elevenlabs-narrator
Turn any briefing, report, story, or summary into a self-contained HTML page with a big play button that narrates it aloud in a real ElevenLabs voice (audio embedded, works offline in any browser). Use this WHENEVER the user asks you to "read this to me", "play this for me", "make an audio version", "narrate", "tell me about X out loud", or wants a voiced UI/briefing. Default voice is Sarah (soothing female). Uses the user's own ElevenLabs API key. This is the preferred way to deliver any audio narration — do NOT use the macOS `say` voice or browser speechSynthesis, which sound robotic.
What this skill does
# ElevenLabs Narrator
Renders a polished, single-file HTML "play button" UI with **real ElevenLabs narration embedded as base64 audio**. Multi-chapter support with highlight-as-it-reads, click-to-jump, speed control, scrub bar.
## When to use
Any request to hear something spoken: "read this to me", "play it", "audio version", "narrate this", "make me something I can listen to", or building a voiced UI/dashboard.
## How to use
1. **Pick the voice.** Default = **Sarah** (`EXAVITQu4vr4xnSDxMaL`, soothing female). Other ready options in `config.json` → `voice_options`: Lily (velvety British), Matilda, Clara, Bella. The user can name any; pass it via the spec `"voice"` field or `--voice`.
2. **Write a spec JSON** describing the content, then run the engine:
```bash
python3 ~/.claude/skills/elevenlabs-narrator/narrate.py /path/to/spec.json
```
Spec shape:
```json
{
"title": "The Headline",
"subtitle": "optional sub-line (HTML allowed)",
"badge": "small uppercase tag",
"out": "/Users/russellshomeimac2021/Desktop/something.html",
"voice": "Sarah",
"stats": [{"b":"~$456K","s":"Monthly rev"}],
"footer": "sources / credits (HTML allowed)",
"chapters": [
{"n":"01","t":"Chapter Title","speak":"Exactly what the voice says.","html":"<p>On-screen content. <ul class='facts'><li>bullet</li></ul></p>"}
]
}
```
- `speak` = the narration text (write it conversationally; spell out numbers like "four hundred fifty thousand" for natural delivery).
- `html` = what's shown on the card (supports `ul.facts`, `.tag`, `.verdict/.opt` styles already in the template).
- One chapter = a single clip. Many chapters = a chaptered briefing.
3. **Quick one-off** (no spec file):
```bash
python3 ~/.claude/skills/elevenlabs-narrator/narrate.py --text "Hello, here is your update." --out ~/Desktop/clip.html --title "Update" --voice Sarah
```
4. **Open it** for the user with `open <path>` and offer the file.
## Add a "Listen to this page" bar to an EXISTING page
For pages you've already built (e.g. the One Hour Sites site), don't rebuild them — inject a compact play bar at the top with `add_play_bar.py`:
```bash
python3 ~/.claude/skills/elevenlabs-narrator/add_play_bar.py /path/page.html --text-file narration.txt --voice Sarah --title "Listen to this page"
```
- Generates ElevenLabs audio, embeds it, injects the bar after `</nav>` (or after `<body>`), CSS + JS inline. Idempotent (re-running replaces the old bar).
- Write the narration conversationally: "what's on this page, why choose one option over another, and what the outcome should be." Spell out numbers for natural delivery.
- **Standing rule for the One Hour Sites site (`~/Desktop/OneHourSites/`): every new page gets this play bar at the top.**
## Notes
- Output HTML is fully self-contained (audio inlined) — save finished deliverables to `~/Desktop`.
- Credits: ~1 ElevenLabs credit per character of `speak`. Check remaining with:
`curl -s -H "xi-api-key: $(python3 -c "import json;print(json.load(open('$HOME/.claude/skills/elevenlabs-narrator/config.json'))['api_key'])")" https://api.elevenlabs.io/v1/user/subscription`
- To change the default voice permanently, edit `default_voice_id` in `config.json`.
- List all account voices: `GET https://api.elevenlabs.io/v1/voices` with the `xi-api-key` header.
- The API key lives in `config.json` (local, gitignored-by-convention). It is the user's key, provided for this purpose.
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.