agentleFS
Sign inStart free
giuseppenesca87-pnggiuseppenesca87-png/claude-code-house-rules/skills/project-launch-check/SKILL.md

project-launch-check

Skill0 starsChanged 2 months agoMITView on GitHub

Use automatically when opening an existing project, starting work in a repository, trying to run an app, debugging local setup, verifying a feature, preparing a project for Claude Code, or when the user says the app/site/project does not work.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    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:

    Use this skill to understand and run a project safely.

    line 8
  2. Distinctive:

    Run minimal safe checks:

    line 33
  3. Distinctive:

    do not hide failures

    line 38
  4. Distinctive:

    use Playwright MCP when useful

    line 41
  5. Distinctive:

    test mobile/responsive if relevant

    line 45
  6. Distinctive:

    If the project has a non-trivial launch process, write the recipe down in the project (a short "how to run this" section in the README or …

    line 47
  7. Distinctive:

    Run recipe worth saving in the project

    line 58

≈ “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

Project Launch Check

Use this skill to understand and run a project safely.

Steps

  1. Inspect project files:
    • README
    • package.json
    • pnpm-lock/yarn-lock/package-lock
    • Makefile
    • docker-compose
    • env examples
    • framework config
    • test config
    • deployment config
  2. Identify:
    • stack
    • package manager
    • install command
    • dev command
    • build command
    • test command
    • env vars needed
    • database or services needed
  3. Run minimal safe checks:
    • install only if needed
    • build/typecheck/test when available
    • launch app
    • capture errors
    • do not hide failures
  4. For web apps:
    • use Playwright MCP when useful
    • open local app
    • check console errors
    • verify main flow
    • test mobile/responsive if relevant
  5. If the project has a non-trivial launch process, write the recipe down in the project (a short "how to run this" section in the README or in CLAUDE.md), so the startup process is not rediscovered from scratch every session.

Output format

  1. Project stack summary
  2. Commands discovered
  3. Missing requirements
  4. Errors found
  5. How to run locally
  6. Run recipe worth saving in the project
  7. Next best fix

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