Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
clink-standalone
A Python script that lets Claude execute external AI CLI tools (Gemini, Codex, Claude Code) directly without needing an MCP server. It provides role-based prompts, file reference support, and configurable timeouts for delegating tasks to specialized tools.
mcp-tools-as-code
Converts MCP server tools into typed TypeScript APIs to reduce token usage by transforming tool calls into programmatic code execution. Enables native control flow, data filtering before model exposure, and workspace persistence across agent executions.
prompt-engineering
This skill provides structured guidance for creating effective LLM prompts across various techniques like chain-of-thought and few-shot learning. It covers practical scenarios from simple queries to complex pipelines, with clear examples and model-specific considerations for Claude and other AI systems.
delta-derivation
This skill extracts differences between Claude.ai conversation exports by comparing IDs and node states. It identifies new conversations and detects changes in existing ones using bisimulation verification. The tool provides shell scripts and Clojure code for delta analysis with integration into a Justfile workflow.
biddeed-2025-complete-analysis
This skill generates detailed year-end reports by aggregating data from conversations, GitHub repos, Supabase databases, and personal tracking systems. It produces both markdown documents and interactive HTML dashboards with charts, focusing on business metrics, technical deployments, swimming performance, and family life management.
framework
This skill provides expert knowledge of the SpecWeave framework, a spec-driven development system for AI coding assistants. It covers increment-based workflows, mandatory file structures, naming conventions, and lifecycle management to ensure disciplined, documentation-first development.
code-reviewer
An elite AI-powered code review expert that analyzes code for security vulnerabilities, performance issues, and best practices using modern static analysis tools and AI techniques to ensure quality, security, and maintainability.
agentdb-memory-patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
ccxt-php
CCXT cryptocurrency exchange library for PHP developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in PHP 8.1+. Use when working with crypto exchanges in PHP projects, trading bots, or web applications. Supports both sync and async (ReactPHP) usage.
airflow-dag-patterns
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.
langfuse
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
firebase
Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I
rag-engineer
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.
computer-use-agents
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.
system-design
Design systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries.
reconciliation
Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
anthropic
Anthropic Claude API integration — chat completions, streaming, vision, tool use, and batch processing via the Anthropic Messages API. Generate text with Claude Opus, Sonnet, and Haiku models, process images, use tool calling, and manage conversations. Built for AI agents — Python stdlib only, zero dependencies. Use for AI text generation, multimodal analysis, tool-augmented AI, batch processing, and Claude model interaction.
web-learner
自主上网学习技能 - 让 AI 能够主动搜索、浏览和从互联网获取知识。当用户要求了解最新信息、学习新知识、查询新闻、获取某个主题的详细信息，或需要从网络上获取数据时触发此技能。
afrexai-data-governance
Imported from https://github.com/openclaw/skills.
youtube-analytics
YouTube Data API v3 analytics toolkit. Analyze YouTube channels, videos, and search results. Use when the user asks to: check YouTube channel stats, analyze video performance, compare channels, search for videos, get subscriber counts, view engagement metrics, find trending videos, get channel uploads, or analyze YouTube competition. Requires a YouTube Data API v3 key from Google Cloud Console.
financial-intel
Stock momentum scanner and portfolio intelligence. Look up any ticker for momentum scores, RSI, coil breakout patterns, and AI analysis. Scan top signals across 6,500+ stocks and crypto. Track portfolio holdings with real-time alerts. Market pulse, sector trends, win/loss proof data, and risk assessment — all through natural conversation. Powered by 730 days of backtested data with an 80% 5-day win rate.
openclaw-expert
Expert skill for OpenClaw (formerly Clawdbot/MoltBot) — the self-hosted AI agent framework. ALWAYS use when user mentions OpenClaw, Clawdbot, MoltBot, openclaw.json, openclaw gateway, openclaw channels, openclaw nodes, openclaw models, openclaw skills, openclaw doctor, AGENTS.md, SOUL.md, USER.md, HEARTBEAT.md, MEMORY.md, IDENTITY.md, TOOLS.md, BOOTSTRAP.md, ClawHub, clawhub, openclaw workspace, openclaw config, openclaw sessions, openclaw pairing, openclaw docker, openclaw sandbox, openclaw heartbeat, openclaw compaction, memorySearch, multi-agent, bindings, dmPolicy. Covers installation, configuration, troubleshooting, security hardening, channel setup, skill development, memory tuning, Docker deployment. Also trigger for "my bot", "my agent", "Lobster", or agent issues after config changes.