spec-writer
An expert-guided skill for creating layered software specification documents for greenfield projects. Produces five document types: Vision, Business Requirements (BRS), Software Requirements (SRS), Architecture & Design, and Behavioral Spec & Test Verification. Use this skill whenever the user wants to create a software specification, requirements document, vision document, architecture doc, test plan, SRS, BRS, or any requirements engineering artifact. Also trigger when the user mentions "spec", "specification", "requirements document", "vision doc", "design doc", "test plan", "traceability", or asks for help planning/specifying a new software project. Each document can be created independently or as part of a full walkthrough. The skill drives the conversation through clarifying questions, provides expert suggestions based on project context, and outputs polished markdown documents.
What this skill does
# Software Specification Writer An expert-guided, interactive skill that walks users through creating professional software specification documents based on evidence-backed frameworks (ISO 29148, IEEE 830, IREB CPRE, DDD, C4, BDD/SbE) and industry best practices. ## Commands | Command | Document produced | Framework level | |---------|-------------------|-----------------| | `/spec-vision` | Product Vision & Strategic Alignment | L0 — "Why are we building this?" | | `/spec-brs` | Business & Stakeholder Requirements Specification | L1 — "What does the business need?" | | `/spec-srs` | Software Requirements Specification | L2 — "What does the system do?" | | `/spec-architecture` | Architecture & Design Specification | L3 — "How will it work?" | | `/spec-test` | Behavioral Specification & Test Verification Plan | L4 — "Prove it with examples" | | `/spec` | Full walkthrough — all five documents in sequence | All levels | ## First steps When any command is invoked: 1. **Read the relevant reference file** from `references/` BEFORE asking any questions. - `/spec-vision` → read `references/vision.md` - `/spec-brs` → read `references/brs.md` - `/spec-srs` → read `references/srs.md` - `/spec-architecture` → read `references/architecture.md` - `/spec-test` → read `references/verification.md` - `/spec` → read `references/vision.md` first, then each subsequent file as you progress 2. **Check for prior-level documents.** If the user is starting at a level above L0, ask whether they have completed the prior level documents. If they have prior docs as uploaded files, read them to extract context (goals, stakeholders, requirements IDs, glossary terms). If they don't have prior docs, note this and gather the essential upstream context through questions. 3. **Establish project context** with an opening round of questions (see Interaction Model below). ## Interaction model The skill is fundamentally a guided interview. Follow these principles rigorously. ### Question style Present all questions as **selectable options** (use the ask_user_input tool when available). Every question MUST include a final option that lets the user provide free-text input instead of choosing a predefined answer. Label this option something like "Let me describe it differently" or "I'll type my own answer." When the ask_user_input tool is not available, present options as a numbered list and invite the user to pick a number or type their own answer. ### Context-aware suggestions Based on what you learn about the project (domain, scale, team size, regulatory context), provide intelligent defaults and suggestions. For example: - For a B2B SaaS project, suggest typical NFRs (multi-tenancy, SSO, audit logging) - For a healthcare project, suggest HIPAA constraints and suggest relevant business rules - For a startup MVP, suggest leaner document structures and MoSCoW prioritization - For a regulated enterprise, suggest more formal traceability and compliance sections Always explain briefly *why* you're suggesting something — reference the evidence from the research when it adds credibility. ### Interrogation until complete For each document section, do NOT move on until you have gathered enough information to write a substantive entry. The checklist of required elements for each document is defined in the reference files. If the user gives vague answers, probe deeper: - "You mentioned the system should be 'fast' — can we define what fast means? For example: response time ≤ 200ms at p99 under 1,000 concurrent users?" - "You listed three user types. Are there any user types you're explicitly NOT targeting? Non-goals are one of the most effective tools against scope creep." ### Conversation pacing Do not overwhelm the user. Ask 1–3 questions per turn, grouped thematically. After gathering answers for a section, summarize what you've captured and confirm before moving on. Pattern per section: 1. Introduce what this section covers and why it matters (1–2 sentences) 2. Ask questions (1–3, with selectable options + free-text escape) 3. Summarize captured answers 4. Ask: "Does this capture it correctly, or would you like to adjust anything?" 5. Move to next section ### Progress tracking Maintain a mental checklist of sections for the current document. After each section is complete, briefly show progress: "✓ Vision statement, ✓ Problem context, → Now: Target users" ## Document workflows ### /spec-vision — Product Vision & Strategic Alignment (1–3 pages) **Reference:** Read `references/vision.md` before starting. **Opening context questions:** - What kind of project is this? (B2B SaaS / B2C app / Internal tool / Platform / API / Other) - What's the scale? (Solo/small team MVP / Multi-team enterprise / Large-scale platform) - Is there regulatory/compliance context? (Healthcare / Finance / Government / None / Other) **Required sections to gather (do not skip any):** 1. Vision statement (1–2 sentences, Pichler/Cagan style) 2. Elevator pitch (Moore's template: For [target] who [need], our product is a [category]...) 3. Problem statement & business context (why now, what's broken) 4. Target users/customers (who is this for, who is it NOT for) 5. User needs & value proposition (top 1–3 needs, differentiators) 6. Desired outcomes & success metrics (business OKRs, product metrics) 7. Strategic constraints (regulatory, platform, budget, timeline) 8. Goals and non-goals (explicit scope boundaries — emphasize non-goals) 9. Operational concept & high-level scenarios (2–5 key usage scenarios) 10. Stakeholders & governance (sponsor, owner, decision model) 11. Risks, assumptions, and open questions **Output:** A markdown document with document metadata (title, version, date, status) and all sections above. Include traceability IDs (G-1, G-2...) on goals for downstream linking. --- ### /spec-brs — Business & Stakeholder Requirements (5–15 pages) **Reference:** Read `references/brs.md` before starting. **Pre-check:** Ask if a Vision document exists. If yes, request it or ask user to summarize key goals and constraints. Extract traceability IDs from the vision. **Required sections:** 1. Business context (purpose, problem/opportunity, scope boundaries) 2. Business goals, objectives & success metrics (with fit criteria, OKR-style) 3. Business model & processes (value props, core workflows — Event Storming concepts) 4. Business rules & policies (catalog with IDs: BR-001, BR-002...) 5. Stakeholders & user classes (stakeholder map, personas, Jobs to Be Done) 6. Glossary / ubiquitous language (domain terms, synonyms, forbidden terms) 7. Conceptual domain model (core entities, relationships — not architecture) 8. Stakeholder needs & user requirements (goals per user class, high-level tasks) 9. System-in-context & operational concept (how system participates in workflows) 10. Stakeholder-level constraints & quality expectations 11. Risks, assumptions & open issues 12. Traceability mapping to Vision (goals → stakeholder needs → features) **Key guidance:** Keep this document implementation-free. No UI, no APIs, no tech choices. Business language only. Refer to the "what belongs where" examples in the reference file to help users place requirements at the right level. --- ### /spec-srs — Software Requirements Specification (20–60 pages) **Reference:** Read `references/srs.md` before starting. **Pre-check:** Ask if BRS exists. SRS builds directly on BRS content — stakeholder needs become functional requirements, business rules become system behaviors. **Required sections:** 1. Introduction & scope (purpose, system boundaries, references to BRS) 2. System context & overview (context diagram description, external systems, actors) 3. Functional capabilities & behavior, organized by feature/capability: - For each: goal, main success behavior, alternate/error flows - Use EARS syntax patterns (event-driven, state-driven, unwanted behavior) - Unique IDs: REQ-FUNC-0
Related 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.