implementation-notes
Keep a running implementation-notes.html while implementing a spec. Use this whenever the user asks to implement a SPEC, PRD, design doc, issue, or feature and wants ongoing notes about design decisions, spec interpretations, deviations, tradeoffs, or open questions. Also trigger for prompts like “maintain implementation notes”, “document how this diverges from the spec”, or “capture anything I should know as you build”.
What this skill does
# Implementation Notes
When implementing from a spec, maintain a running `implementation-notes.html` file alongside the work. The notes are for the human reviewer: they should explain how the implementation interprets the spec, where it diverges, and what the reviewer may need to confirm.
## Core workflow
1. Locate and read the spec before changing code.
2. Create or update `implementation-notes.html` near the project root unless the user names a different location.
3. Keep the notes current as you work, not just at the end. Add entries whenever you make a meaningful interpretation, decision, or deviation.
4. Prefer concise, scannable notes over a long narrative. The file should help the user review the implementation quickly.
5. Before handing off, do a final pass over the notes and make sure they match the actual implementation.
## What to capture
Include these sections:
- **Design decisions**: choices made where the spec was ambiguous or underspecified.
- **Deviations from spec**: intentional departures from the spec, with the reason.
- **Tradeoffs considered**: alternatives considered and why the implemented approach won.
- **Open questions**: anything the user should confirm, revise, or decide later.
Only include items that matter. Do not fill sections with generic statements; use “None so far” when a section is empty.
## File format
Write a complete, readable HTML document. Keep it dependency-free: inline CSS is fine, but do not require external scripts, CDNs, or build steps.
Use this structure as a starting point:
```html
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Implementation Notes</title>
<style>
body {
font-family: system-ui, sans-serif;
line-height: 1.5;
max-width: 900px;
margin: 2rem auto;
padding: 0 1rem;
}
h1,
h2 {
line-height: 1.2;
}
.meta {
color: #555;
}
li {
margin-block: 0.5rem;
}
code {
background: #f4f4f4;
padding: 0.1rem 0.25rem;
border-radius: 0.25rem;
}
</style>
</head>
<body>
<h1>Implementation Notes</h1>
<p class="meta">Updated: YYYY-MM-DD HH:MM</p>
<h2>Design decisions</h2>
<ul>
<li><strong>Decision:</strong> ... <br /><strong>Why:</strong> ...</li>
</ul>
<h2>Deviations from spec</h2>
<ul>
<li><strong>Deviation:</strong> ... <br /><strong>Why:</strong> ...</li>
</ul>
<h2>Tradeoffs considered</h2>
<ul>
<li>
<strong>Options:</strong> ... <br /><strong>Chosen:</strong> ... <br /><strong
>Reason:</strong
>
...
</li>
</ul>
<h2>Open questions</h2>
<ul>
<li>...</li>
</ul>
</body>
</html>
```
## Good notes
Good notes are specific and reviewable:
- “The spec says notifications should be sent after approval, but does not define retry behavior. I implemented three retries with exponential backoff to match the existing email worker.”
- “I did not implement bulk deletion because the spec mentions it only in the future-work section and there is no API contract yet.”
- “I chose server-side filtering over client-side filtering because the dataset can exceed 10k rows and the existing endpoint already supports indexed queries.”
Avoid vague notes like:
- “Made some UI decisions.”
- “Implemented differently for performance.”
- “Need to check stuff later.”
## Handoff
In the final response, mention the path to `implementation-notes.html` and summarize the most important open questions or deviations, if any. If there are no deviations or open questions, say so briefly.
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.