new-design-doc
Proactively suggest creating a design document when discussing significant changes, new features, or architectural decisions. Also triggers when user has existing markdown docs that should be converted to org-mode. Use when conversation involves design decisions that should be documented, when user mentions RFC/RFD/design doc, or when proposing changes that warrant formal documentation. Trigger on phrases like "we should document this", "this needs an RFC", "let me think through the design", "convert this to org", or when discussing tradeoffs between multiple approaches.
What this skill does
# Design Doc Suggestion This skill helps identify when a design document should be created and guides the process. ## Prerequisites **Before triggering, check that the project has been set up with the backlog system.** Look for either: - `backlog.org` in the project root, OR - `docs/design/` directory exists If neither exists, do NOT proactively trigger this skill. The project hasn't been set up with the backlog system yet. Silently skip - don't suggest setup or explain why the skill isn't running. **Exception:** If the user explicitly asks to "create a design doc" or similar, you may suggest running `/backlog:setup` first to initialize the system. ## When to Offer This **Trigger conditions for NEW design doc:** - Discussion involves significant architectural decisions - Multiple approaches are being weighed with tradeoffs - User mentions "RFC", "RFD", "design doc", "proposal" - User says "we should document this", "let me think through..." - A feature requires coordination across multiple components - Changes that will affect how others use the system **Trigger conditions for CONVERTING existing markdown:** - User mentions "convert to org", "migrate to org-mode" - User has markdown design docs in `docs/legacy/` or similar - User asks about integrating old documentation - Discussion references existing `.md` design documents - User says "we have an old RFC", "there's a markdown doc for this" **Proactive offers:** For new doc: "This seems like a significant design decision. Should I create a design doc to capture the motivation, options, and decision? That would help track the rationale and any implementation tasks." For conversion: "I see there's an existing markdown document for this. Should I convert it to org-mode format? I can extract the tasks, assign IDs, and optionally queue them to the backlog." ## Workflow ### 1. Confirm Scope Ask: - What's the one-sentence summary? - What category? (read valid categories from `README.org`'s `* Document Categories` table) - Any specific options already being considered? - (If converting) Which markdown file should I convert? ### 2. Create the Document **For new docs:** Use `/new-design-doc <title>` to scaffold, then: 1. Fill in **Summary** - one paragraph overview 2. Fill in **Motivation** - why this matters, what problem it solves 3. Fill in **Design** - options considered with tradeoffs 4. Add **Tasks** - implementation work with `[PROJECT-NNN-XX]` IDs 5. Add **Questions** - open issues as `** OPEN` **For conversion:** Use `/new-design-doc <title> <source.md>` to convert, then: 1. Review the converted structure 2. Verify task IDs are properly assigned 3. Check that code blocks converted correctly 4. Offer to queue tasks to backlog ### 3. Use Org-Mode Properly Remind yourself: - Documents are numbered sequentially (001, 002, ...) - check existing docs for next number - Add `#+CATEGORY:` to frontmatter (use categories from `README.org`) - Use `** TODO [PROJECT-NNN-XX] Task title` (not markdown checkboxes) - Use `** OPEN Question` / `** DECIDED Question` (not plain text) - Add `:PROPERTIES:` for EFFORT, VERSION, DECIDED date - Reference the template: `docs/design/000-template.org` ### 4. Update Index Add the new doc to `docs/design/README.org` in the appropriate section. ### 5. Queue Tasks (for conversions) After converting, offer to queue extracted tasks: - List tasks with their new IDs - Ask which to queue to backlog Active section - Use `/task-queue` for each selected task ## What Makes a Good Design Doc | Section | Good | Bad | |------------|-------------------------------------------|------------------------| | Summary | "Add caching layer to reduce API latency" | "Caching stuff" | | Motivation | Explains the problem and why it matters | Jumps to solution | | Design | Shows 2-3 options with tradeoffs | Only shows chosen option| | Tasks | Specific, actionable, has IDs | Vague, no IDs | ## Conversion Rules Summary | Markdown | Org-Mode | |----------|----------| | `## Heading` | `* Heading` | | `- [ ] Task` | `** TODO [PROJECT-NNN-XX] Task` | | `- [x] Task` | `** DONE [PROJECT-NNN-XX] Task` | | ` ```lang` | `#+begin_src lang` | | `[text](url)` | `[[url][text]]` | ## Files - Template: `docs/design/000-template.org` - Index: `docs/design/README.org` - Examples: Any existing `docs/design/NNN-*.org`
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.