agentleFS
grace-methodgrace-method/grace-plugin/skills/project-setup/SKILL.md

project-setup

Skill0 starsChanged 2 months agoMITView on GitHub

Initialize a new project or initiative. Establish artifact strategy, classify project type, set predictability expectations, and scaffold the methodology starter structure before Stage 1 product definition begins.

48 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

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 7

    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. Distinctive:

    Use this skill at the very start of a new project or when introducing GRACE into an existing repository that does not yet have a clear …

    line 12
  2. Very specific:

    Standard structure: create the GRACE docs/ tree in the repository

    line 39
  3. Distinctive:

    Custom mapping: keep the org's existing structure and map GRACE concepts onto it

    line 40
  4. Distinctive:

    If standard structure is chosen, scaffold the folder tree and seed files.

    line 42
  5. Distinctive:

    Create only missing files by default.

    line 43
  6. Distinctive:

    Do not overwrite existing artifacts unless the human explicitly asks for it.

    line 46
  7. Distinctive:

    When using the standard structure, scaffold this tree:

    line 59
  8. Distinctive:

    Use these sources when seeding starter files:

    line 84

“Common” is measured: kept by at least 6 in 10 of the 40 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

Use this skill at the very start of a new project or when introducing GRACE into an existing repository that does not yet have a clear artifact strategy.

Purpose

This skill exists to make the Stage 1 entry path real. It does not perform full product definition or business analysis. Its job is to:

  • classify the project at a high level
  • choose how the methodology will map onto the repository
  • scaffold the core artifact structure and starter orientation files when appropriate
  • make the artifact strategy explicit before downstream work begins

Interaction Pattern

  1. Classify the project type.
    • a — personal learning or scratch work
    • b — personal tool or workflow
    • c — tooling or methodology for others or teams
    • d — commercial, regulated, or mission-critical system
  2. Set the predictability dial.
    • high — work is expected to be governed, review-heavy, and artifact-forward
    • low — work is exploratory and lighter-weight
    • hybrid — early work is exploratory, but later stages need stronger structure
  3. Choose the artifact strategy.
    • Standard structure: create the GRACE docs/ tree in the repository
    • Custom mapping: keep the org's existing structure and map GRACE concepts onto it
  4. If standard structure is chosen, scaffold the folder tree and seed files.
    • Create only missing files by default.
    • Seed only the starter orientation files unless the human explicitly asks for more.
    • Let stage skills create detailed stage artifacts when that stage begins.
    • Do not overwrite existing artifacts unless the human explicitly asks for it.
  5. Establish environment parity.
    • Identify all environments the project will run in (local, preview, production, CI).
    • Pin the runtime version explicitly: engines field in package.json, .nvmrc, or equivalent for the stack.
    • Confirm the same version will be used in all environments.
    • Flag any known environment differences as intentional technical debt.
  6. Present the artifact strategy statement for approval.
    • Summarize project type, predictability dial, chosen structure, and any important exceptions.

Standard Structure

When using the standard structure, scaffold this tree:

docs/
├── README.md
├── ROADMAP.md          # created at the close of Stage 1, not seeded here
├── HANDOFF.md
├── BACKLOG.md
├── release-planning/
├── 01-project-definition/
├── 02-analysis/
│   └── requirements/
├── 03-design/
│   └── adr/
├── 04-implementation/
│   └── features/
│       └── stories/
├── 05-validation/
├── 06-operations/
│   └── incidents/
└── 07-retirement/

Template Sources

Use these sources when seeding starter files:

Target pathTemplate source
docs/README.mdtemplates/docs-readme.md
docs/HANDOFF.mdtemplates/handoff.md
docs/BACKLOG.mdtemplates/backlog.md

docs/ROADMAP.md is deliberately not seeded here. A roadmap needs a strategic goal, which does not exist until Stage 1 closes; an empty one written now would be the "empty template treated as evidence" this skill warns against. The project-definition skill creates it, via the roadmap skill.

Current Implementation Note

Stage 1 template ownership lives with project-definition, and the rest of the lifecycle templates live with their corresponding stage skills. project-setup owns the structure, starter orientation files, and routing decision, not the detailed stage artifact content.

Output

Produce a short project-setup record containing:

  • project type
  • predictability dial
  • chosen artifact strategy
  • scaffold action taken or deferred
  • important mapping notes or exceptions

Gate

Human approval is required before treating the artifact strategy as settled or proceeding into product definition or business analysis.

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.