Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/Consensys/c0 --skill run-agent-eval명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Run and improve the c0 agent evaluation loop using the local and remote Cloudflare MCP harness, versioned history notes, and current Cloudflare product updates. Use when evaluating agent quality, harness behavior, retrieval quality, model/tool performance, or when the user asks to benchmark, score, improve, or retest the agent workflow.
Derive Cloudflare worker env types from Alchemy resource Env types instead of hand-writing env shapes. Use when editing worker bindings, adding or removing env vars in packages/infra, touching cloudflare-env.d.ts or env.d.ts files, importing from cloudflare:workers, or fixing env typing in API or web apps.
Use when changing c0 deployment configuration, runtime-editable global settings, auth providers, AI providers, MCP Context Forge, discovered registries, secret references, or open-source deployment configuration.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | run-agent-eval |
| description | Run Agent Eval |
| disable-model-invocation | true |
Run the project agent evaluation loop using .cursor/skills/agent-eval-loop/SKILL.md.
.cursor/skills/agent-eval-loop/SKILL.md first.notes/agent-eval-history/ before choosing a new improvement.nub run agent:eval:targets.nub run agent:eval:local and nub run agent:eval:remote as appropriate for the selected target.nub run agent:eval:note:write --input <summary-json> --recap "<short recap>".notes/agent-eval-history/