OpenClaw

review

Professional reviewer and critic. Trigger whenever the user wants structured feedback on anything: documents, plans, code, decisions, strategies, designs, pitches, or arguments. Also triggers on phrases like "what do you think", "is this good", "check this for me", "give me feedback", "what am I missing", "does this make sense", or when the user shares something and wants an honest outside perspective before it goes further.

ethagent0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install ethagent/review

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Review — Structured Feedback System

What This Skill Does

Evaluates anything the user shares and delivers structured, prioritized, actionable feedback. Not praise. Not vague encouragement. Real assessment of what works, what does not, what is missing, and what should be reconsidered — delivered in a way the user can act on immediately.

Core Principle

Feedback that does not lead to action is noise. Every piece of feedback in a review must point to something specific the user can do differently. If a problem cannot be articulated specifically enough to suggest a fix, it is not ready to be delivered as feedback.

Workflow

Step 1: Identify What Is Being Reviewed

REVIEW_TYPES = {
  "document":   { criteria: ["clarity","structure","completeness","accuracy","audience_fit"] },
  "plan":       { criteria: ["feasibility","completeness","risk_coverage","dependencies","success_metrics"] },
  "code":       { criteria: ["correctness","readability","efficiency","edge_cases","maintainability"] },
  "decision":   { criteria: ["problem_definition","options_considered","evidence_quality","risk_assessment","reversibility"] },
  "pitch":      { criteria: ["hook","problem_clarity","solution_credibility","ask","objection_handling"] },
  "argument":   { criteria: ["claim_clarity","evidence_strength","logic","counterarguments","conclusion"] },
  "strategy":   { criteria: ["goal_clarity","market_reality","resource_feasibility","competitive_awareness","execution_path"] },
  "design":     { criteria: ["purpose_fit","usability","consistency","clarity","edge_cases"] }
}

If the type is not explicit, infer from what was shared. Apply the most relevant criteria set.

Step 2: Assess Against Criteria

For each relevant criterion, evaluate on a simple scale:

ASSESSMENT_SCALE = {
  "strong":   "Works well. No action needed. Worth noting so the user knows what to keep.",
  "adequate": "Functional but could be stronger. Worth improving if time allows.",
  "weak":     "...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/ethagent/review
Version: —
Commit: 1b08b6c59dd402f8e8b12094109657e1be2b6062
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Review — Structured Feedback System

## What This Skill Does

Evaluates anything the user shares and delivers structured, prioritized, actionable feedback.
Not praise. Not vague encouragement. Real assessment of what works, what does not, what is
missing, and what should be reconsidered — delivered in a way the user can act on immediately.

## Core Principle

Feedback that does not lead to action is noise. Every piece of feedback in a review must point
to something specific the user can do differently. If a problem cannot be articulated specifically
enough to suggest a fix, it is not ready to be delivered as feedback.

## Workflow

### Step 1: Identify What Is Being Reviewed
```
REVIEW_TYPES = {
  "document":   { criteria: ["clarity","structure","completeness","accuracy","audience_fit"] },
  "plan":       { criteria: ["feasibility","completeness","risk_coverage","dependencies","success_metrics"] },
  "code":       { criteria: ["correctness","readability","efficiency","edge_cases","maintainability"] },
  "decision":   { criteria: ["problem_definition","options_considered","evidence_quality","risk_assessment","reversibility"] },
  "pitch":      { criteria: ["hook","problem_clarity","solution_credibility","ask","objection_handling"] },
  "argument":   { criteria: ["claim_clarity","evidence_strength","logic","counterarguments","conclusion"] },
  "strategy":   { criteria: ["goal_clarity","market_reality","resource_feasibility","competitive_awareness","execution_path"] },
  "design":     { criteria: ["purpose_fit","usability","consistency","clarity","edge_cases"] }
}
```

If the type is not explicit, infer from what was shared. Apply the most relevant criteria set.

### Step 2: Assess Against Criteria

For each relevant criterion, evaluate on a simple scale:
```
ASSESSMENT_SCALE = {
  "strong":   "Works well. No action needed. Worth noting so the user knows what to keep.",
  "adequate": "Functional but could be stronger. Worth improving if time allows.",
  "weak":     "...

搜索