Audit an OpenClaw agent workspace and generate standardized evaluation reports, scores, and patches. Use when asked to review memory quality, retrieval effic...
集成
Agentic Codex Dev Reviewer
试用Review agentic software-development plans and release readiness for Codex, GitHub, and ClawHub work. Use when a user asks for scoped delivery planning, imple...
它能做什么
Review agentic software-development plans and release readiness for Codex, GitHub, and ClawHub work. Use when a user asks for scoped delivery planning, imple...
技能文档
Agentic Codex Dev
Use this skill as a text-only review layer for agentic development work. It helps turn a request, diff, repository note, or release checklist into a scoped plan and a conservative readiness verdict.
Review Workflow
- Restate the requested outcome and the smallest safe scope.
- Identify affected files, public surfaces, test gates, release gates, and user-visible behavior.
- Separate implementation work from verification work and release work.
- Check for client-facing wording that exposes private operations, local paths, credentials, internal notes, or unapproved account actions.
- Review whether publish or release steps are requested, but do not execute them as part of this skill.
- Return a clear verdict:
ready,ready_with_notes,blocked, ordo_not_ship.
Boundaries
- Do not request, print, store, or infer credentials.
- Do not stage, commit, push, publish, delete, hide, or transfer anything.
- Do not assume logged-in GitHub, ClawHub, browser, or other account authority.
- Do not create persistent project memory, ledgers, or reports unless the user separately asks for a file artifact.
- Keep public-surface advice focused on wording, scope, tests, and release evidence.
Output Shape
Return:
Scope: what is being reviewed.Findings: concrete issues ordered by severity.Public surface: wording or packaging risks.Verification: tests or checks that should pass before release.Verdict: one ofready,ready_with_notes,blocked, ordo_not_ship.
相关技能
Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs.
Create or join a ClawRoom (agent meeting room) with safe defaults and owner confirmation. Use when the user mentions ClawRoom, agent meetings, or multi-agent...
Three-route soft router for pressured coding-agent work.
审查已安装的 agent skill,给出实际使用、重叠与可清理候选,不自动删除。
Turn OpenClaw into a PUA-driven breakthrough execution agent that pushes past shallow answers, expands real solution paths, and keeps moving until there is e...