kit-learn-repo
Skill6 starsChanged 27 days agoMITView on GitHub
Learn an unfamiliar codebase — purpose, layout, how to run/test, safe change points. Use when joining a repo, switching projects, or before the first change in a new area.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- rules/AGENTS.mdAGENTS.md
- kit-audit-metricsSkill
- kit-audit-skillsSkill
- kit-capture-lessonSkill
- kit-challenge-designSkill
- kit-check-blastSkill
- kit-create-prSkill
- kit-debate-decision-treeSkill
- kit-debug-prodSkill
- kit-decisionsSkill
- kit-evolveSkill
- kit-explainSkill
- kit-minimizeSkill
- kit-optimize-contextSkill
- kit-planSkill
- kit-proveSkill
- kit-reviewSkill
- kit-strip-diffSkill
- kit-triage-commentsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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: line 13
Not a full design challenge (kit-challenge-design)
- Very specific: line 14
Not implementing yet (kit-plan / kit-minimize if you still need a path)
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Learn Repo
Build a practical mental model fast — not an encyclopedia.
What this is NOT
- Not a full design challenge (
kit-challenge-design) - Not implementing yet (
kit-plan/kit-minimizeif you still need a path)
Flow
- Basics — README / docs: what it does, runtime, package manager, how to run and test locally.
- Layout — entry points (apps, services, CLIs), major domains, one vertical slice (one API or user flow).
- Tooling — relevant MCP/extensions for this repo (names only; configure secrets outside chat).
- Recent signal — recent commits/PRs in the area you’ll touch (direction, not ownership gospel).
- Warnings — fragile zones: generated code, migrations, hidden coupling, custom deploy assumptions.
Output
Short brief:
- What it does
- How it’s laid out
- How to run / test
- Where to change safely for the user’s ask
- Warnings + open questions + what to read next
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.

