speckit-generator
Project-focused specification and task management system. Run /speckit.init to install 8 project-local commands: /plan, /tasks, /design, /analyze, /clarify, /implement, /revert, /lint. Each command MUST be invoked separately and requires user approval before proceeding. NEVER chain commands automatically - each produces output that requires user review. Use /plan when user wants to create plans from specs. Use /tasks only AFTER user has approved plans. Git checkpoints enable safe revert.
What this skill does
# SpecKit Generator
Project-focused specification management with 1 bootstrap command (/speckit.init) that installs 8 project-local commands to transform specifications into executed implementations with git checkpoint safety.
## Table of Contents
- [Critical Workflow Rules](#critical-workflow-rules)
- [Overview](#overview)
- [Commands](#commands)
- [Command: init](#command-init)
- [Command: plan](#command-plan)
- [Command: tasks](#command-tasks)
- [Command: analyze](#command-analyze)
- [Command: clarify](#command-clarify)
- [Command: implement](#command-implement)
- [Command: revert](#command-revert)
- [Memory File System](#memory-file-system)
- [Idempotency](#idempotency)
---
## Critical Workflow Rules
**MANDATORY: Commands must NOT be chained automatically.**
Each command produces artifacts that require user review and approval before proceeding to the next phase. This is not optional.
### Required Gates
| After Command | MUST DO | Before Proceeding To |
|---------------|---------|---------------------|
| `/speckit.init` | Present created structure, confirm memory files | Any other command |
| `/speckit.plan` | Present plan summary, wait for explicit approval | `/speckit.tasks` |
| `/speckit.tasks` | Present task summary, wait for explicit approval | `/speckit.implement` |
### Recommended Workflow
```
/speckit.init
↓ [User reviews structure]
/speckit.plan
↓ [User reviews plan]
/speckit.analyze ← Run BEFORE approving plan
↓ [Address any CRITICAL/HIGH findings]
/speckit.clarify ← Run if [TBD] items exist
↓ [User approves final plan]
/speckit.tasks
↓ [User reviews tasks]
/speckit.implement
```
### What NOT To Do
- ❌ Run `/speckit.plan` then immediately `/speckit.tasks` without user approval
- ❌ Generate all artifacts in one session without checkpoints
- ❌ Skip `/speckit.analyze` before plan approval
- ❌ Proceed past a GATE without explicit user confirmation
### Gate Response Format
After completing a command, present results in this format:
```
## [Command] Complete
[Summary of what was created/modified]
### Artifacts Created
- [list of files]
### Recommended Next Steps
1. Review the [artifacts] above
2. Run `/speckit.analyze` to check compliance (if applicable)
3. Run `/speckit.clarify` to resolve any [TBD] items (if applicable)
**Awaiting your approval before proceeding.**
```
---
## Overview
SpecKit provides a complete workflow for specification-driven development:
```
init → plan → tasks → implement
↑ ↑ ↑ ↑
└──────┴──────┴─────────┘
analyze/clarify (anytime)
```
### Core Principles
1. **Separation of Concerns**: Plans define WHAT, tasks define HOW
2. **Memory-Driven Compliance**: All execution references constitution.md and relevant memory files
3. **Idempotent Operations**: All commands safe to run repeatedly
4. **Deterministic Analysis**: analyze produces identical output for identical input
---
## Commands
### Plugin Command (Global)
| Command | Purpose | When to Use |
|---------|---------|-------------|
| `/speckit.init` | Establish .claude/ foundation with git, install project commands | New projects or incomplete setup |
### Project Commands (Installed by /speckit.init)
| Command | Purpose | When to Use |
|---------|---------|-------------|
| `/plan` | Create plans from specifications | After specs exist in speckit/ |
| `/tasks` | Generate tasks from plans | After plans are approved |
| `/design` | Generate detailed task designs | Before implementing complex tasks |
| `/analyze` | Audit project consistency | Anytime for health check |
| `/clarify` | Resolve ambiguities | When specs have open questions |
| `/implement` | Execute tasks with git checkpoint | When ready to implement |
| `/revert` | Revert to checkpoint with analysis | When implementation fails |
| `/lint` | Scan code for anti-patterns | Before code review or after implementation |
---
## Command: init
Establish the `.claude/` foundation with appropriate memory files for the project.
