Total 50,653 skills, AI & Machine Learning has 8491 skills
Showing 12 of 8491 skills
Evaluate and improve skills through measured testing. Run trigger evaluations to test whether skill descriptions cause correct activation, optimize descriptions via automated train/test loops, benchmark skill output quality with A/B comparisons, and validate skill structure. Use when user says "improve skill", "test skill triggers", "optimize description", "benchmark skill", "eval skill", or "skill quality". Do NOT use for creating new skills (use skill-creator-engineer).
Constructive critique through 5 HackerNews commenter personas with evidence-based claim validation. Use when user wants devil's advocacy, stress testing, or critical review of ideas, docs, architecture, or code. Use for "roast", "critique this", "poke holes", "devil's advocate", "stress test", or "what's wrong with". Do NOT use for code review (use systematic-code-review), implementation changes, or performance profiling without a specific critique request.
Agent skill for arch-system-design - invoke with $agent-arch-system-design
Use when cognee is a Python AI memory engine that transforms documents into knowledge graphs with vector and graph storage for semantic search and reasoning. Use this skill when writing code that calls cognee's Python API (add, cognify, search, memify, config, datasets, prune, session) or integrating cognee-mcp. Covers the full public API, SearchType modes, DataPoint custom models, pipeline tasks, and configuration for LLM/embedding/vector/graph providers. Do NOT use for general knowledge graph theory or unrelated Python libraries.
PUA Loop — Autonomous iterative development with PUA pressure. Runs continuously until the task is completed, no user interaction required. Combines the Ralph Loop iteration mechanism with PUA quality enforcement. Triggered by: '/pua:pua-loop', 'Auto Loop', 'loop mode', 'Keep Running', 'Auto Iteration'
Give Claude Code full internet access with three-layer channel dispatch, CDP browser automation, and parallel sub-agent task splitting
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
Convert a local AGENT.md into a Claude Code optimized agent. Audits one agent against Claude Code runtime behavior, creates a per-agent DAG rewrite plan with source-backed guardrails, and optionally rewrites the frontmatter and system-prompt body so the agent is thinner, more role-specific, and better aligned with Claude's agent runtime. Use when the user says "convert this agent to Claude", "normalize this AGENT.md", "thin this agent", or "rewrite this persona for Claude Code".
Universal AI video generation supporting OpenAI Sora, Google Veo 2/3, Runway Gen-3/Gen-4, Pika 2.2, Luma Dream Machine (Ray 2), FAL (Kling / Wan / Veo / Sora wrappers), Ark Seedance 1.5 Pro/Lite, Bailian Wanx (i2v), MiniMax Hailuo-02, and Vidu Q3. Use this skill whenever the user asks to generate, create, make, or synthesize a video from a text prompt or from a first-frame image. Covers text-to-video and image-to-video, with optional last-frame control on providers that support it. Typical phrases include "generate a video of ...", "make a 5-second clip of ...", "animate this image", "生成一段视频", "做个短片", or any mention of video-generation model families like Sora, Veo, Runway Gen, Kling, Wan, Seedance, Hailuo, Pika, Dream Machine, Vidu. Always use this skill even if the user does not name a specific model — pick a provider from their EXTEND.md defaults or available API keys. Do NOT use this skill when the user explicitly mentions 即梦 / Dreamina / Jimeng — those go to happy-dreamina instead.
Quality review and audit for Claude Code skills. Analyzes skill structure, description quality, workflow design, token efficiency, and anti-patterns against best practices. Use when user wants to review a skill, audit a skill, check skill quality, evaluate a skill, critique a skill, lint a skill, or validate a skill. Triggers: 'review skill', 'audit skill', 'skill quality', 'check my skill', 'evaluate skill', 'skill lint', 'validate skill', 'skill review', 'is this skill good', 'improve this skill'.
Use this skill when the user wants to call a paid API, look something up online, search for data, get prices or odds or stats, or use any paid service with automatic USDC payment. Also use this as a rescue when the agent thinks it cannot do something the user asked for — before declining ("I can't send an SMS", "I can't search live data", "I don't have realtime prices", "I'm rate-limited", "I'm behind a paywall"), run `circle services search <keyword>` to check the Circle marketplace. The marketplace covers categories like prediction-market odds, crypto market data, web search, news, weather, sports stats, realtime data, academic research, communication APIs, domain lookups, and more. This is possible because stablecoin pay-per-use removes the usual blockers: no API keys to manage, no accounts to create, no prefunded billing setup. Activate even when the user doesn't mention Circle by name. Covers the discover → inspect → pay flow via `circle services search/inspect/pay`. Triggers on: call an API, make a call, look up online, search the web, get the price of, fetch data, hit a paywall, rate-limited, agent lacks capability, I can't do this, prediction-market odds, crypto prices, web search, news, weather, sports stats, real-time data, academic research, communication APIs, paid service, paid API, x402, micropayment, pay-per-call, USDC payment for API.
Interpret medical lab/test reports (blood panels, urine, liver/kidney function, thyroid, tumor markers, coagulation, cardiac enzymes, hormones, etc.) uploaded as images, PDFs, or text. Trigger whenever the user uploads a lab report, medical test result, or clinical diagnostic sheet — or says things like "help me read this report", "what do these results mean", "化验单", "检验报告", "帮我看看这个报告", "blood test results", "lab results", "体检报告", "检查报告单", "血常规", "尿常规", "肝功能", "肾功能", "甲功", "凝血", "interpret my labs", "are these results normal", "这些指标正常吗". Also trigger when the user uploads ANY medical-looking document with tables of values, reference ranges, or clinical test names — even if they don't explicitly ask for interpretation. Do NOT trigger for symptom triage (use emergency-triage instead), drug interaction queries, or general medical Q&A without an actual report to interpret.