Browse AI and ML workflow skills for model integration, prompt engineering, evaluations, and LLM automation across major IDEs.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
Run repeatable inference smoke tests using geppetto/pinocchio example binaries (single-pass, streaming, tool-loop, OpenAI Responses thinking) including tmux-driven TUI tests. Use when refactors touch InferenceState/Session/EngineBuilder, tool calling loop, event sinks, provider request formatting, or when you need a quick does inference still work? checklist.
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.
Runs SpatialVortex benchmarks (flux position accuracy, ELP accuracy, sacred boost verification, geometric reasoning, humanities final exam, performance benchmarks), compares to SOTA/baselines (GPT-4, Claude 3, BERT), generates markdown reports/tables with scores (e.g., 95% accuracy, 111.1% improvement, latency), and suggests optimizations. Automatically invoked for run benchmarks, benchmark SpatialVortex, compare flux accuracy, eval geometric reasoning, check ASI progress, submit results. Uses Rust benchmark suite (cargo run --bin run_benchmarks), saves JSON outputs, and prepares for GitHub PR or PapersWithCode upload.
Use the Agent Hive MCP (Model Context Protocol) server for programmatic project management. Use this skill when working with MCP tools to list projects, claim/release projects, update status, add notes, or query dependencies through the MCP interface.
Use when preparing a Formax code handoff: selecting files, generating repomix bundles, and writing a high-quality prompt for WebGPT or another coding agent with clear constraints and validation scope.
Manage git worktrees for parallel AI agent development. Use this when asked to create, list, open, close, or merge worktrees, or when working with wt-* commands.
What Does AI Think About Singapore Restaurants? — A systematic study of LLM restaurant recommendations
Complete feature development workflow orchestrating multiple skills from planning to deployment. Triggers: FD, 新功能, 開發功能, feature, implement, 實作, 實現, 建立功能, create feature, develop, 開發新, add feature, 加功能, 功能開發.
MixSeek Agent Skills collection for AI coding assistants. Provides workspace management, team configuration, evaluation setup, and debugging tools for MixSeek-Core.
Agent for building cycling routes
Frontend UI/UX design intelligence - activate FIRST when user requests beautiful, stunning, gorgeous, or aesthetic interfaces. The primary skill for design decisions before implementation. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check frontend UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.