onboard-repo
Skill1 starsChanged 2 months agoMITView on GitHub
Build up context on a repo you do not know. Asks scoping questions, explores, proposes a table of contents fitted to THIS repo, then writes only what is kept. Use when the user lands on a project they do not know, or says "onboard", "survey this repo", "I am new to this repo", "get familiar with the repo".
6 other projects use a version of this.
Adopted by
Most recently taken up by
- tounsils/claude-code-skillstheir own version, first seen Oct 25, 2026
- waqarqasim/portable-agent-skillstheir own version, first seen Oct 13, 2026
- raniellimontagna/agent-toolkittheir own version, first seen Oct 11, 2026
- YogirajA/Claude-Skillstheir own version, first seen Sep 17, 2026
- n24q02m/better-code-review-graphtheir own version, first seen Mar 22, 2026
- n24q02m/crgtheir own version, first seen Mar 22, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- n24q02m/better-code-review-graph★ 76same name
- n24q02m/crg★ 76same name
- raniellimontagna/agent-toolkit★ 3same name
- tounsils/claude-code-skills★ 1same name
- YogirajA/Claude-Skills★ 1same name
- waqarqasim/portable-agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- defend-reviewSkill
- review-prSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Follow PROMPT.md in this same folder, in full.
- Distinctive: line 25
Phase 0 is talkative and blocking when you can speak: When you cannot, apply the prompt's fallback: carry on, record the questions, write …
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Getting a foothold on a new repo
Follow PROMPT.md in this same folder, in full. Read it now, before doing anything.
Read ~/.claude/skills/onboard-repo/PROMPT.mdFive points that fatigue drops first.
- You propose, you do not dump. There is no list of documents to produce. Phase 3 is the heart: you explore, you submit a table of contents fitted to this repo, and you write nothing before agreement. Three or four documents are almost always enough. On a small repo, one document and one figure are the right answer.
- Check the ground before measuring. Shallow clone, stale checkout, access refused on the
forge: those are the only errors that produce a wrong document rather than merely an
incomplete one. A
git shortlogon a truncated clone invents a dominant contributor. - Phase 0 is talkative and blocking when you can speak. When you cannot, apply the prompt's fallback: carry on, record the questions, write the table of contents instead of asking for it, and produce neither of the two sensitive outputs (profile of the people who decide, dominant external brick).
- Look for the project's policy on AI contributions. It varies from repo to repo inside a single organisation, from "welcome" to "closed without review". You are probably an agent.
- A finding that gets re-verified deserves a script; a script that acts does not install itself. Perishable figures and checks the project's CI does not replay on my machine call for an executable rather than a paragraph. But you propose it: never write into a tool configuration, an automation file or a repository hook without explicit agreement.
This prompt is also designed to be pasted as-is into another agent. If the user asks for it,
give them the contents of PROMPT.md without paraphrasing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.