interactive-design-review
This skill should be used when a spec, PRD, design doc, RFC, or plan needs human sign-off and the user would rather review something visual than read markdown. Trigger when the user says "review this as HTML", "PRD as HTML", "PDR as HTML", "make a review doc", "I hate reading markdown", "let me approve this visually", "interactive review", or when about to ask for design approval before building. Produces ONE self-contained interactive HTML the user reviews section-by-section and approves, emitting a copyable Approve / Request-changes verdict to paste back.
What this skill does
# Interactive Design Review (PDR-as-HTML)
Turn a spec / PRD / design into a self-contained interactive HTML review the user
can skim, expand where they care, and approve — instead of reading raw markdown.
The artifact returns a **structured verdict** (Approve & build, or Request changes
with specific areas) the user copies back into the chat.
## When to use
- A design/spec/plan exists and needs explicit human approval before implementation.
- The user has signaled they dislike reading markdown or prefer visual/interactive review.
- A design-approval gate (e.g. after brainstorming, before building) where a vague
"looks good" is not good enough — a section-level, decision-weighted sign-off is wanted.
## Why it works
Reading a long markdown spec invites skimming and rubber-stamping. An interactive
review forces section-level attention, surfaces the heavy decisions visually, and
returns a verdict in a fixed format. In practice this catches missing requirements
*before* any code is written.
## Workflow
1. **Write the design to markdown first.** The markdown is the source of truth; the
HTML renders it. Never let the HTML become the only copy of the design.
2. **Build one self-contained HTML file** following
`../_shared/single-file-html-conventions.md` (inline CSS/JS, no deps, light/dark).
Write it next to the markdown (usually `docs/...-design.html`).
3. **One card per design section**, with a sticky side nav + scrollspy so the user can
jump and always knows their place.
4. **Tag each section by decision-weight** so the eye lands on what matters — e.g.
`COMMIT-NOW` (costly to change later), `DEFER` / `SNOOZE` (cheap to add later),
`RULE` (a hard constraint). Use distinct colors.
5. **Progressively disclose dense detail.** Keep cards scannable; put the reasoning,
per-item rationale, or option tables behind a click (expandable rows / details).
6. **Add a review-progress tracker** (e.g. "sections reviewed: 4/11") so long reviews
feel finite.
7. **Add a fixed approval bar** with two actions:
- **Approve & build** — optional notes → composes an approval verdict.
- **Request changes** — multiselect the areas to revise + free-text details →
composes a change-request verdict.
Each button writes a plain-text verdict and copies it to the clipboard (with a
visible confirmation and manual-select fallback) for the user to paste into chat.
8. **Loop on feedback.** When the user requests changes, edit BOTH the markdown and the
HTML (keep them in sync), re-deliver, and repeat until approved.
## Verdict format
The copied text must be unambiguous and self-contained, and its **literal first token must
be the marker word** (`APPROVED` / `REQUEST CHANGES`) — not an emoji, which clipboards and
terminals can strip. Put any emoji after the word. For example:
```
APPROVED — build <thing> as specified. Notes: <optional>.
```
or
```
REQUEST CHANGES before building. Areas: <picked areas>. Details: <text>.
```
Leading with the bare marker keeps the verdict reliably parseable by the next agent turn.
## Section content patterns
- **Decision tables** with click-to-expand rows for rationale (good for things like a
locked schema, config keys, or trade-off matrices).
- **Two-column "commit vs defer"** callouts to make the costly-vs-cheap split visible.
- **Hard-rule callouts** styled distinctly (e.g. a red left-border) for non-negotiables.
## Resources
- **`../_shared/single-file-html-conventions.md`** — the shared single-file HTML
technique (self-contained file, theming, copy-to-clipboard, density discipline).
- **`references/structure.md`** — the section/nav/approval-bar layout and verdict-button
logic in more detail, with a worked structure.
## Pitfalls
- Do not let the HTML drift from the markdown — edit both on every change.
- Do not bury the approval action; the verdict bar must be always reachable (fixed).
- Do not over-pack a card — if it needs paragraphs, move detail behind a disclosure.
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.