docs-writer
Generates structured product and technical documents through guided discovery. 4 document types: PRD, Brief (1-page summary generated alongside PRD), Design Doc (single project-wide living technical document covering strategy through prescriptive plan), ADR (single architecture decision record, append-only log). Use when defining product requirements, drafting product specs, designing systems, recording architecture decisions, or maintaining the project's living technical doc. Not for feature spec tied to implementation or meeting/session notes.
What this skill does
# Docs Writer Generates structured product and technical documents through guided discovery. 4 document types, each with its own workflow depth. ## Quick start ```text trigger --> detect type --> load reference --> discovery --> drafting ``` Detect document type from the trigger. If ambiguous, ask the user. | Type | Reference | |------|-----------| | PRD — product requirements | [prd.md](references/prd.md) | | Design Doc — single project-wide living technical document | [design.md](references/design.md) | | ADR — single accepted decision record | [adr.md](references/adr.md) | Auto-loaded (no direct triggers): - `discovery.md` — by PRD, Design Doc, ADR at start of discovery - `quality.md` — before presenting any draft - `brief.md` — by `prd.md` during drafting (Brief is generated alongside the PRD, never independently) ## Document Boundaries - **PRD** — product only: problem, users, scope, journeys, rules, metrics. No implementation, architecture, tech stack, UI, or API. - **Brief** — 1-page narrative summary of the PRD. Generated alongside, no standalone trigger. - **Design Doc** — single project-wide living technical document. Covers strategy, trade-offs, and prescriptive plan (domain, conventions, architecture, security, observability, testing, deployment). Lifecycle tracked via frontmatter `status`: draft → accepted → in-progress → shipped → superseded. Context section recaps the project in 1-2 paragraphs and links to the PRD; never duplicates product prose. - **ADR** — single architecture decision (1-2 pages). Numbered, immutable once accepted; superseded by new ADRs, never edited. Use when lifting decisions from a PRD/Design Doc or recording retrospectively. When extracted from a Design Doc Alternatives row, the design doc row's `Record` column is updated to the ADR ID and the ADR's References link back to the design doc section anchor. ## Guidelines - Always complete discovery before drafting (for types that require it) - Review the artifact before presenting (load `quality.md`) - Present draft for user feedback before saving - Mark unknowns as TBD rather than inventing constraints - Use concrete, measurable requirements - Keep each document within its domain (PRD = product, Design Doc / ADR = technical) - One decision per ADR — never bundle multiple decisions into a single record - One Design Doc per project — major rewrites spawn `design-doc-v2.md` and supersede the old via frontmatter ## Anti-Pattern: Yes-Man Discovery Discovery is not a formality. When a problem statement is vague, evidence is thin, scope keeps expanding, or the user jumps to solution before naming the problem, push back. Ask for evidence, narrow scope, challenge weak ideas, suggest pivots when the proposed approach is fragile. Gate advancement on understanding, not on willingness to move on. ## Anti-Pattern: ADR as Design Doc ADR records *one* decision after it's been made — context, decision, consequences, alternatives. Design Doc carries the living narrative of trade-offs across the project. Writing a long ADR that weighs several open options is a Design Doc in disguise; writing a Design Doc that captures a single accepted choice is an ADR padded with prose. If the decision is still in motion, leave it in the Design Doc's Alternatives Considered table with `Record = —`. Once accepted, extract it into an ADR, update the design doc row's `Record` column to `ADR-NNNN`, and link the ADR's References back to the design doc section anchor. ## Anti-Pattern: Vague Requirements "Search should be fast", "easy to use", "intuitive interface" are not requirements — they're aspirations. Requirements must be measurable: "Search returns results within 200ms", "new users complete onboarding in under 2 minutes", "task completion rate above 90% without help text". If a requirement can't be measured, it can't be verified. ## Anti-Pattern: Product Prose in Technical Sections A Design Doc's Context section recaps the project in 1-2 paragraphs and links to the PRD. It does not restate Problem Statement, list Personas, or walk through Journeys. Goals translate product NFRs into technical targets (latency, throughput, isolation); they do not echo product KPIs (DAU, conversion, NPS). If a reviewer cannot tell whether they are reading the PRD or the Design Doc, the Context is too long or the Goals are not technical. Cut and link. ## Anti-Pattern: Technical Detail in PRD A PRD describes the product: problem, users, scope, journeys, business rules, success metrics. It does not specify architecture, tech stack, APIs, UI components, or any "how it is built" detail. Discussions of microservices vs monolith, SQL vs NoSQL, REST vs GraphQL, framework choice, or deployment topology belong in the Design Doc. If a PRD section reads like it could be implemented in two ways and the reviewer is asked to choose, that section is a technical decision in disguise — extract it to the Design Doc or ADR and leave a link in its place.
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.