by YurunChen
Living project docs for coding agents: keep guides, progress logs, change maps, and handoff context updated as your repo evolves.
# Add to your Claude Code skills
git clone https://github.com/YurunChen/repo-docs-skillsGuides for using ai agents skills like repo-docs-skills.
Last scanned: 6/27/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-06-27T06:53:56.751Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}Repo-Docs is not a file-tree tour, a generated API dump, or a chat transcript. It is a small project guide that tells a reader what the repo does, how the behavior moves, where the proof lives, and how to keep that understanding fresh.
AI coding is no longer a niche workflow. Two 2026 open-source studies make the scale visible: AIDev reports 932,791 agent-authored pull requests across 116,211 GitHub repositories, while a multi-method census of 180 million repositories shows that many agent traces are missed by single-signal detection.
That growth creates a new maintenance problem: the code may be real, but the project understanding is often temporary. Repo-Docs gives coding agents a repeatable way to preserve the reasoning layer inside the repository itself.
flowchart LR
A["User asks or agent changes repo"] --> B["Understanding sync check"]
B --> C["Update README and walkthrough"]
B --> D["Update change-log"]
B --> E["Patch modules / glossary / references"]
B --> F["Update AGENTS.md / CLAUDE.md"]
C --> G["User can read the current project"]
D --> G
E --> G
F --> G
The loop is intentionally conservative. A good update touches the page that would otherwise mislead the next reader, not every page that could be polished.
| Artifact | Job |
|---|---|
repo-docs/README.md |
Orient the reader and point to the first useful path. |
walkthroughs/one-real-run.md |
Follow one real behavior from observable entry to output. |
code-map.md |
Map in-scope source directories to responsibilities, important code, tests, and likely change points. |
modules/ |
Explain durable concepts the walkthrough names. |
references/ |
Hold source evidence and optional quality review. |
glossary.md |
Translate repeated project terms into plain meaning. |
change-log.md |
Record meaningful guide work, verification, and sync anchors. |
AGENTS.md / CLAUDE.md |
Tell future coding agents when and how to keep docs current. |
Give this natural-language install request to your coding agent:
Install the repo-docs skill from this project:
https://github.com/YurunChen/repo-docs-skills
Make both repo-docs and repo-docs-zh available in my agent skill directory.
Then ask it to run the skill in any repository:
Use the repo-docs skill to create docs for this repository.
Use this when you prefer a shell install. The URL is a GitHub repository raw-file URL; GitHub serves the raw script bytes through its raw content host after redirect.
curl -fsSL https://github.com/YurunChen/repo-docs-skills/raw/main/install.sh | bash
Windows PowerShell:
irm https://github.com/YurunChen/repo-docs-skills/raw/main/install.ps1 | iex
From this source checkout:
./install.sh
# Install into all known locations: ~/.codex/skills, ~/.claude/skills, ~/.agents/skills
./install.sh --agent all
# Install into one explicit skills directory
./install.sh --target ~/.agents/skills
Use the repo-docs skill to create docs for this repository.
Use repo-docs-zh to create a Chinese repo guide for this project.
Explain how this subsystem works using repo-docs and the current source.
| Mode | Use when | What it preserves |
|---|---|---|
| Seed | The repo is new or has little runtime evidence | Goals, decisions, planned work, and unknowns |
| Build | The repo needs its first guide | Walkthrough, concepts, references, glossary, and sync rule |
| Sync | A repo question or guide-covered behavior may make docs stale | The smallest page that would otherwise mislead |
| Cleanup | The user asks to remove generated docs | Docs package and stale root-agent pointers |
| Question refinement | A question exposes a wrong reader model | The corrected page, then an answer linked to it |
python skills/repo-docs/scripts/validate_repo_docs.py /path/to/repo-docs --repo-root /path/to/repo
Use --lite for small projects and --seed for repositories that still need
status-labeled plans instead of implementation claims. --repo-root checks
source locators and post-anchor drift.
A good Repo-Docs package is useful after the chat ends.
| Principle | Meaning |
|---|---|
| Behavior before inventory | Teach one real workflow before listing files. |
| Reader handles before locators | Explain the concept, then link to the exact path, function, field, or command. |
| One durable fact, one home | Concepts and needed details live in modules; evidence and quality audit live in references; history lives in the change log. |
| Evidence stays visible | Current source, tests, config, data, commands, and artifacts outrank memory or stale docs. |
| Patches stay surgical | When understanding drifts, update the smallest page that fixes the reader model. |
repo-docs-skills/
├── skills/
│ ├── repo-docs/ # installable skill package
│ └── repo-docs-zh/ # Chinese language overlay
├── site/ # homepage source
├── docs/ # GitHub Pages publish tree
├── install.sh
├── install.ps1
├── README.md
└── README_CN.md
The installable skill source lives under skills/. The site/ directory is homepage source, while docs/ is the GitHub Pages publish tree.
<skills-dir>/
├── repo-docs/
│ ├── SKILL.md
│ ├── REFERENCE.md
│ ├── WRITING.md
│ ├── PAGE_RULES.md
│ ├── SCOPE_MODES.md
│ ├── SYNC_RULES.md
│ ├── QUALITY_RULES.md
│ ├── EXAMPLES.md
│ ├── validate_repo_docs.py
│ └── scripts/
│ └── validate_repo_docs.py
└── repo-docs-zh/
└── SKILL.md
Repo Docs Skills is developed by the AI4GC Lab at Zhejiang University.
repo-docs-skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by YurunChen. Living project docs for coding agents: keep guides, progress logs, change maps, and handoff context updated as your repo evolves. It has 368 GitHub stars.
Yes. repo-docs-skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/YurunChen/repo-docs-skills" and add it to your Claude Code skills directory (see the Installation section above).
repo-docs-skills is primarily written in Python. It is open-source under YurunChen on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh repo-docs-skills against similar tools.
No comments yet. Be the first to share your thoughts!