How do I install the Docgen skill?

Run npx skillmds@latest add zedarvates/docgen 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 Docgen safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Docgen?

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 Docgen free to use?

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

Who published Docgen?

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

Docgen by zedarvates — Agent Skill

Name: Docgen
Author: zedarvates

Docgen

Generate documentation with a local model drafting and the cloud only refining (0 cloud tokens for the draft), plus a local session review that summarises what a work session did. Use to write README/module docs/CHANGELOG/guides/ADRs cheaply, or to produce end-of-session notes/learnings from a transcript.

zedarvates d5efc30 5 files · 11.9 KB Updated Sep 17, 2026

File contents

docgen — local-drafted docs (cloud-refined) + session review

Documentation is verbose, so the LOCAL model writes the first draft and the cloud model is spent only on a final polish — the video's "pre-write local, correct with cloud" pattern, built on [[auto_router]]'s draft_refine fusion.

python -m skills.docgen.cli draft "deploy the service" --kind guide
python -m skills.docgen.cli draft "auth module" --kind module
python -m skills.docgen.cli session ~/.claude/projects/.../transcript.jsonl
python -m skills.docgen.cli session "user: did X\nassistant: built Y" --text

draft — local model drafts (readme|module|changelog|guide|adr); cloud refines only if a key is set (otherwise you keep the local draft, marked un-refined). 0 cloud tokens for the draft itself.
session — reads a transcript (Claude Code .jsonl, markdown, or raw text) and a LOCAL model returns done / decisions / learnings / next. 0 cloud tokens.

Exposed via [[llm_mcp]] as draft_doc and session_review. Pairs with [[ingest]] (pull sources to document) and [[checkup]] (what changed this session).

Frequently asked questions