BenchClaw is a Codex/OpenCode skill workflow for benchmark construction, evaluation, and maintenance. It standardizes the full pipeline—from idea drafting and data generation to evaluation, reporting, failure diagnosis, and skill refinement—so agents can build reproducible, auditable benchmarks with clear quality gates, lineage, and rollback.
npx add-skill EurecaMoment/BenchClawBenchClaw is a Codex/OpenCode skill workflow for benchmark construction, evaluation, and maintenance. It standardizes the full pipeline—from idea drafting and data generation to evaluation, reporting, failure diagnosis, and skill refinement—so agents can build reproducible, auditable benchmarks with clear quality gates, lineage, and rollback.
Claude Code skill for Figma — extract CSS, export images, and inspect design files.
This is a public repo for a Claude skill I've built and want to share with the community.
Explore AI agent patterns, design principles, and infrastructure to build and deploy practical, user-friendly intelligent agents.
Reusable AI agent skills for idea validation, startup research, and workspace memory. Install with npx skills add.
Claude Code skill for building and maintaining technical product documentation in Notion
122 AI Agent Skills for full-lifecycle product development (PM × UI × Backend) | 覆盖产品全生命周期的122个AI Agent技能，从探索发现到增长运营，横跨产品×设计×后端三大领域