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.
hypothesis-generation
This skill provides a structured workflow for generating scientific hypotheses from observations. It guides users through literature search, evidence synthesis, hypothesis formulation, prediction development, and experimental design. Outputs are formatted as LaTeX documents with visual schematics, following a systematic scientific method approach.
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Council
Multi-agent debate system. USE WHEN council, debate, perspectives, agents discuss. SkillSearch('council') for docs.
substrate-vulnerability-scanner
Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use when auditing Substrate runtimes or FRAME pallets. (project, gitignored)
competitive-ads-extractor
This skill scrapes competitor ads from platforms like Facebook and LinkedIn, analyzes messaging patterns, and provides actionable insights for improving your own campaigns. It saves screenshots, identifies successful creative approaches, and highlights common pain points competitors target.
lark-doc
This skill fetches Lark/Feishu documents and converts them to Markdown format, plus appends structured troubleshooting summaries. It's designed for teams using Lark for documentation who need to access guides and record issue resolutions programmatically.
tech-stack-evaluator
Comprehensive technology stack evaluation and comparison tool with TCO analysis, security assessment, and intelligent recommendations for engineering teams
agent-factory
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
session-reflection-analysis
Analyzes Claude Code session history to identify token waste and inefficiency patterns. Uses jq to create 98% reduced summaries, then spawns subagents to propose concrete improvements like CLAUDE.md updates, new skills, and automation scripts. Prevents reading raw session files directly.
performance-correlation
A comprehensive SEO analysis tool that effectively correlates GA4 and GSC metrics with content attributes to identify performance drivers and optimization opportunities.
clawdhub
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
slack
Use when you need to control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
feishu-doc
Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.
add-uint-support
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture.
biomni
Biomni is an autonomous AI agent framework for biomedical research that executes multi-step tasks across genomics, drug discovery, and clinical analysis. It decomposes complex queries, generates analysis code, retrieves from integrated databases, and produces research reports. The tool handles CRISPR design, single-cell RNA-seq, GWAS interpretation, and multi-omics integration with specific workflow examples.
paid-ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.
cargo-fuzz
cargo-fuzz is the de facto fuzzing tool for Rust projects using Cargo. Use for fuzzing Rust code with libFuzzer backend.
claw-team-builder
Agent Team 规划与配置工具。通过多轮交互澄清需求，自动创建 Agent 配置、工作空间、Bootstrap 文件。 触发场景： - 用户说"创建新 Agent" / "新建 bot" / "配置多个 bot" - 用户说"规划 agent team" / "我需要几个不同的 agent" - 用户说"添加一个 agent" / "帮我建一个新 agent" - 用户提到需要不同场景使用不同的 AI 角色 功能： 1. 需求澄清 - 引导用户描述使用场景和 Agent 定位 2. 配置读取 - 自动读取现有 openclaw.json，分析已有配置 3. 方案设计 - 推荐 Agent 配置方案，检测冲突 4. 自动创建 - 创建目录、文件、更新配置 5. 配置验证 - 确保配置正确可用
json-canvas
This skill enables Claude to create and edit JSON Canvas files used in Obsidian for visual note-taking. It provides detailed specifications for nodes, edges, and layouts, with practical examples for mind maps, flowcharts, and research boards. The documentation covers validation rules and layout guidelines.
threejs-materials
Three.js materials - PBR, basic, phong, shader materials, material properties. Use when styling meshes, working with textures, creating custom shaders, or optimizing material performance.
hono-routing
Build type-safe APIs with Hono for Cloudflare Workers, Deno, Bun, Node.js. Routing, middleware, validation (Zod/Valibot), RPC, streaming (SSE), WebSocket, security (CSRF, secureHeaders). Use when: building Hono APIs, streaming SSE, WebSocket, validation, RPC. Troubleshoot: validation hooks, RPC types, middleware chains, JWT verify algorithm required (v4.11.4+), body consumed errors.
add-malli-schemas
This skill provides specific guidance for adding Malli schemas to Metabase API endpoints. It includes concrete examples, common patterns, and step-by-step instructions for route params, query params, request bodies, and response schemas. The skill references actual code files and established patterns within the Metabase codebase.
skill-developer
A meta-skill for creating and managing other Claude Code skills. Provides detailed guidance on skill structure, trigger patterns, hook mechanisms, and configuration. Includes templates, examples, and troubleshooting steps for implementing skills that auto-activate based on user prompts or file content.