agentleFS
Docat0209Docat0209/SoloForge/skills/project-init/SKILL.md

project-init

Skill1 starsChanged 7 months agoMITView on GitHub

Project initialization checklist. Triggers ONLY when: about to run git init, npm init, or creating a brand new repository. Do NOT trigger when: discussing project structure or working in an existing project.

  • Commits and pushes

38 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use harness-audit, workflow and 3 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.
  • sattva2020Skill

    harness-audit

    Audits a codebase for "AI-agent harness" maturity across six layers (context engineering, tools & MCP, memory & state, tests & evals, observability, guardrails & approvals). Scores each layer, flags AGENTS.md/CLAUDE.md drift, gives prioritized fixes. Use for "audit harness", "оцени харнес", "check agent readiness", "is this project agent-ready", "проверь готовность к AI-агентам".

    Also in 3 projects that use this

  • VercelSkill

    workflow

    Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue", "event", "push", "subscribe", or step-based orchestration.

    Also in 3 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 4 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    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

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

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 0

    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. Very specific:

    Railway: Create a service → add environment for dev branch

    line 59
  2. Very specific:

    Render: Create a Preview Environment linked to dev

    line 60

“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

Project Initialization SOP

CI is the foundation that enforces everything else. Set it up FIRST, not last.

1. Git Setup

  • git init (if not already a repo)
  • Create initial commit on main
  • Create dev branch from main: git checkout -b dev
  • Push both branches: git push -u origin main && git push -u origin dev
  • Set dev as the default working branch

2. First Issue

  • Create GitHub Issue #1: "chore: project initialization" tracking all setup tasks
  • Include acceptance criteria checkboxes for each step in this checklist
  • Create branch chore/project-init from dev

3. Test Runner

  • Detect project language and install the appropriate test runner:
    • JS/TS: Vitest (vitest.config.ts)
    • Python: pytest (pyproject.toml or pytest.ini)
    • Go: built-in go test
    • Other: use the community standard runner
  • Add a sample passing test to verify the runner works
  • Add test script to package manager (e.g., "test": "vitest run")

4. E2E Setup

  • Install Playwright: npm init playwright@latest (or equivalent)
  • Create tests/e2e/ directory
  • Add a smoke test (e.g., app loads, returns 200)
  • Ensure Playwright runs in CI (headless, with npx playwright install --with-deps)

5. CI/CD (GitHub Actions)

  • Create .github/workflows/ci.yml with these steps:
    1. Lint (ESLint, ruff, golangci-lint, etc.)
    2. Typecheck (tsc --noEmit, mypy, etc.)
    3. Unit + Integration tests (vitest, pytest, go test)
    4. E2E tests (Playwright)
    5. Build (verify production build succeeds)
  • Trigger on: push to dev, pull requests to dev and main
  • Verify CI passes with a test push

6. Staging/Preview Environment

Set up automatic preview deployments for the dev branch. This enables automated verification via staging-verify before releasing to main.

  • Detect or choose deployment platform:
    • Vercel: vercel link → enable Git Integration → preview deployments deploy automatically for all branches
    • Netlify: netlify init → Site settings → Build & deploy → Branch deploys → add dev
    • Railway: Create a service → add environment for dev branch
    • Render: Create a Preview Environment linked to dev
    • Self-hosted: Configure CI/CD to deploy dev branch to a staging subdomain
  • Verify the dev branch has a stable preview URL (branch-level, not per-PR)
  • Document the staging URL in the project's CLAUDE.md:
    ## Environments
    - Production: <main-deploy-url>
    - Staging: <dev-preview-url>
  • Verify staging deploys automatically on push to dev
  • Smoke test: push a change to dev, confirm it appears at the staging URL

7. Branch Protection

  • Protect dev branch via GitHub API or UI:
    • Require status checks to pass (CI workflow)
    • Require PR reviews (optional for solo projects)
  • Verify protection works: a failing PR should be blocked

8. Project CLAUDE.md

  • Create CLAUDE.md in project root with:
    • Project description and tech stack
    • How to run: dev server, tests, build, lint
    • Key directories and architecture notes
    • Environment variables needed (names only, no values)

Completion

  • Open PR from chore/project-init to dev
  • Self-review the PR diff
  • Merge, verify CI passes, close Issue #1, delete branch

Learning

Store project metadata in auto memory (memory/project_meta.md):

  • Project name
  • Tech stack, test runner, CI setup, repo URL
  • This enables cross-project pattern retrieval in future conversations.

Next Steps

Report to user: "Project initialized: [name]. Git: ✅. CI: ✅. Staging: [status]. Dev branch: ✅"

Suggested next steps (user decides):

  • Project ready → "Run work-breakdown to plan features"
  • Need monitoring → "Run infra-ops"
  • Need legal docs → "Run legal-guard"

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.