doc-coauthoring
Guide users through a structured 3-stage workflow for co-authoring documentation — Context Gathering, Refinement & Structure, and Reader Testing. Use this skill whenever the user wants to write documentation, proposals, technical specs, decision docs, RFCs, PRDs, design docs, or any structured content. Trigger when the user mentions writing docs, drafting a proposal, creating a spec, writing up decisions, or similar documentation tasks, even if they just say "write a doc" or "let's draft something."
What this skill does
# Doc Co-Authoring Workflow A structured workflow for collaborative document creation through three stages: Context Gathering, Refinement & Structure, and Reader Testing. ## Workflow Overview Documents created without structured collaboration often fail their readers — the author's implicit knowledge creates blind spots that only surface after publication. This workflow closes the gap by systematically gathering context, building content section-by-section, and testing the result with a fresh perspective before sharing. ### Stage Summary | Stage | Goal | Exit Condition | |-------|------|----------------| | **1. Context Gathering** | Close the knowledge gap between user and Claude | Edge cases and trade-offs can be discussed without needing basics explained | | **2. Refinement & Structure** | Build the document section by section through brainstorming and curation | All sections drafted, refined, and reviewed for coherence | | **3. Reader Testing** | Verify the document works for readers who lack the author's context | Fresh Claude instance answers reader questions correctly and surfaces no new gaps | ## Trigger Conditions Offer this workflow when the user: - Mentions writing documentation: "write a doc", "draft a proposal", "create a spec", "write up" - References specific doc types: PRD, design doc, decision doc, RFC, technical spec - Appears to be starting a substantial writing task ### Initial Offer Present the three stages and explain the value: this approach catches blind spots before others read the document. Ask whether the user prefers this structured workflow or freeform collaboration. If the user declines, work freeform. If the user accepts, proceed to Stage 1. ## Stage 1: Context Gathering Gather all relevant context before writing begins. The goal is to reach a level of understanding where questions can target edge cases and trade-offs rather than basics. See [context-gathering.md](references/context-gathering.md) for the detailed interview process, including initial questions, info dumping guidance, integration usage, and clarifying question patterns. **Key activities:** 1. Ask meta-context questions (doc type, audience, desired impact, template, constraints) 2. Encourage the user to dump all context in whatever format works for them 3. Pull in context from connected tools (Slack, Drive, etc.) when available 4. Ask 5-10 clarifying questions based on gaps 5. Repeat until understanding reaches the edge-case level **Transition:** Ask if there is more context to provide, or if it is time to start drafting. ## Stage 2: Refinement & Structure Build the document section by section through a brainstorm-curate-draft-refine cycle. See [refinement-structure.md](references/refinement-structure.md) for the detailed per-section workflow, output format handling, and quality checks. **Per-section cycle:** 1. **Clarify** — Ask 5-10 questions about what the section needs 2. **Brainstorm** — Generate 5-20 candidate points, surfacing forgotten context and new angles 3. **Curate** — User selects what to keep, remove, or combine 4. **Gap Check** — Confirm nothing important is missing 5. **Draft** — Write the section using `str_replace` on the scaffold 6. **Refine** — Iterate on edits until the user is satisfied **Section ordering:** Start with the section that has the most unknowns (core proposal for decision docs, technical approach for specs). Leave summary sections for last. **Near completion:** After 80% of sections are done, re-read the entire document and check for flow, consistency, redundancy, contradictions, and filler content. ## Stage 3: Reader Testing Test the document with a fresh Claude instance (no context from the authoring conversation) to catch blind spots. See [reader-testing.md](references/reader-testing.md) for testing procedures for both sub-agent and manual approaches, plus the final review checklist. **Key activities:** 1. Predict 5-10 questions readers would realistically ask 2. Test each question with a fresh Claude instance 3. Run additional checks for ambiguity, false assumptions, and contradictions 4. Fix any gaps found, then retest **Exit condition:** Reader Claude consistently answers correctly and surfaces no new gaps. ## Guidance Principles ### Tone - Be direct and procedural - Explain rationale briefly when it affects user behavior - Execute the process rather than selling it ### Handling Deviations - If the user wants to skip a stage, ask if they prefer freeform writing instead - If the user seems frustrated, acknowledge the pace and suggest ways to accelerate - The user retains agency to adjust the process at any point ### Context Management - Address knowledge gaps as they arise rather than letting them accumulate - Track what has been learned and what remains unclear throughout ### Output Management - Use `create_file` / artifacts when available for the document scaffold - Use `str_replace` for all edits — reprinting the entire document wastes tokens and makes changes harder to track - Create a markdown file in the working directory when artifacts are unavailable - Brainstorming lists belong in conversation, not in the document artifact ### Quality Focus - Each iteration targets meaningful improvements - The goal is a document that actually works for its readers, which requires patience through the stages
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.