research-decision-room
Turn messy user research notes, interviews, support tickets, surveys, and product context into an evidence-backed decision room: a single HTML artifact with an evidence ledger, theme map, confidence heatmap, opportunity matrix, decision memo, and experiment queue. Use when teams need to move from qualitative signals to product or design decisions without fabricating certainty.
What this skill does
# Research Decision Room Skill
Create a single-page HTML decision artifact that helps a product or design team
turn messy evidence into a clear next move. The output is not a decorative
research deck. It is a working room for debate: evidence, themes, confidence,
tradeoffs, and recommended experiments stay visible together.
## Resource map
```text
research-decision-room/
├── SKILL.md
├── example.html
└── references/
├── checklist.md
└── evidence-model.md
```
Read `references/evidence-model.md` before synthesis and run
`references/checklist.md` before emitting the artifact.
## When to use this skill
Use this skill when the user has any mix of:
- Interview notes, usability-test observations, support tickets, sales call notes,
app-store reviews, NPS comments, survey open text, analytics snippets, or
product-decision context.
- A decision that needs evidence: "Should we build X?", "Which onboarding path
should we try?", "Why are users dropping off?", "What do customers actually
mean by slow?"
- A need to share findings with stakeholders who will not read a long research
report.
Do not use it for pure visual inspiration, campaign ideation, or brand moodboards.
## Workflow
### Step 1 - Establish the decision frame
Identify the decision scope from the user's prompt. If the user did not give a
decision, derive one from the evidence and label it as inferred.
Write a short frame with:
- Decision question.
- Audience or segment.
- Time horizon.
- Known constraints.
- What this artifact will not decide.
If key context is missing and the task is not blocked, proceed with labelled
assumptions instead of asking a broad question.
### Step 2 - Build the evidence ledger
Normalize every useful signal into ledger rows using the model in
`references/evidence-model.md`.
Each ledger row must include:
- `id`: short stable id, such as `I-03`, `T-14`, `M-02`.
- `source_type`: interview, usability, support, survey, analytics, sales, field
note, or stakeholder.
- `segment`: user type or "unknown".
- `signal`: one-sentence observation.
- `quote_or_metric`: direct quote, metric, or "not provided".
- `strength`: strong, medium, or weak.
- `limitations`: why this evidence may be biased or incomplete.
Never invent quotes, participant counts, dates, revenue impact, or metrics. If
the user did not provide a number, use "not provided" and explain what evidence
would increase confidence.
### Step 3 - Synthesize themes and tensions
Cluster evidence into 4 to 6 themes. For each theme:
- Name the theme in plain human language.
- List the evidence ids that support it.
- Explain the behavior behind it, not just the UI complaint.
- Mark confidence as high, medium, or low.
- Note contradictions or segment differences.
Prefer verbs over nouns: "Teams abandon setup when the first blank state asks
for too much" is better than "Onboarding problem".
### Step 4 - Score opportunities
Create an opportunity matrix with 3 to 5 options. Score each option on a 1 to 5
scale:
- Evidence strength.
- User pain.
- Business leverage.
- Implementation risk, where 5 means low risk and 1 means high risk.
Show the total score, but do not let the score replace judgment. Add one sentence
on why the top recommendation wins.
### Step 5 - Draft the decision memo
Write a decision memo with:
1. Recommended move.
2. Why now.
3. What evidence supports it.
4. What could be wrong.
5. What to measure next.
6. Reversible next step.
Keep the memo short enough to read in under one minute.
### Step 6 - Create the HTML artifact
Produce a self-contained `index.html`. Use the active `DESIGN.md` for typography,
spacing, color roles, and component tone, but keep the information architecture
stable:
1. Header with decision question, confidence, and last-updated label.
2. Executive readout with recommendation, risk, and next experiment.
3. Evidence ledger with filter chips.
4. Theme map with evidence ids and confidence.
5. Opportunity matrix.
6. Decision memo.
7. Experiment queue with owner, metric, and success threshold.
8. Assumptions and limitations.
The artifact should be interactive but durable. Simple vanilla JavaScript is
allowed for filtering evidence, switching views, or highlighting related ids.
No framework dependency is required.
### Step 7 - Self-check and emit
Run the checklist. Then emit one concise orientation sentence and one HTML
artifact:
```xml
<artifact identifier="research-decision-room" type="text/html" title="Research Decision Room">
<!doctype html>
<html>...</html>
</artifact>
```
Nothing after the closing `</artifact>`.
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.