ArcQian-bitArcQian-bit/codex-real-engineer-skills/skills/repo-cartographer/SKILL.md

repo-cartographer

Skill1 starsChanged 5 months agoMITView on GitHub

Map and explain unfamiliar repositories for Codex before implementation. Use when the user asks where to start, how a codebase works, what files own a behavior, how to onboard into a repo, or which change path is safest. Do not use for focused code review, release work, docs-only edits, or direct bug fixing when the user already supplied the failing surface.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Read project signposts first: README, AGENTS.md, CONTRIBUTING, package files, build scripts, docs, tests, and route or entrypoint …
line 12
Distinctive:
Stop at a map unless the user explicitly asks to implement.
line 16
Very specific:
Prefer rg, rg --files, and targeted file reads.
line 28
Distinctive:
Do not invent architecture names the repo does not support.
line 29
Distinctive:
If the repo is large, map the relevant slice first and say what remains unmapped.
line 31

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Repo Cartographer

Build a useful map before changing code.

Workflow

Read project signposts first: README, AGENTS.md, CONTRIBUTING, package files, build scripts, docs, tests, and route or entrypoint directories.
Identify the runtime, package manager, commands, app boundaries, data stores, external services, and generated-code conventions.
Trace one or two representative flows from entrypoint to side effect. Prefer actual imports, routes, tests, or handlers over guesses.
Name the safest change paths: files to edit, tests to run, fixtures to inspect, and risks to avoid.
Stop at a map unless the user explicitly asks to implement.

Output Shape

What This Repo Is: one paragraph.
How To Run/Verify: commands found in the repo.
Key Areas: directories, ownership, and purpose.
Likely Change Path: where to work for the user's goal.
Open Questions: only blockers that code/docs did not answer.

Ground Rules

Prefer rg, rg --files, and targeted file reads.
Do not invent architecture names the repo does not support.
Mark confidence as High, Medium, or Low when recommending a path.
If the repo is large, map the relevant slice first and say what remains unmapped.

Download now (ZIP)

Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
Henrique-All/skills★ 4same name
wenshuocui50-droid/repo-cartographer★ 1same 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 repository11 other files it gives its agents.
- docs/llms.txtllms.txt
- llms.txtllms.txt
- docs-keeperSkill
- frontend-polisherSkill
- issue-sherpaSkill
- migration-pilotSkill
- perf-labSkill
- pr-reviewerSkill
- real-engineerSkill
- release-captainSkill
- security-scoutSkill

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free