Total 55,011 skills, AI & Machine Learning has 9125 skills
Showing 12 of 9125 skills
Compressed communication using symbols and abbreviations. Use when context is limited or brevity is needed.
Use when creating new skills, editing existing skills, or verifying the validity of skills before deployment
Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what conditions. Achieve better results using your plan mode.
Use when users say "create a skill", "make a new skill", "build a skill", "skill for X", "package this as a skill", or when refactoring/updating/auditing existing skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations.
Build new AI method from scratch using the MTHDS standard (.mthds bundle files). Use when user says "create a pipeline", "build a workflow", "new .mthds file", "make a method", "design a pipe", or wants to create any new method from scratch. Guides the user through a 10-phase construction process.
Configure OpenClaw gateway integration for waking external automations and AI agents on hook events
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or the loop cap is reached. Use when: implementing features from a spec or plan, hardening existing code, fixing a batch of issues, or any multi-file task that benefits from a build-verify-fix cycle.
A skill for performing web searches, research, and reasoning using the Perplexity API. Handles real-time web information retrieval, deep research analysis, and advanced reasoning tasks. Use when the user asks for web searches, research, or says things like "look up", "search for", "latest information", "research", or "analyze".
Core ML, Create ML, Vision framework, Natural Language framework, on-device ML integration. Use when user wants image classification, text analysis, object detection, sound classification, model optimization, or custom model integration. Covers Core ML vs Foundation Models decision.
NEVER escalate without investigation first. This is the Iron Law. Use when evaluating whether to escalate models, facing genuine complexity requiring deeper reasoning, novel patterns with no existing solutions, high-stakes decisions requiring capability investment. Do not use when thrashing without investigation - investigate root cause first. DO NOT use when: time pressure alone - urgency doesn't change task complexity. DO NOT use when: "just to be safe" - assess actual complexity instead.
Claude Code hooks configuration and development. Covers hook lifecycle events, configuration patterns, input/output schemas, and common automation use cases. Use when user mentions hooks, automation, PreToolUse, PostToolUse, SessionStart, SubagentStart, PermissionRequest, WorktreeCreate, WorktreeRemove, TeammateIdle, TaskCompleted, ConfigChange, or needs to enforce consistent behavior in Claude Code workflows.