### Trigger
- Explicit: `/speckit.init`
- Automatic: Other commands detect missing setup
### Workflow
1. **Check existing state** - Detect if .claude/ exists
2. **Detect tech stack** - Analyze project for languages/frameworks
3. **Present detection** - Show detected stack and recommended memory files
4. **Create structure** - Build directory structure
5. **Copy memory files** - Select and copy based on tech stack
6. **Generate project context** - Create project-context.md
### Directory Structure Created
```
.claude/
├── commands/ # Custom project commands
├── memory/ # constitution.md + tech-specific files
│ └── MANIFEST.md
├── templates/ # Output templates
└── scripts/ # Project scripts
speckit/ # SpecKit artifacts (specs, plans, tasks, designs)
├── spec.md
├── plan.md
├── tasks.md
├── plans/ # Multi-domain plans (if complex)
└── designs/ # Design documents
```
### Memory File Selection
| Category | Files | Selection |
|----------|-------|-----------|
| Universal | constitution.md, documentation.md, git-cicd.md, security.md, testing.md | Always |
| TypeScript/JS | typescript.md | If TS/JS detected |
| React/Next.js | react-nextjs.md | If React/Next detected |
| Tailwind | tailwind-shadcn.md | If Tailwind detected |
| Python | python.md | If Python detected |
| Rust | rust.md | If Rust detected |
### Options
```
Options:
1. Accept recommended selection
2. Add additional memory files
3. Remove memory files from selection
4. Override detected stack manually
```
See `references/command-workflows/init-workflow.md` for detailed workflow.
---
## Command: plan
Create implementation plans from specification files. Hierarchical for complex/multi-domain specs.
### Trigger
- `/speckit.plan`
- `/speckit.plan spec.md`
- `/speckit.plan --all`
### Workflow
1. **Locate specs** - Find spec files in speckit/
2. **Assess complexity** - Single domain vs multi-domain
3. **Generate plans** - Create plan.md (and domain plans if complex)
4. **Validate** - Check plan completeness and consistency
### Output Structure
**Simple (single domain)**:
```
speckit/
├── spec.md
└── plan.md
```
**Complex (multi-domain)**:
```
speckit/
├── spec.md
├── plan.md # Master plan with domain references
└── plans/
├── domain-a-plan.md
├── domain-b-plan.md
└── domain-c-plan.md
```
### Plan Content
Plans contain:
- Requirements mapping (which spec sections covered)
- Architecture decisions
- Implementation approach (phases, NOT tasks)
- Verification strategy
- Notes for task generation
Plans do NOT contain:
- Individual tasks (that's /speckit.tasks)
- Implementation code
- Detailed how-to instructions
### Complexity Detection
| Indicator | Simple | Complex |
|-----------|--------|---------|
| Domains | Single | Multiple distinct |
| Page count | <10 pages | >10 pages |
| Stakeholder count | 1-2 | 3+ |
User can override detection.
See `references/command-workflows/plan-workflow.md` for detailed workflow.
---
## Command: tasks
Generate implementation tasks from plans + constitution + memory files.
### Trigger
- `/speckit.tasks`
- `/speckit.tasks plan.md`
- `/speckit.tasks --all`
### Workflow
1. **Load plan(s)** - Read plan files
2. **Load constitution** - Extract relevant sections
3. **Load memory files** - Get tech-specific guidelines
4. **Generate tasks** - Create *-tasks.md with phases
5. **Validate** - Check task completeness
### Output
```markdown
# [Domain] Tasks
## Phase 1: Foundation
### TASK-001: [Title]
**Status**: PENDING
**Priority**: P1
**Constitution Sections**: §4.1, §4.2
**Memory Files**: typescript.md, git-cicd.md
**Plan Reference**: PLAN-001
**Description**: ...
**Acceptance Criteria**:
- [ ] Criterion 1
- [ ] Criterion 2
```
### Task Statuses
| Status | Meaning |
|--------|---------|
| PENDING | Not started |
| IN_PROGRESS | Currently being worked |
| BLOCKED | Waiting on dependency |
| COMPLETED | Done and verified |
| SKIPPED | InRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.