Onnx Webgpu Converter
Convert HuggingFace transformer models to ONNX format for browser inference with Transformers.js and WebGPU. Use when given a HuggingFace model link to convert to ONNX, when setting up optimum-cli for ONNX export, when quantizing models (fp16, q8, q4) for web deployment, when configuring Transformers.js with WebGPU acceleration, or when troubleshooting ONNX conversion errors. Triggers on mentions…
Sam3
Create and work with Meta SAM 3 (facebookresearch/sam3) for open-vocabulary image and video segmentation with text, point, box, and mask prompts. Use when setting up SAM3 environments, requesting Hugging Face checkpoint access, generating inference scripts, integrating SAM3 into Python apps, fine-tuning with sam3/train configs, running SA-Co or custom evaluations, or debugging CUDA/checkpoint/pro…
Vercel Workflow
Build durable workflows with Vercel Workflow DevKit using "use workflow" and "use step" directives. Use for long-running tasks, background jobs, AI agents, webhooks, scheduled tasks, retries, and workflow orchestration. Supports Next.js, Vite, Astro, Express, Fastify, Hono, Nitro, Nuxt, SvelteKit.
Jake Speak
Explain technical work, product or system behavior, repo changes, decisions, findings, and concepts to Jake in plain English. Use when Jake types /jake-speak, says "Jake Speak", "explain this in Jake Speak", "Jake Speak recap", "plain-English version", "for me", "non-technical recap", or asks for the high-level human version of work just done. Preserve real product names, feature names, status, o…
Claude Advisor
Consult Claude Fable as an independent, read-only second-opinion advisor through the local Claude Code CLI. Use this when you judge that another strong engineering perspective could materially improve a hard decision, ambiguous or high-risk reasoning, a tricky debugging session, a design or architecture choice, a code or plan review, a tradeoff analysis, or validating an approach before you commi…
Shot List
Generate professional shot lists from screenplays and scripts. Use when user uploads a screenplay (.fountain, .fdx, .txt, .pdf, .docx) or describes scenes for production planning. Parses scripts to extract scenes, helps determine camera setups, shot types, framing, and movement through collaborative discussion, then generates beautifully formatted PDF shot lists for production. Triggers include r…
Plaud
Install and use Plaud's voice-recording API surfaces — the Plaud CLI (@plaud-ai/cli) for terminal/scripted access and the Plaud MCP server (@plaud-ai/mcp) for conversational access from Claude Code, Claude Desktop, Cursor, Windsurf, Codex, VS Code, Zed, Claude Web, and ChatGPT. Triggers on mentions of Plaud, voice memos, meeting recordings, transcripts, summaries, AI notes, action items from a re…
Docxmakebetter
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Macos Dmg Builder
Build, sign, notarize, and package native macOS apps into distributable DMGs. Use when users ask to ship a SwiftUI/AppKit/Xcode macOS app, set up notarytool credentials (Apple ID app-specific password + team ID), scaffold or run release scripts (`make macos-release`), or debug Developer ID/notarization failures.
Worktree Bootstrap
>-
Update Changelog
Automate changelog management, version bumping, release entries, and explicit prerelease/tag/publish workflows. Sets up a changelog system (CHANGELOG.md, UI modal, version display) if none exists, or updates an existing one. Use when: updating changelog, bumping version, creating release entry, promoting [Unreleased], handling alpha/beta/rc prerelease versions, setting up changelog, adding versio…
Nextjs Pwa
Build Progressive Web Apps with Next.js: service workers, offline support, caching strategies, push notifications, install prompts, and web app manifest. Use when creating PWAs, adding offline capability, configuring service workers, implementing push notifications, handling install prompts, or optimizing PWA performance. Triggers: PWA, progressive web app, service worker, offline, cache strategy…
Prompt Scheduler
Schedule local AI agent terminal prompts to run later from the user's machine. Use whenever the user wants to run a Claude, Codex, Warp agent, or other terminal command at a specific local time, especially when usage limits reset, a laptop must run the job locally, a command must open in Warp, or the prompt needs tags/names for tracking. Creates macOS launchd one-time jobs, Warp .command launcher…
Kain Personality
Invoke, emulate, build with, or steer the Kain Jares / GenAIAlien personality. Use when Jake asks for Kain, GenAIAlien, "kain's voice", "alien mode", "how would Kain feel about this", "make this sound like Kain", Kain-style tweets/posts/replies/captions/dialogue/scripts/product reactions, Kain persona/worldbuilding, or Kain/GenAIAlien image prompts using bundled reference images. Applies to AI/de…
Skill Seekers
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills. Use when creating Claude skills from docs, scraping documentation, packaging websites into skills, or converting repos/PDFs to Claude knowledge.
Nextstep Tours
Build product tours, onboarding flows, and interactive tutorials/lessons in Next.js with NextStep v2 (nextstepjs). Use when adding guided tours, walkthroughs, onboarding overlays, feature callouts, interactive lessons, or gated step-by-step tutorials to a Next.js App Router or Pages Router app. Covers NextStepProvider setup, multi-tour configuration, DOM-anchored and modal steps, multi-page tours…
Codex App Server
Build rich Codex integrations with the Codex App Server across Electron, Swift, Next.js, and other host apps. Use when embedding Codex into a product, adding ChatGPT or API-key login to a desktop or web host, integrating managed or externally supplied ChatGPT tokens, streaming thread/turn/item events, handling approvals, generating version-matched schemas, or deciding between App Server and the C…
Apple Foundation Models
Build Apple Intelligence features with Foundation Models and Image Playground on iOS 26+, iPadOS 26+, macOS 26+, Mac Catalyst 26+, and visionOS 26+. Use when implementing SystemLanguageModel, LanguageModelSession, guided generation with @Generable/@Guide, tool calling, streaming responses, prompt design, safety and guardrail handling, model availability checks, content tagging, context-window lim…
Simplify
Clean up and simplify recently changed code for quality — not bug-hunting. Use whenever the user asks to "simplify", "clean up this code", "tidy up my changes", "refactor for clarity", "polish my diff", "make this cleaner", or wants their recent edits reviewed for reuse, simplification, efficiency, and altitude (right-depth) issues before committing or opening a PR. Reviews the git diff through f…