agentleFS
eugnmueller-87eugnmueller-87/claude-blueprint/.claude/skills/setup-project/SKILL.md

setup-project

Skill1 starsChanged 5 months agoMITView on GitHub

Bootstrap the .claude/ blueprint into a repo — detect the stack, tune CLAUDE.md and rules, wire the safety hooks, write the drift fingerprint. Run once when seeding a new project, or re-run after the stack changes. Trigger phrases "set up this project", "setupdotclaude", "seed claude into this repo".

  • Reads credentials

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research, implement and 2 more.

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.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 5 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 4 projects that use this

  • DockerSkill

    review-pr

    Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Distinctive:

    Detect the stack: Read (don't guess) what exists:

    line 19
  2. Very specific:

    Write settings.json with the matchers and the allow/deny permission list.

    line 46
  3. Very specific:

    chmod +x: every hook (Git Bash): chmod +x .claude/hooks/*.sh.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 18 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

setup-project

Trigger: "set up this project" / "setupdotclaude" / "seed claude here"

Standing rules: ../_conventions.md.

You are seeding this repo with the standing blueprint. Lead with what you're about to change, do it, then report what landed. Never invent commands — detect them from real manifest files; if a command isn't verifiable, mark it TODO and say so.

Steps

  1. Detect the stack. Read (don't guess) what exists:
    • pyproject.toml / requirements.txt / setup.py → Python. From pyproject.toml, note the real test runner (pytest?), formatter/linter (ruff? black? isort?), type checker (mypy?), and package manager (uv lock file? poetry? plain pip?).
    • package.json → JS/TS; read the scripts block for real commands.
    • railway.json / Procfile / vercel.json → deploy target.
    • .env.example → expected env vars (NEVER read .env itself; the deny list blocks it — that's correct, don't work around it). State the detected stack in one line before writing anything.
  2. Write/patch CLAUDE.md from CLAUDE.template.md. Fill Commands from the REAL detected commands only (e.g. pytest, ruff check ., mypy .). Keep it under 50 non-blank lines (hard cap; aim for 25). Do NOT duplicate code style — that lives in rules/code-quality.md.
  3. Install rules. Copy the always-on rules (code-quality.md, testing.md) and the path-scoped rules that match this repo:
    • python.md (**/*.py) for any Python repo.
    • security.md if there's an api/** / routes/** / handlers/** surface.
    • error-handling.md for services/** / handlers/**. Skip rules with no matching paths — dead rules cost tokens. Drop frontend.md / database.md unless the repo actually has a UI or SQL migrations.
  4. Wire hooks. Copy the four PreToolUse guards (protect-files, warn-large-files, scan-secrets, block-dangerous-commands), format-on-save + auto-test (PostToolUse), session-start, notify. Write settings.json with the matchers and the allow/deny permission list. Retune the allow-list for the stack: for Python add Bash(pytest *), Bash(ruff *), Bash(mypy *), Bash(python -m *), Bash(uv *); keep the git/gh allows; drop the npm allows if there's no package.json.
  5. chmod +x every hook (Git Bash): chmod +x .claude/hooks/*.sh.
  6. Write the fingerprint so session-start can nudge on drift: DOTCLAUDE_FINGERPRINT=1 .claude/hooks/session-start.sh > .claude/.dotclaude.json.
  7. Verify, don't assume. Actually run each command you wrote into CLAUDE.md once (lint, test, typecheck). If one fails or is missing, fix the CLAUDE.md line or mark it # TODO: unverified — never leave a command that doesn't run.
  8. Report (terse): stack detected · files written · commands verified · anything left as TODO. End with the single next action.

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.