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.
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。
基于 SOC 职业分类
Show the user the agent's work on a research project and save iterations on the user's behalf. Scaffold rendering and deploy infrastructure (Quarto today, GitHub Pages, dev container), show the rendered output, save iterations. Doesn't handle research execution (use `asta-flows`).
Install or update the `asta` CLI to the version pinned by this plugin. Invoke whenever `asta` is not on PATH (e.g. `command not found` for `asta`) or when a subcommand/flag appears missing — that signals a stale install needing an update.
Converse with the user to identify the next most productive units of work for the current project, and record them in project.md under Pending Work. Use when the user wants to plan what to work on next, or when there is no project.md yet.
Execute the approved plan in work/<slug>/README.md (status ready), write outputs into work/<slug>/data/, record what happened in the Results section, then hand off to review-work. Use when there is a ready work item.
Write a detailed, executable plan for a single unit of work, then get it approved by review-plan. Updates work/<slug>/README.md with concrete instructions and sets status to ready (or needs-input if review repeatedly rejects).
Critic skill. Given a plan in work/<slug>/README.md (status pending-review), check that the steps are concrete, the tools are appropriate, and the plan is realistic. Write a verdict and feedback back into the README.
| 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.