icon-finder
Find Red Hat Design System icons (@rhds/icons) by keyword or use case with visual previews. Use when choosing an icon for a UI element or looking up available icons.
What this skill does
# Icon Finder (Red Hat Icons)
Find UI icons from [@rhds/icons](https://github.com/RedHat-UX/red-hat-icons) based on a described use case.
## Workflow
1. **Interpret use case** – Derive 1–3 search terms from the user's message (e.g. "merge" → merge, combine, branch; "export" → export, download, share).
2. **Get icon list** – Fetch the demo site: `https://red-hat-icons.netlify.app/`. Extract **only** icon names from lines containing `set="ui"` — look for the pattern `set="ui" icon="<name>"`. Ignore icons from any other set.
3. **Match** – Filter the `ui` icon names by your search terms. Prefer exact or prefix match. When an icon has a `-fill` counterpart, treat them as **one result** (they share a card in the preview). Return **5–8** unique icon concepts.
4. **Generate preview** – Build an HTML file using the template below. Each icon is loaded via an `<img>` tag pointing to the raw GitHub URL — no API calls or base64 decoding needed. Write to `icon-finder-preview.html` in the user's workspace or home directory.
5. **Open preview** – Open the HTML file in the user's default browser (see "Opening the preview" section).
6. **Respond** – Show the match table. Then ask: *"Do any of these work, or would you like me to do a deeper search? I can cast a wider net using related concepts and synonyms you might not have thought of."*
7. **Deep search (only if the user asks for it)** – See "Deep search fallback" section below.
## Icon set
This skill uses **only** the `ui` set (interface actions, status, navigation — ~542 icons). Do not search or return icons from any other set (`standard`, `microns`, `social`).
## Response format
```markdown
### Matches for "[use case]"
| Icon | Fill | Use when |
|------|------|----------|
| `hybrid-cloud` | yes | Multi-provider dashboards, infrastructure overview pages. |
| `multi-cloud` | no | Provider comparison views, cloud strategy settings. |
...
**Usage:**
\`\`\`html
<rh-icon set="ui" icon="hybrid-cloud"></rh-icon>
\`\`\`
Install: `npm install @rhds/icons`
Do any of these work, or would you like me to do a deeper search? I can cast a wider net using related concepts and synonyms you might not have thought of.
```
## Raw SVG URL pattern
Each icon's SVG is available at:
```
https://raw.githubusercontent.com/RedHat-UX/red-hat-icons/main/src/ui/<icon-name>.svg
```
For example: `https://raw.githubusercontent.com/RedHat-UX/red-hat-icons/main/src/ui/cluster.svg`
## HTML preview template
Use this exact template. It loads PatternFly 6 CSS from a CDN — no build step required. Replace `<!-- ICONS -->` with one card per match. Icons are loaded as `<img>` tags — the user's browser fetches them directly from GitHub.
```html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Icon Finder – Results</title>
<link rel="stylesheet" href="https://unpkg.com/@patternfly/patternfly@6/patternfly.min.css">
<style>
.icon-finder-page { padding: var(--pf-t--global--spacer--xl); }
.icon-finder-header { margin-bottom: var(--pf-t--global--spacer--lg); }
.icon-card { text-align: center; }
.icon-variants { display: flex; justify-content: center; gap: var(--pf-t--global--spacer--md); margin-bottom: var(--pf-t--global--spacer--sm); }
.icon-variant { display: flex; flex-direction: column; align-items: center; text-decoration: none; color: inherit; cursor: pointer; }
.icon-variant img { width: 40px; height: 40px; }
.icon-variant span { font-size: var(--pf-t--global--font--size--xs); color: var(--pf-t--global--text--color--link--default); text-decoration: underline; margin-top: var(--pf-t--global--spacer--xs); }
.icon-variant:hover img { transform: scale(1.15); }
.icon-variant:hover span { color: var(--pf-t--global--text--color--link--hover); }
