agentleFS
mikejhillmikejhill/agent-skills/skills/project-setup/SKILL.md

project-setup

Skill0 starsChanged 8 months agoMITView on GitHub

Establish or review a project's foundational structure, collaboration, quality checks, testing, and releases. Use for new repositories or policy design; hosting, language, and team profiles supply concrete controls.

51 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use creative-writing-craft, creative-writing-muse and 10 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.
  • Abdullokh-NSkill

    creative-writing-craft

    Справочник ремесла: проза, сцена, стиль, голос. Загружать, когда нужно знание "как писать", а не режим производства.

    Also in 3 projects that use this

  • Abdullokh-NSkill

    creative-writing-muse

    Точка входа в набор скилов для длинной прозы. Включается, когда автор просит спланировать, написать, продолжить, переписать или разобрать художественный текст — роман, повесть, цикл рассказов. Ведёт маршрут от замысла к готовому куску и держит базу знаний проекта.

    Also in 3 projects that use this

  • badgidsSkill

    character-sim

    Pressure-test a character by speaking or reasoning strictly from that character's current voice, goals, relationships, emotional pressure, and knowledge boundary without creating canon by accident.

    Also in 3 projects that use this

  • jpsweeney97Skill

    writing-principles

    Enforces writing principles for instruction documents (SKILL.md, skill supporting files, subagents, CLAUDE.md). Use when writing, reviewing, or editing any file in **/skills/**/*.md, **/agents/*.md, or **/CLAUDE.md. Triggers on skill creation, skill file updates, CLAUDE.md changes, subagent authoring, or instruction document review.

    Also in 3 projects that use this

  • ItsSidharthaSkill

    story-planning

    Collaborative planning skill for a GitHub issue. Takes issue content and codebase context as input. Runs an iterative clarification loop until the user explicitly agrees to a plan, then saves it to docs/<story_number>/plan.md. Used by the user-story-implementation skill — load this skill at the start of Phase 1 and follow it completely before returning to the orchestrator.

    Also in 3 projects that use this

  • badgidsSkill

    story-review

    Diagnose existing prose at a chosen editorial level, from whole-story and developmental problems through scene, line, copy, and proof passes, without rewriting until the diagnosis is accepted.

    Also in 3 projects that use this

  • +4 more from Abdullokh-N

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 43 edited versions we read keep these.

  • 5

    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:

    Keep responsibilities modular.

    line 13
  2. Distinctive:

    Put purpose, audience, quick start, supported use, and canonical documentation links in root README.md.

    line 14
  3. Very specific:

    Use docs/ for deeper project knowledge.

    line 15
  4. Very specific:

    Keep conventional root files where tools expect them: LICENSE, CHANGELOG.md, CONTRIBUTING.md, SECURITY.md, CODE_OF_CONDUCT.md, and …

    line 16
  5. Distinctive:

    Keep build/package manifests and tool configuration at their conventional paths.

    line 17
  6. Distinctive:

    Treat crashed, incomplete, missing, or invalid mutation results as separate execution failures.

    line 33
  7. Distinctive:

    Prefer short-lived, narrowly scoped publishing identity, verifiable build provenance, and least-privilege jobs.

    line 37

“Common” is measured: kept by at least 6 in 10 of the 43 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 setup

Build the smallest maintainable project that its users can discover, run, test, and release.

Establish the foundation

  • Inspect existing conventions and applicable profiles before changing structure. Preserve working ecosystem conventions.
  • Keep responsibilities modular. Separate reusable logic from delivery interfaces and external integrations; avoid layers without a concrete purpose.
  • Put purpose, audience, quick start, supported use, and canonical documentation links in root README.md. Verify commands before presenting them as working.
  • Use docs/ for deeper project knowledge. Apply project-documentation conventions when available; use technical-writing for wording in any location.
  • Keep conventional root files where tools expect them: LICENSE, CHANGELOG.md, CONTRIBUTING.md, SECURITY.md, CODE_OF_CONDUCT.md, and AGENTS.md as applicable. Create only files with a real purpose. Confirm license intent rather than inventing it.
  • Keep build/package manifests and tool configuration at their conventional paths. Profiles choose source/test layout, lockfiles, formatters, and language tools.
  • Ignore local secrets, build outputs, and temporary artifacts. Use the existing temporary-storage convention. Do not commit credentials or private organizational examples.

Collaboration and quality

  • Integrate changes through reviewable proposals, including changes by the owner. Protect shared history and resolve review discussions before integration; profiles define host controls and approval requirements.
  • Require reproducible quality and security evidence for the revision being integrated. Verify check identities and reporting tools before making them required. Keep any authorized quality exception narrow and auditable; it must not weaken an independent security gate.
  • A proposed policy is not authority to change repository security settings, permissions, or publishing controls. Apply such changes only within the user's explicit authorization; otherwise deliver the concrete proposal and readiness gaps.
  • For GitHub-hosted projects, read references/github.md when designing or applying the collaboration/release profile. Other hosts use equivalent capabilities through their own profiles; do not import GitHub settings into them.

Tests and releases

  • Make core tests deterministic, isolated, and reproducible through the same documented commands locally and in CI. Pin the necessary runtime and dependency inputs.
  • Cover observable behavior, error paths, and meaningful boundaries. Use integration tests at real boundaries; keep mocks from becoming the behavior being tested.
  • Separate fast PR feedback from expensive analysis. Run mutation testing asynchronously on the default branch, without making it an eager PR gate.
  • Compare a complete, valid mutation score with the configured required threshold. Create or update a durable score finding only when the score is below that threshold. Equality passes. Passing survivors remain in reports. Deduplicate findings and retain run/commit evidence.
  • Treat crashed, incomplete, missing, or invalid mutation results as separate execution failures. Never infer a passing score or classify them as score findings. If the threshold is undefined, report the configuration gap instead of inventing one.
  • Version released behavior consistently and record user-visible changes. Identify the source revision, build inputs, and produced artifacts.
  • Build artifacts reproducibly where practical. Verify installation and essential behavior of the actual distributable before publication; test-only source runs do not verify the package.
  • Automate versioned releases from verified source and artifacts without adding manual approval gates by default. When release or bot workflows open PRs, configure the host so automation can open them and their required checks run; nobody should open bot PRs by hand. Separate release creation from deployment; preserve explicitly required approvals and the established release scheme.
  • Prefer short-lived, narrowly scoped publishing identity, verifiable build provenance, and least-privilege jobs. Isolate sensitive permissions from untrusted changes; retain rollback and artifact-integrity controls. Profiles supply registry and host details.

Extend deliberately

Use principles → conventions → profiles. This skill supplies principles; profiles supply language, tool, team, or enterprise choices. State scope and explicit overrides. Do not impose an enterprise tree on a personal repository or silently resolve contradictory applicable profiles. Report conflicts with their sources and proceed only on unaffected work.

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.