spec-dd
This skill should be used when the user asks to "write specifications", "create test specifications", "specification-driven development", "spec-first", "behavioral specs", "derive test scenarios", "test implementation specification", "check specification alignment", "review specs", "verify implementation", or "spec-dd". Also triggers when the user mentions "SDD", "SDD-TDD", "spec-driven", "behavioral testing workflow", "test-first design", or asks about writing specifications before code, deriving tests from specs, or verifying implementation against specifications. Supports a full workflow walkthrough or focusing on individual phases.
What this skill does
# Specification-Driven Development
Orchestrate a spec-first development workflow: behavioral specification, test
scenario derivation, test implementation planning, test implementation, feature
implementation, and cross-artifact alignment review. The skill guides writing
behavioral specifications, derives test scenarios, plans test implementation
approaches, and verifies alignment across all artifacts and code. Quality gates
between phases are advisory — the skill flags issues and recommends addressing
them, but the user can override and proceed.
## Commands
| Command | Phase | Reference |
|---------|-------|-----------|
| `/spec-dd` | Auto-detect phase, assess state, recommend next step | All references |
| `/spec-dd:spec` | Behavioral Specification | `references/specification.md` |
| `/spec-dd:test` | Test Specification | `references/test-specification.md` |
| `/spec-dd:test-impl` | Test Implementation Specification | `references/test-implementation-specification.md` |
| `/spec-dd:verify` | Implementation Verification | `references/verify.md` |
| `/spec-dd:review` | Alignment Review | `references/review.md` |
All commands accept an optional feature name argument (e.g., `/spec-dd:spec user-auth`).
`/spec-dd:verify` also accepts a spec file path as its first argument
(e.g., `/spec-dd:verify specifications.md chat-ui`). This allows verification against
any spec file, including informal ones not created through the spec-dd workflow.
If no feature name is provided and multiple features exist, list available features and
ask the user to choose.
## Artifacts
All artifacts live in `docs/specs/` with one set of files per feature:
| Artifact | Filename |
|----------|----------|
| Behavioral Specification | `docs/specs/<feature>-specification.md` |
| Test Specification | `docs/specs/<feature>-test-specification.md` |
| Test Implementation Specification | `docs/specs/<feature>-test-implementation-specification.md` |
| Implementation Verification | `docs/specs/<feature>-verification.md` |
| Implementation Review | `docs/specs/<feature>-implementation-review.md` |
## First Steps
When any command is invoked:
1. **Read the relevant reference file** from `references/` BEFORE doing anything else.
- `/spec-dd:spec` -> read `references/specification.md`
- `/spec-dd:test` -> read `references/test-specification.md`
- `/spec-dd:test-impl` -> read `references/test-implementation-specification.md`
- `/spec-dd:verify` -> read `references/verify.md`
- `/spec-dd:review` -> read `references/review.md`
- `/spec-dd` -> read whichever reference applies to the recommended phase
2. **Auto-detect project language** by scanning for manifest files:
- `package.json` (JavaScript/TypeScript)
- `requirements.txt`, `pyproject.toml` (Python)
- `go.mod` (Go)
- `Cargo.toml` (Rust)
- `pom.xml`, `build.gradle` (Java/Kotlin)
- Use the detected language/ecosystem to inform testing frameworks, patterns,
idioms, and handoff prompts throughout the workflow.
3. **For `/spec-dd` (router):** Follow the auto-detect router logic below.
4. **For `/spec-dd:<phase>`:** Check whether prior-phase artifacts exist. If gaps
are found, advise the user which earlier phase to complete first, but do not
block — proceed if the user chooses to continue.
## Phase 1: Behavioral Specification (`/spec-dd:spec`)
**Reference:** Read `references/specification.md` before starting.
**Purpose:** Define what the system does — behavioral contracts, not implementation
details.
**Workflow:**
1. Guide the user through creating or reviewing the behavioral specification for
the selected feature.
