agentleFS
Sign inStart free
bogdanmatasarubogdanmatasaru/claude-code-guide/.claude/skills/project-onboard/SKILL.md

project-onboard

Skill0 starsChanged 5 months agoMITView on GitHub

Set up a project for smooth work with Claude Code — generate/update CLAUDE.md, propose an allowlist of permissions so it stops asking on repetitive commands, and suggest relevant MCP servers. Use when you first open a new repo with Claude Code.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. mkSteady/mkSkills★ 9same name
    2. manastalukdar/ai-devstudio★ 1same name
    3. InfiniteRoomLabs/agent-ops★ 0same name
    4. jcmissmeng/super-skills★ 0same name
    5. Zions-store/project-ledger★ 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.

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Run the steps in order. Be concise with the user.

    line 12
  2. Very specific:

    If CLAUDE.md does not exist: run the equivalent of /init — generate a short one with: the key commands (build/test/lint/run), a brief …

    line 24
  3. Distinctive:

    If it exists: read it, propose additions only for what's missing and useful.

    line 28
  4. Distinctive:

    Ask for confirmation before writing/committing.

    line 29
  5. Very specific:

    Do NOT add destructive commands (deploy, push --force, rm).

    line 36
  6. Very specific:

    Write to .claude/settings.json (project), not the global settings.

    line 37
  7. Very specific:

    If the project uses GitHub and gh is authenticated, suggest the GitHub MCP.

    line 41
  8. Distinctive:

    If it's a web/UI project, mention a browser MCP for visual verification.

    line 42
  9. Distinctive:

    Only suggest + show the command.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 3 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

project-onboard

Goal: after setup.sh has prepared the environment (Ghostty + Claude Code installed), this skill prepares the current project so work is smooth from the first message.

Run the steps in order. Be concise with the user; show what you did, don't explain the theory.

1. Understand the repo

  • Detect the stack: look for package.json, pyproject.toml, go.mod, Cargo.toml, Makefile, *.csproj, etc.
  • Identify the build / test / lint / run commands (from scripts, Makefile, CI).
  • Note obvious conventions (formatter, folder structure, test framework).

2. CLAUDE.md

  • If CLAUDE.md does not exist: run the equivalent of /init — generate a short one with: the key commands (build/test/lint/run), a brief structure overview, code conventions, and non-obvious things to know. Keep it tight (not an essay).
  • If it exists: read it, propose additions only for what's missing and useful.
  • Ask for confirmation before writing/committing.

3. Permissions (fewer prompts)

  • From the commands found in step 1, propose an allowlist in .claude/settings.json for the safe & repetitive ones (e.g. Bash(npm run test:*), Bash(npm run build), Bash(git status), Bash(git diff:*)).
  • Do NOT add destructive commands (deploy, push --force, rm). Read/test/build only.
  • Write to .claude/settings.json (project), not the global settings.

4. Relevant MCP servers (optional)

  • If the project uses GitHub and gh is authenticated, suggest the GitHub MCP.
  • If it's a web/UI project, mention a browser MCP for visual verification.
  • Only suggest + show the command; don't install without an OK.

5. Final summary

Show a short list:

  • what was created/changed (CLAUDE.md, settings.json),
  • the detected test/build commands,
  • the recommended next step (e.g. "run /code-review after your first changes").

Rules: confirm before writing to versioned files; don't touch the user's global settings; don't invent commands — verify they exist in the repo.

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