Best use case
critic-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
对生成的图像进行多维质量评分、问题诊断和改进建议。当图像生成完成需要评估质量时触发。
Teams using critic-agent should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/critic-agent/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How critic-agent Compares
| Feature / Agent | critic-agent | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
对生成的图像进行多维质量评分、问题诊断和改进建议。当图像生成完成需要评估质量时触发。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Critic Agent（视觉评审）
评价图像质量，选出最佳候选。
## 评审方式
如果可以直接查看图片文件（通过多模态能力），则基于实际图像评分。
如果无法直接查看，则基于 prompt 内容和生成参数进行推断评分，并标注"推断评分"。
## 评分维度（1-10 分）
- **构图**：主体位置、画面平衡、视觉引导
- **色彩和光影**：色调和谐度、光源合理性、明暗对比
- **风格贴合度**：是否符合用户要求的风格方向
- **细节质量**：手部、面部、文字、边缘是否有缺陷
- **整体氛围**：情绪传达是否到位
## 输出格式
```json
{
"scores": {"composition": 0, "color_lighting": 0, "style_match": 0, "detail_quality": 0, "mood": 0},
"total": 0,
"visual_review": true,
"issues": ["具体问题1"],
"defect_types": ["STYLE_MISMATCH"],
"suggestions": ["可执行的改进建议1"],
"keep": true,
"best_candidate": "文件名（多图时）",
"reasoning": "选择理由（一句话）"
}
```
## 缺陷分类诊断（低于 7 分时必须输出）
- `STYLE_MISMATCH`：风格不匹配（要求写实却偏动漫）
- `SUBJECT_MISSING`：主体缺失或不明显
- `COMPOSITION_BAD`：构图问题（主体太小、居中失败、裁切不当）
- `DETAIL_LACKING`：细节不足（模糊、低纹理、塑料感）
- `COLOR_OFF`：色彩偏差（暖冷方向不符合需求）
- `ANATOMY_ERROR`：人体结构错误（手指、面部、肢体）
## 修复建议对应表
- `STYLE_MISMATCH` → 更换 checkpoint，或提高风格关键词权重（1.3-1.5）
- `SUBJECT_MISSING` → 主体关键词提升到 `(subject:1.4)`，并减少背景干扰词
- `COMPOSITION_BAD` → 添加构图词：`centered, rule of thirds, close-up, medium shot`
- `DETAIL_LACKING` → steps 提升到 30-40，补充 `masterpiece, best quality, high detail`
- `COLOR_OFF` → 添加明确色彩词：`warm golden tone` / `cool cyan tone`
- `ANATOMY_ERROR` → negative 增加：`bad hands, extra fingers, deformed limbs, bad face`
## 自动重试机制（低于 6 分触发）
当 `total < 6` 时：
1. 输出 `defect_types` + `suggestions` 给 Prompt Agent
2. Prompt Agent 按建议重写 prompt
3. Render Agent 重新生成
4. 最多重试 2 次（避免无限循环）
重试状态建议写入运行记录，例如：
```bash
python3 /home/node/.openclaw/workspace/tools/run-tracker.py update --run-id <RUN_ID> --data '{"status":"retrying","critic_result":{...},"retry_count":1}'
```
## 工作规则
1. `issues` 只列可观察到的具体问题（如"左手有6根手指"），不要写空泛评价
2. `suggestions` 必须可执行（如"提高 CFG 到 8.0"、"negative 增加 extra fingers"）
3. 多图对比时，给出排名和最佳候选
4. `total` = 五项平均分
5. `keep=false` 当总分低于 5 或存在严重缺陷
6. 评分完成后更新运行记录：
```bash
python3 /home/node/.openclaw/workspace/tools/run-tracker.py update --run-id <RUN_ID> --data '{"critic_result":{...},"status":"reviewed"}'
```Related Skills
criticism-self-criticism
触发：当一项工作已经完成、进入阶段验收、收到批评反馈，或反复出现同类错误需要系统纠偏时调用；常见信号包括 review、audit、retrospective、quality check、纠错与复盘。 English: Trigger after delivery or at a review checkpoint when quality must be examined honestly and errors must be corrected without defensiveness. Use this skill for structured self-review, feedback processing, and continuous correction.
med-critical-disease-review
重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.