Use when the user asks to "set up types without a build step", "use vanilla JS with types", "configure erasable syntax", or mentions "JSDoc type checking". It provides instructions for modern type safety using JSDoc in browsers and native TypeScript execution in Node.js.
Specialized knowledge for writing modern high-quality CSS. Trigger this skill when starting a new CSS project/file, when the user asks about new CSS features (e.g. Masonry, View Transitions, Container Queries, Scroll-driven animations), or requests refactoring of legacy styles to modern standards.
Use when drafting documents, reports, posts, presentations, or review comments from source materials, or conducting research across provided documents. Enforces read-first drafting, a source map for every claim, agent verification, and separation of verified from unverified claims.
Add a new named theme pack to the dotfiles theme system (bin/theme). Use when the user pastes an omarchy/omacosy-style theme repo URL, says "add this theme", "new theme pack", or wants another entry for theme next to cycle.
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
Diagnose, verify, monitor, and safely operate pixiv-cli GitHub Actions runs and local CI gates, including PR Quality gate, workflow policy, platform smoke, native/browser evidence, release handoffs, and approved reruns. Use when checks fail or hang, a PR needs readiness verification, a workflow run needs root-cause…
Review pixiv-cli worktree, commit range, or GitHub pull request for architectural boundaries, public CLI/MCP/SDK contracts, security, documentation obligations, tests, and workflow policy. Use for code review, PR review, pre-release review, or review of agent/workflow changes.
Operate Pixiv through the pixiv-cli binary — search illustrations, novels, and users; reverse-search images with SauceNAO or ascii2d; inspect Pixiv artwork or user IDs/URLs; view rankings and recommendations; manage bookmarks/follows; and download works. Load only when the user explicitly mentions Pixiv or pixiv-cli…
Use when the user wants to search cloud GPUs across providers, provision a GPU pod, install AI frameworks (ComfyUI, SwarmUI, vLLM, Ollama, Open WebUI, Axolotl, H2O LLM Studio), pull models from HuggingFace / Civitai / URLs to a unified store, sync workspaces to S3, manage idle-pod lifecycle, or track GPU spend — all…
Run a WCAG accessibility audit on a web page. Checks heading hierarchy, landmark regions, colour contrast, ARIA attributes, keyboard navigation, target size and the WCAG 2.2 additions. Use when the user wants to check, test, or audit accessibility (a11y) on a URL or the current page.
Review code changes, pull requests, or merge requests for bugs, code quality, security, and maintainability. Use when asked to review a PR, MR, diff, or set of changes. Also handles GitHub PRs and GitLab MRs.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Create, improve, optimize, and port games for the Sega 32X (Sega Mars) using Chilly Willy's 32XDK toolchain and the DOOM 32X Resurrection (d32xr) codebase as reference. Use whenever the user wants to port a game (DOS, Genesis, PICO-8, HTML5, or any platform) to the 32X, build or debug a homebrew 32X ROM, or make a 32X…
Pre-ship quality gate for AI agents and automations. Use when the user mentions: pre-ship, checklist, ship check, ready to ship, ready to publish, launch checklist, release checklist, pre-publish, quality gate, go/no-go, agent packaging review, pre-ship check, before release, before publish, packaging audit.
Complete guide to packaging AI agents as Custom GPTs for the ChatGPT GPT Store. Use when the user mentions: Custom GPT, GPT Store, GPT Builder, GPT Actions, GPT packaging, ChatGPT plugin, GPT knowledge files, GPT system instructions, build a GPT, create a GPT, publish GPT, GPT marketplace, GPT distribution, OpenAI…
Complete guide to packaging AI agents as MCP (Model Context Protocol) servers. Use when the user mentions: MCP, Model Context Protocol, MCP server, MCP tool, MCP resource, MCP prompt, claude desktop config, claudedesktopconfig.json, stdio transport, streamable http, mcpb, desktop extension, mcp registry, smithery, mcp…
Detect and rewrite prose that reads as AI-generated: em dashes, AI vocabulary, negative parallelisms, rule-of-three filler, puffery, tone tells. Use for "humanize this", "de-slop", "sounds like ChatGPT", "make this less AI".
Use the spark CLI to access the user's Spark email data - list emails, search by topic, read threads, check calendar events, find availability, look up contacts, and view team info. Use when the user asks about their emails, calendar, contacts, meetings, or scheduling.
Inspect and control the local LLM server(s) via llama-launcher — list profiles, see what's running, switch models, tail logs. Use when the user wants to know what model is loaded, change models, start/stop or restart the server, or troubleshoot a stuck load.