Total 56,451 skills, AI & Machine Learning has 9391 skills
Showing 12 of 9391 skills
Fact-checks LLM responses by extracting verifiable claims, verifying each via web search, producing an audit report with verdicts, and optionally revising inaccurate responses. Use when the user asks to audit, fact-check, double-check, or verify a response.
Detect and neutralize prompt injection attacks in OpenClaw skill content, user inputs, and external data sources. Prevents instruction hijacking and context manipulation.
Find and evaluate Claude skills for specific use cases using semantic search, Anthropic best practices assessment, and fitness scoring. Use when the user asks to find skills for a particular task (e.g., "find me a skill for pitch decks"), not for generic "show all skills" requests.
Expert GPU optimization for modern consumer GPUs (8-24GB VRAM). Use this skill when you need to optimize GPU training, speed up CUDA code, reduce OOM errors, tune XGBoost for GPU, migrate NumPy to CuPy, make a model faster, manage GPU memory, optimize VRAM usage, or benchmark PyTorch. Covers mixed precision, gradient checkpointing, XGBoost GPU acceleration, CuPy/cuDF migration, vectorization, torch.compile, and diagnostics. NVIDIA GPUs only. PyTorch, XGBoost, and RAPIDS frameworks.
Create new skills, modify and improve existing skills, and measure skill performance. Enhanced version with quick commands. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. Triggers on phrases like "make a skill", "create a new skill", "build a skill for", "improve this skill", "optimize my skill", "test my skill", "turn this into a skill", "skill description optimization", or "help me create a skill".
Delegate complex coding tasks to OpenCode agent. Use when building new features, reviewing code, or refactoring large codebases. Allows starting, resuming, and monitoring opencode sessions.
This skill is used when the user requests 'review my prompt', 'analyze my conversation history', 'diagnose my understanding level', or when it is invoked via /prompt-review. It reads past AI Agent conversation histories (Claude Code, GitHub Copilot Chat, Cline, Roo Code, Windsurf, Antigravity), estimates the user's technical understanding level, prompting patterns and AI dependency, then generates a corresponding report.
Event attribution and explanation. Use this skill whenever the user asks for the reason behind a price move. Trigger phrases include: why did X crash, what just happened, why is it pumping, what caused. MCP tools: news_events_get_latest_events, info_marketsnapshot_get_market_snapshot, news_events_get_event_detail, info_onchain_get_token_onchain, news_feed_search_news.
Japanese version of the PUA Universal Motivation Engine. It compels exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology in Japanese. MUST trigger under the following conditions: (1) Any task has failed 2+ times, or you're stuck in a loop of tweaking the same approach; (2) You're about to say 'I cannot', suggest manual handling to the user, or blame the environment without verification; (3) You find yourself being passive — not searching, not reading source code, not verifying, just waiting for instructions; (4) The user expresses frustration in any form: 'try harder', 'stop giving up', 'figure it out', 'why isn't this working', 'again???', 'もっと頑張れ', 'なんでまた失敗したの', 'もう一回やって', 'なんとかしろ', or any similar sentiment regardless of phrasing. It should also trigger when facing complex multi-step debugging, environment issues, configuration problems, or deployment failures where early surrender is tempting. Applies to ALL task types: code, configuration, research, writing, deployment, infrastructure, API integration. DO NOT trigger on first-attempt failures or when a known fix is already executing successfully.
Hand off a task to GitHub Copilot.
Transcribe audio to text using Sarvam AI's Saaras model. Handles speech recognition, transcription, and voice interfaces for 23 Indian languages. Supports 5 output modes, auto language detection, WebSocket streaming, and batch diarization. Use when converting speech to text or building voice-enabled apps.
Create or edit Claude Code skills with expert guidance on structure and best practices