agentleFS
caiaffacaiaffa/claude-code-ultimate-engineering-system/skills/repo-onboarding/SKILL.md

repo-onboarding

Skill17 starsChanged 59 days agoMITView on GitHub

Map an unfamiliar repository before changing it — understand the structure, architecture, conventions, dependencies, scripts, and local development workflow before proposing or making changes.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use mcp-maintainer and release-guard.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • KhaiTrang1995Skill

    mcp-maintainer

    Operate and maintain the local MCP server for this repository. Use for MCP tool updates, policy-guard changes, host configuration, and MCP runtime troubleshooting.

    Also in 3 projects that use this

  • KhaiTrang1995Skill

    release-guard

    Run release-readiness checks for this repository. Use when validating docs, scripts, verification coverage, and operational safety before merge or release.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No README or setup instructions.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 10 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.

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

Mission

Build an accurate mental model of the repository before changing it. Reduce blind edits, architectural drift, and accidental misuse of local conventions.

When to use

  • Entering a new repository.
  • Returning to a repository after time away.
  • Preparing to implement a feature or fix.
  • Explaining how the codebase is organized.

Handoff

  • Receives from: CLAUDE.md orchestrator (onboarding category).
  • Hands off to: backend-platform-engineer (ready to implement), nestjs-architecture-guardian (if NestJS).
  • Record conventions, commands, and danger zones to agent memory so later runs start informed.

Exploration order

1. README.md and docs/        → Intent, setup, high-level architecture
2. package.json / go.mod / etc → Runtime, framework, dependencies
3. Top-level folder structure  → Module boundaries
4. src/ or app/ structure      → Layering (controllers, services, repos)
5. Config files                → Environment, feature flags, secrets
6. Test structure              → Test strategy, fixtures, helpers
7. CI/CD config                → Build pipeline, deploy process
8. Recent git log              → Active areas, recent patterns

What to document

  1. Purpose — what does this system do?
  2. Main modules — what are the actual boundaries (not just folder names)?
  3. Tech stack — runtime, framework, ORM, queue, cache, DB.
  4. Local dev — how to run locally (commands, prerequisites, env setup).
  5. Test strategy — what test types exist, how to run them.
  6. Deploy — how does code get to production?
  7. Conventions — naming, patterns, idioms specific to this project.
  8. Danger zones — areas of high complexity, tech debt, or competing patterns.
  9. Where to add new code — for a new feature, where does it go?

Red flags about codebase health

  • Multiple competing patterns for the same concern (3 different ways to do error handling).
  • "Common" or "utils" folder with 50+ files.
  • Circular dependencies between modules.
  • Tests that mock everything (no integration tests with real DB/queue).
  • No README or setup instructions.
  • Last meaningful commit was months ago on a critical path.

Output format

  1. Repository summary (1 paragraph)
  2. Architecture map (modules, boundaries, dependencies)
  3. Tech stack (runtime, key libraries, infra)
  4. Local dev workflow (setup → run → test)
  5. Conventions (naming, patterns, idioms)
  6. Where to add a new feature (specific path)
  7. Health assessment (clean / has drift / needs refactor)
  8. Risks and unknowns (what's unclear, what's fragile)

Download now (ZIP)

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.