xohzzwn6kcj9/claude-code-harness-kit
A kit of Claude Code hooks (read-only auto-approve, secret guards, opinionated bash guards) + repo-radar, a read-only repo-analysis skill. Less prompt friction, no less safety.
A kit of Claude Code hooks (read-only auto-approve, secret guards, opinionated bash guards) + repo-radar, a read-only repo-analysis skill. Less prompt friction, no less safety.
npx add-skill xohzzwn6kcj9/claude-code-harness-kitA kit of Claude Code hooks (read-only auto-approve, secret guards, opinionated bash guards) + repo-radar, a read-only repo-analysis skill. Less prompt friction, no less safety.
TODO: Messy Virgo Specific Agents & Skills
AI 招聘助手:不打分,只数命中。三层独立评估(任务/能力/事件)+ HR vs 用人部门双维议事,把'匹配度 85%'变成你和同事真正能讨论的判断。/ Structured hiring skill for AI agents — count hits not scores, three-layer evaluation, dual-perspective council.
OpenClaw Agent Skill — Taiwan professional basketball (PLG + TPBL) data
GREP AI Agent Skills - headless auth, research, and status checking for Claude Code & OpenClaw
A systematic methodology for building full-stack applications - opinionated Claude Code skills covering infrastructure, database, backend, and frontend development
Navigation contract for AI coding agents in large repos. Templates, validation scripts, and a Python CLI for authoring three-layer context packs. Companion to the agent-recall research.