菜单
Critic skill. Given an executed work item (status pending-assessment), assess whether the Goal was actually accomplished. Identify the root cause when it was not (incorrect assumption, technical blocker, missing data). Updates work/<slug>/README.md Assessment section.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/allenai/asta-plugins --skill review-work命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | review-work |
| description | Critic skill. Given an executed work item (status pending-assessment), assess whether the Goal was actually accomplished. Identify the root cause when it was not (incorrect assumption, technical blocker, missing data). Updates work/<slug>/README.md Assessment section. |
| allowed-tools | Read(work/**) Read(project.md) Edit(work/**) Bash(ls work/**) Bash(jq *) |
Independent assessment of executed work. Reads only what is on disk; it does not see the executor's reasoning, by design.
work/<slug>/README.md with status: pending-assessment, plus the artifacts under work/<slug>/data/.
Same README, updated:
# Assessment populated with a verdict and explanation (see template below).status: done (if goal was accomplished) or status: needs-input (if it was not and human direction is needed) or status: pending-plan (if the assessment recommends a fresh plan attempt).# Goal section. Compare against # Results. Does the work actually answer the goal, or only adjacent questions?# Results, verify it is present under work/<slug>/data/.# Results supported by the artifacts? Spot-check by reading a sample.# Assessment
## Verdict
<accomplished | partial | not accomplished>
## Reasoning
<one or two paragraphs explaining the verdict against the Goal>
## Root cause (if not fully accomplished)
<one of: incorrect assumption | technical blocker | missing data | scope drift | other — with a sentence of detail>
## Recommended next status
<done | needs-input | pending-plan>
accomplished → set status: done.partial with a clear next step the agent can take → set status: pending-plan and write a short note in the Assessment recommending what to plan next.partial or not accomplished requiring user input → set status: needs-input.