2. Use selectable options plus a free-text escape for every question. Ask 1-3
questions per turn, grouped thematically. Summarize captured answers before
moving on.
3. Review for ambiguity:
- Vague language ("fast", "secure", "easy", "simple", "efficient")
- Missing edge cases and boundary conditions
- Undefined terms and implicit assumptions
- Unmeasurable acceptance criteria
4. Mark any unresolved items with `[NEEDS CLARIFICATION]`.
5. Produce or update `docs/specs/<feature>-specification.md`.
**Advisory gate:** No unresolved `[NEEDS CLARIFICATION]` markers before proceeding
to Phase 2.
**Artifact template:**
```markdown
# <Feature> - Behavioral Specification
## Objective
What this feature does and why it exists.
## User Stories & Acceptance Criteria
Numbered user stories, each with measurable acceptance criteria.
## Constraints
Technical, business, or regulatory constraints.
## Edge Cases
Boundary conditions, error states, unusual inputs.
## Non-Goals
What this feature explicitly does NOT do.
## Open Questions
Items marked [NEEDS CLARIFICATION] that must be resolved.
```
## Phase 2: Test Specification (`/spec-dd:test`)
**Reference:** Read `references/test-specification.md` before starting.
**Purpose:** Derive test scenarios from the behavioral spec only — no implementation
knowledge.
**Pre-check:** Verify that `<feature>-specification.md` exists. If it does not,
advise the user to complete Phase 1 first. If the user chooses to proceed anyway,
note the risk and continue.
**Workflow:**
1. Derive Given/When/Then scenarios from each acceptance criterion in the
behavioral specification.
2. Enforce one behavior per scenario, one action per step.
3. Build a coverage matrix mapping every spec requirement to test scenarios.
4. Language-aware review: ensure scenarios are realistic and testable for the
project's detected testing ecosystem.
5. Check traceability: every acceptance criterion must have at least one test
scenario.
6. Produce or update `docs/specs/<feature>-test-specification.md`.
**Advisory gate:** Full traceability between spec requirements and test scenarios
before proceeding to Phase 3.
**Artifact template:**
```markdown
# <Feature> - Test Specification
## Coverage Matrix
Table mapping each acceptance criterion to its test scenarios.
## Test Scenarios
Given/When/Then format. Grouped by user story or functional area.
## Edge Case Scenarios
Boundary conditions derived from the specification's edge cases section.
## Traceability
Summary confirming every acceptance criterion is covered.
```
## Phase 3: Test Implementation Specification (`/spec-dd:test-impl`)
**Reference:** Read `references/test-implementation-specification.md` before starting.
**Purpose:** Map every test scenario to a technical approach for implementing it
as actual test code.
**Pre-check:** Verify that `<feature>-test-specification.md` exists. If it does
not, advise the user to complete Phase 2 first. Proceed if the user overrides.
**Workflow:**
1. Guide the user through describing the technical approach for implementing
each test scenario as actual test code.
2. Use language-aware patterns: test framework selection, fixture strategies,
mock/stub approaches, test file organization.
3. Map every test scenario from the test specification to specific test
functions, test classes, or test modules.
4. Describe shared fixtures, test data factories, and setup/teardown strategies.
5. Verify completeness: every Given/When/Then scenario has a corresponding
test implementation approach.
6. Produce or update `docs/specs/<feature>-test-implementation-specification.md`.
**Advisory gate:** Every test scenario mapped to a test implementation approach
before proceeding to Phase 4.
**Artifact template:**
```markdown
# <Feature> - Test Implementation Specification
## Test Framework & Conventions
Detected stack, test framework, test runner, conventions.
## Test Structure
How tests are organized: files, classes/modules, naming conventions.
## Test Scenario Mapping
Map each test scenario to a test function/method with setup and assertion strategy.
## Fixtures & Test Data
Shared fixtures, factories, test data approach, setup/teardown.
## Alignment Check
Confirmation that every test scenario has a test implementation approach.
```
## Phase 4: Test ImpleRelated 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.