agentleFS
my-chiefmindmy-chiefmind/ai-maestro/skills/dev-setup/SKILL.md

dev-setup

Skill6 starsChanged 47 days agoMITView on GitHub

Bootstrap a repo for local development from a clean checkout. Use when starting on a new machine or a fresh clone: install the right toolchain versions, dependencies, env config, and confirm the app builds and tests run before any work begins.

  • Reads credentials
  • Installs packages

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Pin the toolchain: Use the version manager the repo specifies (.nvmrc, .tool-versions, .python-version, etc.).

    line 15
  2. Distinctive:

    Build: Run the build once; fix setup issues, not code.

    line 22
  3. Distinctive:

    Verify the baseline: Run the test suite. Note the known-good baseline (some suites have a small set of accepted-failing tests) so later you …

    line 23
  4. Distinctive:

    If a setup step's docs mention a prod path (a prod DB, prod secrets), that's not permission to use it — set up against local/dev only.

    line 28
  5. Distinctive:

    Don't commit machine-generated churn (rebuilt lockfile entries, editor files).

    line 30

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

Dev Setup

Get a repo from git clone to "builds + tests green" reproducibly, so no one debugs their environment mid-ticket.

Steps

  1. Read the project's context.md for the toolchain, versions, and commands. Don't guess the package manager or test runner — the project declares them.
  2. Pin the toolchain. Use the version manager the repo specifies (.nvmrc, .tool-versions, .python-version, etc.). Mismatched runtimes cause phantom failures.
  3. Install dependencies with the project's lockfile-respecting command (npm ci, uv sync, pnpm i --frozen-lockfile, …). Don't run an installer that rewrites the lockfile — that churn is not your change.
  4. Configure env. Copy .env.example → .env (or the documented path) and fill in local values. Secrets come from the documented local source, never from a prod path.
  5. Build. Run the build once; fix setup issues, not code.
  6. Verify the baseline. Run the test suite. Note the known-good baseline (some suites have a small set of accepted-failing tests) so later you can tell a regression from noise.

Guardrails

  • If a setup step's docs mention a prod path (a prod DB, prod secrets), that's not permission to use it — set up against local/dev only.
  • Don't commit machine-generated churn (rebuilt lockfile entries, editor files). Restore it with git checkout before you start real work.

Done when: the app builds and the test suite runs to its known baseline from a clean checkout.

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.