Loading...
Loading...
Found 2,026 Skills
Guide for creating effective opencode skills. Use for creating or updating skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Examples: - user: "Create a skill for git workflows" → define SKILL.md with instructions and examples - user: "Add examples to my skill" → follow the user: "query" → action pattern - user: "Update skill description" → use literal block scalar and trigger contexts - user: "Structure a complex skill" → organize with scripts/ and references/ directories - user: "Validate my skill" → check structure, frontmatter, and discovery triggers
Performance optimization and continuous improvement for sobriety.tools recovery app. Use for load time optimization, offline capability, crisis detection, performance monitoring, automated issue detection. Activate on "sobriety.tools", "recovery app perf", "crisis detection", "offline meetings", "HALT check-in", "sponsor contacts". NOT for general Next.js help, unrelated Cloudflare Workers, or non-recovery apps.
Build RAG pipelines with Exa.ai for real-time web retrieval. Use when building retrieval-augmented generation, integrating Exa with LangChain, LlamaIndex, Vercel AI SDK, or implementing AI agents with web search capabilities. Triggers on: RAG pipeline, retrieval augmented generation, Exa LangChain, Exa LlamaIndex, ExaSearchRetriever, ExaSearchResults, Exa MCP, Exa tool calling, Claude tool use, AI agent web search, grounded generation, citation generation, fact checking, hallucination detection, OpenAI compatibility, chat completions.
Use when defining SLIs/SLOs, managing error budgets, or building reliable systems at scale. Invoke for incident management, chaos engineering, toil reduction, capacity planning.
Official Anthropic SDK for Claude AI with chat, streaming, function calling, and vision capabilities
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
AI-powered crypto trading agent via natural language. Use when the user wants to trade crypto (buy/sell/swap tokens), check portfolio balances, view token prices, transfer crypto, manage NFTs, use leverage, bet on Polymarket, deploy tokens, set up automated trading strategies, submit raw transactions, execute calldata, or send transaction JSON. Supports Base, Ethereum, Polygon, Solana, and Unichain. Comprehensive capabilities include trading, portfolio management, market research, NFT operations, prediction markets, leverage trading, DeFi operations, automation, and arbitrary transaction submission.
[Project Management] Capture ideas, manage product backlogs, apply prioritization frameworks (RICE, MoSCoW), and facilitate stakeholder communication. Triggers: product owner, backlog management, user story prioritization, product roadmap, product backlog.
Create and scaffold new skills with proper frontmatter, directory structure, and validation. Use when the user asks to build a new capability, integrate a new API, or extend the system with a repeatable workflow.
Write and maintain an implementation diary capturing what changed, why, what worked, what failed (with exact errors and commands), what was tricky, and how to review and validate. Activates proactively during non-trivial implementation work (new features, bug fixes, refactors, research spikes). Does not activate for trivial tasks like one-line fixes, config tweaks, or quick questions.
Download YouTube video transcripts (subtitles/captions) using yt-dlp. Use this skill whenever the user provides a YouTube URL and wants the transcript, asks to "download transcript", "get captions/subtitles", or "transcribe a YouTube video". Also triggers when user needs text content extracted from any YouTube video, even if they don't explicitly say "transcript" (e.g., "what does this video say", "get me the text from this video", "I need the content of this YouTube link").
Run a single Terminal-Bench problem through Paperclip in a bounded, human-in-the-loop improvement cycle until the smoke passes, the board rejects the next fix, the iteration budget is exhausted, or a real blocker is named. Each iteration runs a bounded smoke against an isolated Paperclip App worktree, captures artifacts, diagnoses the exact stop point with `/diagnose-why-work-stopped`, requests board confirmation before any product fix, then reruns against the same worktree. Use whenever an issue asks to "run Terminal-Bench in a loop", "drive Terminal-Bench until it passes", "loop fix-git through Paperclip", or otherwise points at a Terminal-Bench task and asks for bounded iteration with diagnosis.