.icon-name { font-weight: var(--pf-t--global--font--weight--body--bold); font-size: var(--pf-t--global--font--size--sm); word-break: break-word; }
.icon-hint { font-size: var(--pf-t--global--font--size--xs); margin-top: var(--pf-t--global--spacer--xs); }
.icon-finder-footer { margin-top: var(--pf-t--global--spacer--xl); }
</style>
</head>
<body>
<div class="icon-finder-page">
<div class="icon-finder-header pf-v6-c-content">
<h1>Icon Finder Results</h1>
<p>From <a href="https://github.com/RedHat-UX/red-hat-icons">@rhds/icons</a> (set: UI)</p>
<p><strong>Prompt:</strong> <!-- PROMPT --></p>
<p><strong>Search terms:</strong> <!-- TERMS --></p>
</div>
<div class="pf-v6-l-gallery pf-m-gutter" style="--pf-v6-l-gallery--GridTemplateColumns--min: 160px;">
<!-- ICONS -->
</div>
<div class="icon-finder-footer pf-v6-c-content">
<p>Don't see what you need? <a href="https://docs.google.com/forms/d/e/1FAIpQLSfXbS0o6oeMA86CpmuTKIoZrrKVhbjKboBrHl2jIPJDfkt_MQ/viewform" target="_blank">Submit a custom icon request</a>.</p>
</div>
</div>
</body>
</html>
```
Each card replaces `<!-- ICONS -->`. All cards use the same structure — a `<div>` card with one or two icon variants inside. Each variant is an independently clickable `<a>`.
**Card with fill variant** (two variants side-by-side):
```html
<div class="pf-v6-c-card icon-card">
<div class="pf-v6-c-card__body">
<div class="icon-variants">
<a class="icon-variant" href="https://github.com/RedHat-UX/red-hat-icons/blob/main/src/ui/ICON-NAME.svg" target="_blank">
<img src="https://raw.githubusercontent.com/RedHat-UX/red-hat-icons/main/src/ui/ICON-NAME.svg" alt="ICON-NAME">
<span>outline</span>
</a>
<a class="icon-variant" href="https://github.com/RedHat-UX/red-hat-icons/blob/main/src/ui/ICON-NAME-fill.svg" target="_blank">
<img src="https://raw.githubusercontent.com/RedHat-UX/red-hat-icons/main/src/ui/ICON-NAME-fill.svg" alt="ICON-NAME-fill">
<span>fill</span>
</a>
</div>
<div class="icon-name">icon-name</div>
<div class="icon-hint">UI context: <em>where in a software UI this icon fits</em></div>
</div>
</div>
```
**Card without fill variant** (single variant):
```html
<div class="pf-v6-c-card icon-card">
<div class="pf-v6-c-card__body">
<div class="icon-variants">
<a class="icon-variant" href="https://github.com/RedHat-UX/red-hat-icons/blob/main/src/ui/ICON-NAME.svg" target="_blank">
<img src="https://raw.githubusercontent.com/RedHat-UX/red-hat-icons/main/src/ui/ICON-NAME.svg" alt="ICON-NAME">
<span>outline</span>
</a>
</div>
<div class="icon-name">icon-name</div>
<div class="icon-hint">UI context: <em>where in a software UI this icon fits</em></div>
</div>
</div>
```
Replace `<!-- PROMPT -->` with the user's original message and `<!-- TERMS -->` with a comma-separated list of the search terms derived in step 1 of the workflow.
## Opening the preview
After writing `icon-finder-preview.html`, open it in the user's default browser. The page loads PatternFly CSS from a CDN and icon SVGs from GitHub, so it works fine as a local file — no server needed.
## Deep search fallback
The initial search matches on direct keywords only. If the user isn't satisfied, the deep search expands to synonyms, related concepts, and adjacent terminology they may not have thought of.
### How it works
1. **Expand the search terms** — Starting from the user's original use case, brainstorm 10–20 related terms across these categories:
- **Synonyms:** direct alternatives (e.g. "merge" → combine, join, unite, fuse)
- **Related concepts:** things in the same domain (e.g. "cloud cluster" → topology, network, hub, infrastructure, region)
- **Abstract/metaphorical:** shapes or ideas that could represent the concept (e.g. "cluster" → nodes, grid, constellation, beehive, atom)
- **Technical terms:** domain-specific jargon (e.g. "cloud environments" → tenant, orchestration, federation, interoperability)
2. **Re-scan the full icon list** — Using the already-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.