python-docs

A documentation tool for Python projects that creates and updates written guides from source code. It can also produce API references and Mermaid diagrams, which are text-based diagrams.

In plain words
What is it for?
Documenting modules, generating API documentation, drawing architecture diagrams, and updating docs after code changes.
Why use it?
It helps keep documentation aligned with the code and organizes it by Python package or module.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/arnabdeypolimi/claude_code_setup/python-docs
Any agent
npx skills add arnabdeypolimi/claude_code_setup --skill python-docs
Clone the repo
git clone --depth 1 https://github.com/arnabdeypolimi/claude_code_setup

Made for: Claude Code, Codex.

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00098 $0.01585
Opus 5 $0.00049 $0.00792
Sonnet 5 $0.00020 $0.00317
Haiku 4.5 $0.00010 $0.00159

Measured 2d ago against content hash ffce35306506, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/python-docs/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Documentation

Generate and maintain documentation for Python projects by analyzing source code.

Docs Folder Layout

docs/
├── README.md                  # Project-level documentation index
├── artalk/                    # ARTalk package docs (maps to src/artalk/)
│   ├── README.md             # ARTalk docs index with module table
│   ├── architecture.md       # System architecture with Mermaid diagrams
│   ├── core.md               # Core types, config, constants
│   └── pipeline.md           # High-level orchestration API
└── modules/                   # Non-ARTalk module docs (maps to other src/ packages)
    ├── _template.md          # Template for new module docs
    ├── logging_utils.md      # Logging utilities (maps to src/logging_utils/)
    └── segmentation.md       # Segmentation module (maps to src/segmentation/)

File Placement Rules

Source location Doc location Index to update
src/artalk/ docs/artalk/<module>.md docs/artalk/README.md module table
src/artalk/ (architecture) docs/artalk/architecture.md docs/artalk/README.md module table
src/<other_pkg>/ docs/modules/<pkg>.md docs/README.md structure tree
  • ARTalk sub-module docs go in docs/artalk/ (e.g., motion.md, renderer.md, tracking.md)
  • Non-ARTalk package docs go in docs/modules/
  • New module doc template lives at docs/modules/_template.md
  • Cross-references between artalk docs use relative paths: [core.md](core.md)
  • Cross-references from modules/ to artalk/ use: [artalk](../artalk/)

After Creating/Moving Any Doc

  1. Update the relevant index (docs/artalk/README.md or docs/README.md)
  2. Fix all cross-reference links affected by the change
  3. Verify no broken relative links remain

Workflow Selection

Request Workflow
Document a module Create Module Doc
Architecture / system diagram Create Architecture Doc
Code changed, update docs Sync Docs
Check doc accuracy Sync Docs (audit mode)

Read the full file on GitHub · 132 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 132 lines · 98 tokens per session scan A ffce35306506

Subscribe to this mod's changes

python-docs is a skill published in the GitHub repository arnabdeypolimi/claude_code_setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 1,585 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

pytorch

Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.

itsmostafa/llm-engineering-skills · 40 tokens

modelcontextprotocol-python-sdk-context

Answers questions about the official Model Context Protocol (MCP) Python SDK (mcp package on PyPI, modelcontextprotocol/python-sdk on GitHub). Tracks the main branch (v2 pre-alpha — MCPServer/snakecase/constructor-on handlers). Use when working with MCP servers or clients in Python, debugging v1→v2 migrations, or…

nick-railsback/skill-engine · 116 tokens

docker-py

Provides patterns for programmatic Docker container management using the Docker SDK for Python and aiodocker. USE WHEN the user asks to "manage Docker containers from Python", "create containers programmatically", "stream container logs", "execute commands in a running container", "build images with docker-py"…

AnExiledDev/CodeForge · 109 tokens

fastapi

Teaches modern FastAPI development including REST APIs, Pydantic v2 models, SSE streaming, and ASGI middleware patterns. USE WHEN the user asks to "build a FastAPI app", "create a REST API with FastAPI", "add SSE streaming", "use dependency injection in FastAPI", "define Pydantic models", "stream LLM responses", "add…

AnExiledDev/CodeForge · 131 tokens

pydantic-ai

Teaches PydanticAI agent development with tool decorators, RunContext dependency injection, streaming, and VercelAIAdapter. USE WHEN the user asks to "build a PydanticAI agent", "add tools to an agent", "stream responses with PydanticAI", "test a PydanticAI agent", "connect PydanticAI to Svelte", "configure model…

AnExiledDev/CodeForge · 130 tokens

bump-dependency

Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.

home-assistant/core · 42 tokens