Discover AI Agent Skills

Guides seeding deterministic Fusion Framework module state in tests — mockFramework, mockAppModules, and module-owned enableXMock helpers (msal, service-discovery, context, bookmark, feature-flag, analytics, telemetry, http, app) — while keeping each module's real configurator, provider, validation, and lifecycle. USE FOR: signing in a mock user, seeding context/bookmarks/feature-flags, faking HTTP/OpenAPI responses, choosing a mock boundary, adding a mock for a custom module. DO NOT USE FOR: configuring vitest.config.ts, rendering React components/hooks, or Vitest Browser Mode setup (use fusion-framework-testing); dev-server-time API mocking/proxying in dev-server.config.ts (use fusion-developer-app); backend/service-repo mocking.

Full Sentry SDK setup for Svelte and SvelteKit. Use when asked to "add Sentry to Svelte", "add Sentry to SvelteKit", "install @sentry/sveltekit", or configure error monitoring, tracing, session replay, or logging for Svelte or SvelteKit applications.

Guides for writing and editing Remotion documentation. Use when adding docs pages, editing MDX files in packages/docs, or writing documentation content.

Pinterest's UI design system. Use when building interfaces inspired by Pinterest's aesthetic - light mode, Inter font, 4px grid.

MaxMind GeoIP2 integration. Manage data, records, and automate workflows. Use when the user wants to interact with MaxMind GeoIP2 data.

Anthropic's Contextual Retrieval technique in depth. Prepend LLM-generated chunk-specific context (Claude Haiku) to each chunk before indexing. Combines contextual BM25 + contextual embeddings + reranking for up to 67% retrieval failure reduction. Full production pipeline with prompt caching (90% cost cut), batch processing, and eval numbers. USE WHEN: user mentions "contextual retrieval", "contextual embeddings", "Anthropic contextual retrieval", "chunk context", "contextual BM25", "49% retrieval improvement" DO NOT USE FOR: generic chunking - use `chunking-strategies`; hybrid search fundamentals - use `hybrid-search`; reranking on its own - use `reranking`

Official Framer Motion skill for animation variants — state machines, orchestrated animations, stagger, repeat, sequencing. Use when building orchestrated animations, animation state machines, staggered entrances, or when asking about Framer Motion variants, transition variants, or choreographed animations.

Use when producing in-game art with Layer: characters, heroes, NPCs, enemies and mascots, environment and background concept art, parallax layers, or game UI such as icons, buttons, frames, panels, HUD elements and currency symbols. Also when a cast must stay on-model across many images, when an icon must read at 64px, or when a character must be split into parts for a skeletal rig. Keywords: character art, NPC, enemy, concept art, background, parallax, game UI, HUD, icon set, Spine, rigging.

Perform a detailed SWOT analysis — strengths, weaknesses, opportunities, and threats with actionable recommendations. Use when doing strategic assessment, competitive analysis, or evaluating a product or business position.

Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.

Work with Obsidian vaults using the official obsidian CLI: read/search/create/edit notes, tasks, links, properties, plugins.

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

BluOS CLI (blu) for discovery, playback, grouping, and volume.

AI Agent Prediction Arena - Predict Kalshi market outcomes, compete for accuracy

Aggregates and analyzes market sentiment for specific crypto or stock tickers by scanning news and social signals. Useful for quick vibe checks before trading.

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read the bundled docs and cookbooks to find useful patterns and discover new combinations.

Use this skill when you need evidence-bounded authentication-testing analysis and validation preparation; triggers include 身份认证测试 and authentication-testing.

Plan and execute upgrades for Python libraries, handling breaking changes. Use when performing major version bumps for frameworks like Django or FastAPI.