find-skills不知道装什么技能?想让 AI 自己找到最合适的技能?技能发现·Find Skills 是场景驱动+关键词双模式的技能发现工具(skill discovery / skill finder / install skills):用自然语言描述场景/需求(如"我想做一个海报""帮我分析股票""找个薅羊毛技能"),或明确说"安装技能/find skills/找个skill/有没有做XX的技能"时,自动从官方内置、本地已安装、SkillHub、虾评、GitHub、ClawHub 六层联合搜索并推荐最合适的技能,支持一键安装。已完全替代官方原 find-skills 插件。触发词:找技能、安装技能、技能推荐、技能发现、find skills、skill discovery、install skill。
Install via ClawdBot CLI:
clawdbot install JimLiuxinghai/find-skillsGrade Excellent — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://skills.sh/Audited Apr 16, 2026 · audit v1.0
Generated Feb 24, 2026
A web development team wants to improve the speed and efficiency of their React application. They ask the agent for guidance, and the find-skills skill searches for React performance skills, recommending a skill like vercel-react-best-practices that provides optimization guidelines from Vercel Engineering.
A software engineering manager seeks to streamline code review processes by automating PR checks. The agent uses the find-skills skill to search for PR review skills, finding tools that offer automated feedback and best practices for code quality.
A startup developing an API needs to create comprehensive documentation quickly. They inquire about skills for generating API docs, and the find-skills skill identifies relevant documentation skills that automate doc creation from code comments.
A design agency wants to ensure their web projects meet accessibility standards. They ask for help with accessibility tools, and the find-skills skill searches for design skills focused on UI/UX accessibility, recommending skills that provide guidelines and checks.
Offer basic skills for free to attract users, with premium or advanced skills available for a subscription fee. This model encourages adoption while generating revenue from power users and enterprises seeking specialized capabilities.
Provide customized skill packages and support for large organizations, including integration with internal tools and dedicated updates. This model targets businesses needing scalable, secure solutions for team-wide agent enhancements.
Partner with tool providers (e.g., Vercel, GitHub) to promote their skills, earning commissions on installations or referrals. This model leverages ecosystem growth by aligning with popular platforms and services.
💬 Integration Tip
Use specific keywords from user queries to run npx skills find commands effectively, and always present install commands with clear links to skills.sh for further details.
Scored Apr 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...