Loading...
Loading...
Found 3,316 Skills
Drop-in inspector panel for any json-render app. Use when the user wants to debug a generative UI, inspect the spec tree, edit state at runtime, see dispatched actions, follow stream patches live, browse a catalog, or pick DOM elements to find their spec keys. Triggers include "add devtools", "debug json-render", "inspect the spec", "why is this element not rendering", "see the state at runtime", or requests to tap streams / capture action logs for `@json-render/devtools`.
Generate opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, paid newsletters, opinion essays, reported features, technical deep-dives. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including making a flat intro punchier or rewriting a draft opening. Also trigger when user asks for a post title, titre d'article, headline, or when ghostwriting skills reach the opening or titling step. Proposes 3-4 hooks pulling distinct psychological levers (curiosity gap, contrarian, scene, promise, authority), 2 candidates each, waits for the user to pick. Do NOT trigger for social posts (LinkedIn feed, Twitter/X, TikTok, Bluesky, Threads), READMEs or doc first lines, taglines, email subjects or openers, ad copy (Google/Meta Ads), landing-page headlines, press releases, SEO meta, fiction openings, talk/podcast/video script intros, or body rewrites.
AI Radar Skill — Zero-API, Zero-Key, Zero-Server Chinese AI News Query. Data comes from public static JSON files hosted on GitHub Pages by AI News Radar (automatically updated daily via GitHub Actions). You can retrieve data with curl, no authentication, no UA requirements, no rate limits, and you can fork the entire data pipeline to create your own version. This Skill should be triggered when users ask any Chinese AI news-related questions such as "What's happening in the AI circle today?", "AI news in the past 24 hours", "AI daily briefing", "Any recent large model releases?", "AI product updates", "What's new in Agent tools?", "What have OpenAI/Anthropic/Google released recently?", "Hot topics in the AI circle", "Check AI Radar", "Which AI news sources are worth following?", etc. Even if users only say "AI circle", "AI news", or "What's new today", as long as the context is in the AI / large model / Agent / developer tools domain, this Skill should be triggered. **Do NOT undertrigger** — if users ask for AI news and you don't invoke this Skill, you're treating outdated training data as today's news, which is harmful to users. Do NOT use this Skill for maintaining the AI News Radar repository itself (adding news sources, modifying crawling logic, deploying Pages — use Bole Skill / ai-news-radar for that); do NOT use it for non-AI general news queries; do NOT use it for private information sources that require login status.
Pre-flight before creating a pull request: run `greptile review` on the committed branch, VERIFY the review actually matches this branch's diff, triage its findings, apply safe fixes (propose risky ones), and only then `gh pr create`. Runs in repos where greptile is configured. Trigger ONLY on explicit PR-creation intent: "crea el PR", "create the PR", "abrí el PR", "open a PR", or immediately before a `gh pr create`. Do NOT fire on a bare commit.
Use when React Context patterns for state management. Use when sharing state across component trees without prop drilling.
Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.
ANIMA as limit construction over condensed skill applications. Formalizes prediction markets as belief ANIMAs, structure dishes as condensation media, and impact as equivalence class change. Use for understanding agency at maximum entropy, compositional world modeling, or applying Scholze-Clausen condensed mathematics to AI.
Design software architectures with appropriate patterns for scale, maintainability, and team structure. Covers layered, hexagonal, event-driven, CQRS, and modular monolith architectures. Produces architecture decision records, component diagrams, and dependency maps. Prevents over-engineering, premature distribution, and architectural drift.
Expert in absurdist, unhinged, and deliberately weird brand voices that work. Covers the Duolingo owl energy, chaotic social media presence, and knowing exactly how far to push. Understands why weird works and when it catastrophically fails. Use when "absurdist, unhinged, duolingo, weird brand, chaotic energy, off the rails, brand character, " mentioned.
Provides usage guidance for Instructure UI (InstUI) React components. Use when working with @instructure/ui packages, when asked how to use InstUI components, which component to choose, or how to apply props, guidelines, theming, or accessibility rules. Covers AiInformation, Alert, AppNav, Avatar, Badge, Billboard, Breadcrumb, Button, Byline, Calendar, Checkbox, CheckboxGroup, CloseButton, ColorContrast, ColorIndicator, ColorMixer, ColorPicker, ColorPreset, CondensedButton, ContextView, DataPermissionLevels, DateInput, DateInput2, DateTimeInput, DrawerLayout, Drilldown, Editable, FileDrop, Flex, FormField, FormFieldGroup, Grid, Heading, IconButton, Img, InlineList, InPlaceEdit, InstUISettingsProvider, Link, List, Menu, Metric, MetricGroup, Modal, NutritionFacts, NumberInput, Overlay, Pages, Pagination, Pill, Popover, ProgressBar, ProgressCircle, RadioInput, RadioInputGroup, RangeInput, Rating, Responsive, Select, SideNavBar, SimpleSelect, SourceCodeEditor, Spinner, Table, Tabs, Tag, Text, TextArea, TextInput, TimeSelect, ToggleButton, ToggleDetails, ToggleGroup, Tooltip, TopNavBar, Tray, TreeBrowser, TruncateText, View.
Build AI-powered chat applications with TanStack AI and React. Use when working with @tanstack/ai, @tanstack/ai-react, @tanstack/ai-client, or any TanStack AI packages. Covers useChat hook, streaming, tools (server/client/hybrid), tool approval, structured outputs, multimodal content, adapters (OpenAI, Anthropic, Gemini, Ollama, Grok), agentic cycles, devtools, and type safety patterns. Triggers on AI chat UI, function calling, LLM integration, or streaming response tasks using TanStack AI.
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.