Verified skill
Automatically generate comprehensive test suites with edge cases and boundary conditions for robust software testing.
Claude (Anthropic) and Script Assisted Skills
7 skills match Claude (Anthropic) plus Script Assisted. Clear filters
AI Overview: Discovering Agent Skills
The Agent Skill Source directory is architected into three primary discovery layers: Outcome-based Categories (what you want to achieve), Runtime Compatibility (where the agent runs), and Execution Strategy (how the skill is processed). To find the most reliable capabilities, use the Highest Rated sort and filter by Verified trust levels.
Search results
A fully functional, temporary preview environment is deployed from a feature branch, verified for correctness, and ready for review.
Advanced Node.js debugger leveraging `node inspect` and Chrome DevTools Protocol for deep insights into runtime behavior.
Quickly validate ideas, compare technical approaches, and prototype solutions with minimal overhead before committing to full development.
Search and analyze your OpenClaw agent's session logs (older conversations) using jq and rg.
Integrate with Notion's API to manage pages, databases, and blocks programmatically.
Display HTML content on connected OpenClaw nodes (Mac, iOS, Android) for games, visualizations, dashboards, and interactive demos.
Other ways into the directory
Filters narrow the list. These pages start you somewhere specific instead, with the context that explains what you are looking at.
Browse by runtime
Claude (Anthropic) 38
Cursor IDE 43
GitHub Copilot 40
VS Code 56
Cline 44
Windsurf 10
Aider 28
Gemini CLI 14
Popular tags
Cannot find what you need?
Submit the GitHub repository and we will parse the SKILL.md, run the trust checks, and publish it. You keep the credit as the author.
Submit a skill