agentleFS
BinayakDotelBinayakDotel/skills-marketplace/skills/setup-project/SKILL.md

setup-project

Skill1 starsChanged 35 days agoMITView on GitHub

One-time setup of a repo for the dev-flow skills. Detects the stack, then writes the project profile (AGENTS.md), the justfile command contract, stack rules from packs, GitHub issue tracking (labels, ticket template, board script) and, for web UI, a design contract skeleton. Never edits skills. Use when starting a new repo or bringing an existing one into dev-flow.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-pr, tdd and 1 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.
  • 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

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    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

1 rule. 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Look only at: package.json and lockfiles, pnpm-workspace.yaml, next.config.*, any convex/ folder, vitest.config.*, project.godot, *.csproj, …

    line 14

“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

Skills stay global and unchanged. This skill writes the project's own facts once, from the templates and packs next to this file (<skill-dir> is the folder containing this SKILL.md).

1. Detect (read, don't ask)

Look only at: package.json and lockfiles, pnpm-workspace.yaml, next.config.*, any convex/ folder, vitest.config.*, project.godot, *.csproj, pyproject.toml, Cargo.toml, justfile, AGENTS.md, CLAUDE.md, .cursor/rules/, docs/, git remote -v. At most 15 reads; never node_modules. Match packs with <skill-dir>/packs/INDEX.md.

2. Ask once

One batch, at most 6 questions, each with your recommendation:

  1. The project in one sentence.
  2. Packs: confirm the detected list.
  3. Git: Graphite or plain git, and the base branch.
  4. Tracker: GitHub Issues with a project board (recommended) or local markdown; the board title.
  5. Models for tickets/take, implement, address/done, and when stuck.
  6. Web UI: write the design contract skeleton now? (Yes if the project has or will have screens.)

3. Write

Show the file list first, then write.

  • AGENTS.md from templates/AGENTS.md, the block under 60 lines. If it exists, replace only the block between <!-- dev-flow:start --> and <!-- dev-flow:end -->, or append the block. Keep every other tool's managed block as it is (Next.js writes one between BEGIN:nextjs-agent-rules and END:nextjs-agent-rules). If only CLAUDE.md exists, add the line See AGENTS.md. to it.
  • justfile: merge each pack's justfile.snippet, keeping existing recipes. Every contract recipe must exist: test-q, typecheck, lint, check, run, stop, task. A recipe with no tool for this stack becomes @echo "n/a for this stack".
  • .cursor/rules/<rule>.mdc from each chosen pack's rules/, with every <<placeholder>> filled from detection. Packs never add always-on rules.
  • GitHub (if chosen): docs/agents/issue-tracker.md and .github/ISSUE_TEMPLATE/ticket.md from templates/; scripts/task.sh and scripts/project-env.sh from templates/ (make them executable); labels: gh label create status:todo --color ededed, gh label create status:in-progress --color fbca04, gh label create status:in-review --color 0e8a16 (ignore "already exists").
  • docs/DECISIONS.md from templates/DECISIONS.md if missing.
  • Web UI (if chosen): docs/design/README.md from templates/design-contract.md, docs/design/screens.json containing [], scripts/shots.ts from packs/ui-web/, and .shots/ in .gitignore. Then tell the human the references and tokens come from the design-package skill, run with a strong model (Claude), not from this setup.

4. Hand over

Print the steps only the human can do, then stop:

  1. gh auth refresh -s project
  2. gh project create --owner <owner> --title "<board title>"; in its settings add a Status option named In Review; then scripts/project-env.sh <owner> <project number>.
  3. One milestone per phase: gh api repos/<owner>/<repo>/milestones -f title="Phase 1".
  4. just check once; fix the setup (not the code) until it runs.

End with one line: Next: /tickets <spec section> on <model for tickets>.

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.