agentleFS
Sign inStart free
bt2gobt2go/claude-skills/skills/onboarding-map/SKILL.md

onboarding-map

Skill0 starsChanged 3 months agoMITView on GitHub

Use when the user lands in an unfamiliar repository and needs to know how it is built and where to start.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the manifest first: package.json, pyproject.toml, go.mod, Cargo.toml, or the equivalent.

    line 12
  2. Distinctive:

    Read any existing README, CONTRIBUTING and configuration files before browsing source.

    line 13
  3. Distinctive:

    Prefer facts read from the repository over assumptions from the framework's conventions.

    line 23
  4. Distinctive:

    Keep the whole map under two pages.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Onboarding map

Produce the orientation document the repository should have had.

Procedure

  1. Read the manifest first: package.json, pyproject.toml, go.mod, Cargo.toml, or the equivalent. It names the stack and the scripts.
  2. Read any existing README, CONTRIBUTING and configuration files before browsing source.
  3. Find the entry points: the server bootstrap, the CLI main, the route table, the job registry.
  4. Map the top level directories, one line each, describing responsibility rather than contents.
  5. Trace one real request or command end to end and record the files it passes through in order.
  6. Record how to run it locally: install, environment variables required, database or service dependencies, the dev command.
  7. Record how to test it and how it ships.
  8. Note the three files that change most often according to git log, since that is where the work is.

Rules

  • Prefer facts read from the repository over assumptions from the framework's conventions.
  • Say plainly when something is undocumented or appears stale.
  • Keep the whole map under two pages.

Output format

Stack: ...
Run locally: <numbered steps and commands>
Directory map: <bullets>
One request end to end: <ordered file list>
Tests: <command>
Deploy: <how>
Hot files: <top three from git log>
Open questions: <bullets>

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.

Check your setup, free