA256-cached)
27
28	QA: Did `graphify-out/GRAPH_REPORT.md` get created? How many nodes and edges? If graphify fails, go to Step 1B.
29
30	#### Step 1B: Fallback (if graphify unavailable)
31
32	```bash
33	# TypeScript/JS projects:
34	cd <skill-directory>/scripts && npm install
35	npx ts-node extract_ts.ts <project-root> <project-root>/.docs-extract.json
36
37	# Python projects:
38	python3 <skill-directory>/scripts/extract_py.py <project-root> <project-root>/.docs-extract.json
39	```
40
41	Read `references/extraction-guide.md` for framework-specific notes on the fallback output.
42
43	---
44
45	### Step 2: Read the Graph Report
46
47	Read `graphify-out/GRAPH_REPORT.md` in full. This gives you:
48	- God nodes — highest-degree concepts (what everything connects through). Use these for the Architecture section.
49	- Community clusters — logical groupings of related code. Use these for module documentation.
50	- Surprising connections — non-obvious cross-file relationships. Note these in Architecture.
51	- Suggested questions — graphify's assessment of what is worth documenting.
52
53	Then run targeted queries for specific doc sections:
54
55	```bash
56	# API routes
57	graphify query "show all API routes and endpoints" --graph graphify-out/graph.json
58
59	# Data models
60	graphify query "what are the main data models and types?" --graph graphify-out/graph.json
61
62	# Auth flow
63	graphify query "how does authentication work?" --graph graphify-out/graph.json
64
65	# Entry points
66	graphify query "what is the entry point and how is the app initialised?" --graph graphify-out/graph.json
67	```
68
69	Each query returns a focused subgraph. Relationships are tagged `EXTRACTED` (found in source) or `INFERRED` (with confidence score). Trust `EXTRACTED` fully. Use `INFERRED` but flag uncertainty.
70
71	QA: Cross-check 2-3 routes from the query against actual source files before writing docs.
72
73	---
74
75	### Step 3: Read Existing Documentation
76
77	Before writing anything new, check what already exists:
78
79	1. Read `README.md` if present. Note which sections exist and which are stale or missing.
80	2. Read `docs/API.md`, `docs/api.md`, or `API.md` if present.
81	3. Read `CHANGELOG.md` for context on recent changes worth noting.
82
83	Decide what to generate:
84	- No README — generate a full README from Template 1 in `references/output-template.md`
85	- README exists, API section stale — update only that section (Template 3)
86	- README exists, fully outdated — ask: "Your README exists but appears outdated. Rewrite fully or update specific sections?"
87
88	QA: List exactly what you will write or update before starting.
89
90	---
91
92	### Step 4: Generate Documentation
93
94	Read `references/output-template.md` for the exact templates to use.
95
96	README — Project Description:
97	From `package.json` or `pyproject.toml` description + god nodes summary from `GRAPH_REPORT.md`.
98
99	README — Architecture Section:
100	Use god nodes and community clusters to write a plain-English architecture overview. Example:
101	> "The system is organised around 3 core modules: `AuthService` (god node, connects to 14 other components), `DatabaseAdapter` (bridges all data access), and `EventBus` (central to async flows). The auth and request-handling modules are

Varnan-TechPublisher · 70 listings

Preview

Varnan-Tech/opendirectory

# docs-from-code

You are a technical writer. Your job is to generate accurate, developer-friendly docs by first building a knowledge graph of the codebase with graphify, then us

**DO NOT invent code.** If you cannot find a clear description for something, write `[Description needed]`. Accurate but sparse docs are better than confident b

**Before starting:** Confirm you are inside a codebase directory. If the user pointed you at a remote repo, clone it first. If neither, ask: "Can you point me t

RepoVarnan-Tech/opendirectory

LicenseMIT

TypeSkills

CategoryDocumentation

UpdatedJul 2026

Repo stars550

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type