How do I install the Doc Generator skill?

Run npx skillmds@latest add tomevault-io/doc-generator-5 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Doc Generator safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Doc Generator?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Doc Generator free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Doc Generator?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Doc Generator by tomevault-io — Agent Skill

Name: Doc Generator
Author: tomevault-io

Doc Generator

Generates comprehensive documentation from Python source code. Analyzes modules, classes, and functions using AST parsing and AI interpretation, then outputs Sphinx RST or MkDocs Markdown docs. Identifies missing docstrings and generates them. Writes a DOCS_REPORT.md with coverage stats. Use when you need to document an existing Python project or fill in missing docstrings.

tomevault-io Updated Sep 17, 2026

File contents

doc-generator

Python source → polished documentation. Nanobot reads your code and writes the docs.

Usage

@Nanobot doc-generator --path src/ --format mkdocs
@Nanobot doc-generator --path src/ --format sphinx
@Nanobot doc-generator --path src/core/engine.py --fill-docstrings
@Nanobot doc-generator --path src/ --output docs/

What It Does

Parse: AST-parses all .py files — extracts modules, classes, functions, type hints
Audit: Identifies missing docstrings, undocumented parameters, no return type annotations
Generate: Creates one doc file per module. AI writes docstrings for undocumented items if --fill-docstrings
Structure: Builds navigation tree (MkDocs: mkdocs.yml nav section; Sphinx: index.rst toctree)
Report: Writes DOCS_REPORT.md with coverage stats

Files Created

docs/
  api/<module_name>.md          # (MkDocs format) or .rst (Sphinx)
  index.md                      # Home page with project overview
DOCS_REPORT.md                  # Docstring coverage %, missing items list
mkdocs.yml                      # (if --format mkdocs and not present)

DOCS_REPORT.md Contents

Overall docstring coverage: XX%
Modules with 0% coverage (list)
Functions with missing return-type annotations
Parameters with no type hints

Formats

Format	Files	Preview
MkDocs	`.md` files + `mkdocs.yml`	`mkdocs serve`
Sphinx	`.rst` files + `conf.py`	`make html`

Fill Docstrings Mode

With --fill-docstrings, Nanobot reads the function implementation and writes a docstring inline — it modifies your source files. Review with git diff before committing.

Philosophy

Documentation generated from code is always in danger of drifting. The report's coverage stats are designed to be run in CI — fail the build when docstring coverage drops below a threshold.

Source: mk-knight23/AI-Agent-Nanobot — distributed by TomeVault.

---name: doc-generator-5description: Generates comprehensive documentation from Python source code. Analyzes modules, classes, and functions using AST parsing and AI interpretation, then outputs Sphinx RST or MkDocs Markdown docs. Identifies missing docstrings and generates them. Writes a DOCS_REPORT.md with coverage stats. Use when you need to document an existing Python project or fill in missing docstrings.---# doc-generatorPython source → polished documentation. Nanobot reads your code and writes the docs.## Usage```@Nanobot doc-generator --path src/ --format mkdocs@Nanobot doc-generator --path src/ --format sphinx@Nanobot doc-generator --path src/core/engine.py --fill-docstrings@Nanobot doc-generator --path src/ --output docs/```## What It Does1. **Parse**: AST-parses all `.py` files — extracts modules, classes, functions, type hints2. **Audit**: Identifies missing docstrings, undocumented parameters, no return type annotations3. **Generate**: Creates one doc file per module. AI writes docstrings for undocumented items if `--fill-docstrings`4. **Structure**: Builds navigation tree (MkDocs: `mkdocs.yml` nav section; Sphinx: `index.rst` toctree)5. **Report**: Writes `DOCS_REPORT.md` with coverage stats## Files Created```docs/ api/<module_name>.md # (MkDocs format) or .rst (Sphinx) index.md # Home page with project overviewDOCS_REPORT.md # Docstring coverage %, missing items listmkdocs.yml # (if --format mkdocs and not present)```## DOCS_REPORT.md Contents- Overall docstring coverage: XX%- Modules with 0% coverage (list)- Functions with missing return-type annotations- Parameters with no type hints## Formats| Format | Files | Preview ||--------|-------|---------|| MkDocs | `.md` files + `mkdocs.yml` | `mkdocs serve` || Sphinx | `.rst` files + `conf.py` | `make html` |## Fill Docstrings ModeWith `--fill-docstrings`, Nanobot reads the function implementation and writes a docstring inline — it modifies your source files. Review with `git diff` before committing.## PhilosophyDocumentation generated from code is always in danger of drifting. The report's coverage stats are designed to be run in CI — fail the build when docstring coverage drops below a threshold.---> Source: [mk-knight23/AI-Agent-Nanobot](https://github.com/mk-knight23/AI-Agent-Nanobot) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions