跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 review

Review

检查工作,发现漂移前。 另一种观点认为,早期捕捉到错配. 在自然暂停点、公关前、或感觉不对的时候使用.

114 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

检查工作,发现漂移前。 另一种观点认为,早期捕捉到错配. 在自然暂停点、公关前、或感觉不对的时候使用.

何时用

在以下情况下启动`/审查 ' :在自然暂停点前,感觉有些不对劲,范围似乎已经扩大,或在公关之前

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:/review、When to Use、Review Lenses、The Review Process、Step 1: State the Original Aim、Step 2: Check Alignment。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/code.md、references/writing.md、references/learning.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.

/reviewWhen to UseReview LensesThe Review ProcessStep 1: State the Original AimStep 2: Check AlignmentStep 3: Check the FrameStep 4: Detect DriftStep 5: Decide Next ActionOutput FormatReviewAlignment Check

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
review
description
Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 3
  • references/code.md
  • references/writing.md
  • references/learning.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「review」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-dd14356282303626-%E5%AE%A1%E6%9F%A5.html
请存为 .cursor/skills/review/SKILL.md 或 .claude/skills/review/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/open-horizon-labs/skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/open-horizon-labs/skills' --list

npx skills add 'https://github.com/open-horizon-labs/skills' --skill 'review'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: review description: Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.

/review

A second opinion before committing. Checks alignment between intent and execution, detects drift, and decides: continue, adjust, or salvage.

Part of the Intent → Execution → Review loop at every scale — from a single commit to a multi-week project. Review closes the loop.

When to Use

Invoke /review when: before committing, at natural pause points, something feels off, scope seems to have grown, or before PRs.

Do not use when: You're in deep flow and making progress. Review at natural breaks, not arbitrary intervals.

Review Lenses

Default to the core workflow review in this file. When the artifact being reviewed needs a sharper domain lens, load the matching supporting reference:

Use these as lenses, not replacement workflows. The final review still answers the core /review questions: aim, alignment, sufficiency, mechanism, drift, completion, and next action.

The Review Process

Step 1: State the Original Aim

"The aim was: [original intent in one sentence]"

If you can't state the aim clearly, that's the first finding.

Step 2: Check Alignment

Ask six questions. Keep them artifact-neutral; load a review lens only when the artifact needs domain-specific judgment.

  1. Necessary? — Does this still need to exist now, or did speculative work creep in?
  2. Aligned? — Does the current work still serve the original aim?
  3. Sufficient? — Is this enough for the aim without unnecessary scope, abstraction, or entanglement?
  4. Mechanism clear? — Can you state why this approach should produce the intended outcome?
  5. Risks retired? — Did every named risk, alternate frame, invalidation signal, and stop/pivot trigger get tested, accepted with evidence, or triggered?
  6. Complete? — Are promised characteristics, dependencies, verification, and handoff covered?

If RNA MCP is available, check work against guardrails (oh_search_context with artifact_types: ["guardrail"]) and declared outcomes (outcome_progress).

Step 3: Check the Frame

Before naming ordinary drift, ask whether the interpretation itself collapsed:

  • What situation did we think we were in?
  • What evidence no longer fits that story?
  • Did the aim, mechanism, or constraints change meaning rather than just change scope?
  • Would continuing require pretending the old frame still explains the work?

Frame Collapse — the working interpretation no longer explains the evidence, constraints, or aim. Treat this separately from drift. Route it by where the break lives: back to /problem-statement for a bad frame, /problem-space for a bad situation map, /aim for changed intent, or /salvage when the session needs learning extraction before restart.

A named alternate frame that remains model-checkable but untested is incomplete execution, not automatic frame collapse and not a note for later. A named risk with a non-adversarial check is also incomplete: if the evidence would pass the tempting local patch, the risk was not retired. Route to Adjust when the selected approach is still plausible and the missing/adversarial check can be added. Route to Reframe only when evidence already invalidates the selected approach or the alternate frame better explains the problem than the current one.

Step 4: Detect Drift

Drift is the gap between where you started and where you are. Explicitly name any drift found:

Scope Drift — task grew beyond original boundaries Solution Drift — approach changed from plan Goal Drift — aim itself shifted without explicit decision Frame Collapse — evidence invalidated the story that made the work make sense

For each drift or frame collapse:

Drift: [type]
Started as: [original frame/plan]
Became: [current evidence/model]
Impact: [what this means]
Route: [continue | adjust | /problem-statement | /problem-space | /aim | /salvage]

Step 5: Decide Next Action

| Decision | When | Action | |----------|------|--------| | Continue | Aligned, on track, and named risks retired or explicitly accepted | Proceed with confidence | | Adjust | Minor drift, recoverable issue, model-checkable named risk is still untested, or retirement evidence is non-adversarial while the selected approach remains plausible | Add the missing/adversarial check or correction and continue | | Reframe | Frame collapse, invalidation triggered, or evidence shows an alternate frame better explains the problem than the selected approach | Return to /problem-statement, /problem-space, or /aim | | Pause | Unclear aim, major questions, or required human/domain verification | Stop, clarify, then resume | | Salvage | Significant drift or failed frame needs extraction | Extract learning with /salvage |

If the review surfaces new hard constraints, record them (oh_record_guardrail_candidate).

Output Format

## Review

**Aim:** [original intent]
**Status:** [Continue / Adjust / Reframe / Pause / Salvage]

### Alignment Check
- Necessary: [Yes/No - brief note]
- Aligned: [Yes/No - brief note]
- Sufficient: [Yes/No - brief note]
- Mechanism clear: [Yes/No - brief note]
- Changes complete: [Yes/No - brief note]
- Risks retired: [Yes/No - every named risk/stop trigger is covered by evidence, accepted with rationale, or triggered]

### Frame Check
[State whether the current frame still explains the evidence. If collapsed, name the new frame or route to reframe/salvage.]

### Drift Detected
[List any drift found, or "None detected"]

### Risk Retirement Review
[List each named risk / alternate frame / stop trigger from Solution Space and Execute with its evidence. Mark untested model-checkable items or non-adversarial checks as Adjust unless observed evidence invalidates the selected approach; mark those as Reframe.]

### Needs Human Verification
Claims that cannot be self-checked by the model and require independent human judgment:
- [claim or assumption that needs external confirmation]
- [one-way decision that was not independently challenged]
- [delivered characteristic that was asserted but not externally observed]

If this section is empty, say why. Model-generated review of model-generated work shares the same blindspots. The purpose of this section is to route the right questions to the actual human checkpoint (PR review, stakeholder sign-off, manual test) rather than pretending the model can answer them.

### Decision
[Reasoning for the status decision]

### Next Steps
[Concrete actions to take]

Completion Gate (Before "Done")

When the user or agent claims work is complete, verify:

  1. Intent clear? — Can you state what changed and why in one sentence?

  2. Work reviewed? — Has the actual artifact been checked against the stated intent?

  3. Evidence present? — Are the relevant checks, examples, or observations recorded?

  4. Feedback handled? — Have review comments or open objections been resolved or explicitly deferred?

  5. Declared criteria delivered? — Were promised characteristics verified, not merely claimed?

  6. Needs Human Verification surfaced? — Have claims the model cannot self-check been flagged for human attention?

  7. Risk retirement complete? — Were all named risks/alternate frames/stop-pivot triggers tested, explicitly accepted, or routed to Adjust/Reframe/Pause? If incomplete:

"Completion gate: [missing step]. Run the check before marking complete."

Session Handoff

If a session file is in use, replace or append ## Review. Preserve frame check, verification result, risk-retirement review, human-verification needs, and unresolved objections for later phases.

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…