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/tslateman/duet --skill sweep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。
Audit a workspace for recurring friction, pick the highest-leverage one, and build the automation that removes it. Use when the user asks "what should I automate", "what's wasting my time", "find the friction in my workflow", wants a self-improvement pass over their own tooling, or runs this on a recurring loop.
Audit whether another agent actually did what was asked, not just whether the code is good. Use to watch, audit, compare, or fix another agent's work: a Claude Code or Codex session, a transcript, a PR, a branch, a CI run, or a workflow run.
Review what agents accomplished, surface loose ends across sessions
正在显示 SKILL.md
基于 SOC 职业分类
| name | sweep |
| description | Post-op check for artifacts, damage, and stale references after agent work |
Audit the working tree after agent work completes. Find what the agents left behind.
Map every file touched, across all repos affected:
git diff --stat
git diff --cached --stat
If other repos were modified (check recent tool output or plan files for cross-repo work), run git diff --stat there too.
Flag anything unexpected, files not mentioned in the plan or task.
Check whether test fixtures, example files, seed data, or sample configs were modified:
example, fixture, seed, sample, mock, test-dataSearch for references that became outdated by the work:
Scan for artifacts agents leave behind:
console.log, print(), echo "DEBUG" statements*.tmp, *.bak, /tmp/ references)Identify changes outside the task scope:
If plan files exist for the work just completed, check acceptance criteria:
Present findings as a short checklist:
Be terse. Name files and line numbers. Skip categories with no findings.
The post-agent triad: sweep checks for collateral damage, the other two check fidelity and threads.
/debrief: cross-session recap of what agents accomplished and the loose ends/agent-watchdog: audit whether an agent did what was asked, with a gap report and a narrow fix