render-agent
生成图片、画图、出图、AI绘画、图像生成。当用户要求生成图片、画一张图、出几张图、AI绘画时，必须使用此技能调用本地ComfyUI生成，不要使用任何在线服务或API。
Best use case
render-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
生成图片、画图、出图、AI绘画、图像生成。当用户要求生成图片、画一张图、出几张图、AI绘画时，必须使用此技能调用本地ComfyUI生成，不要使用任何在线服务或API。
Teams using render-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/render-agent/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How render-agent Compares
| Feature / Agent | render-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?
生成图片、画图、出图、AI绘画、图像生成。当用户要求生成图片、画一张图、出几张图、AI绘画时，必须使用此技能调用本地ComfyUI生成，不要使用任何在线服务或API。
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
# 图像生成（ComfyUI 本地）
当用户要求生成图片时，按以下步骤执行，不要询问用户选择方案，直接执行：
## 第一步：健康检查
```bash
python3 /home/node/.openclaw/workspace/tools/comfyui-client.py health
```
如果返回 ok:false，告诉用户执行 `bash ~/ai-studio/start_comfyui.sh`
## 第二步：创建运行记录
```bash
python3 /home/node/.openclaw/workspace/tools/run-tracker.py new
```
记住返回的 run_id，后续每步都要更新。
## 第三步：生成 prompt
根据用户的中文描述，先读取模板库：
```bash
cat /home/node/.openclaw/workspace/prompt-templates.json
```
然后生成英文 prompt：
- SDXL 用关键词+权重：`(cyberpunk:1.2), (cinematic lighting:1.3), ...`
- 拼接匹配风格模板的 suffix
- negative 固定加：`(worst quality:1.4), (low quality:1.4), blurry, deformed hands, extra fingers, bad anatomy, watermark, text`
## 第四步：修改工作流并提交
```python
import json, random
with open('/home/node/.openclaw/workspace/workflows/sdxl_basic.json') as f:
wf = json.load(f)
wf['6']['inputs']['text'] = '你生成的正向prompt'
wf['7']['inputs']['text'] = '你生成的负向prompt'
wf['3']['inputs']['seed'] = random.randint(1, 2**31)
with open('/tmp/gen_workflow.json', 'w') as f:
json.dump(wf, f)
```
## 第五步：执行生成
单张：
```bash
python3 /home/node/.openclaw/workspace/tools/comfyui-client.py wait --workflow /tmp/gen_workflow.json --output-dir /home/node/ai-outputs
```
用户要求多张时，改不同seed重复提交。
## 第六步：更新运行记录
```bash
python3 /home/node/.openclaw/workspace/tools/run-tracker.py update --run-id <RUN_ID> --data '{"status":"completed","checkpoint":"sd_xl_base_1.0.safetensors","seeds":[...],"render_result":{...}}'
```
## 第七步：报告结果
告诉用户图片已生成，文件在 ~/ai-studio/comfyui/output/creative_workshop/ 目录下。
## 规则
- 不要询问用户选择方案，直接用ComfyUI生成
- 不要推荐在线服务、不要推荐安装其他技能
- 不要输出长篇方案对比，直接执行
- 每次生成都要创建运行记录
## 黑图检测与重试
生成完成后检查图片文件大小：
- 文件小于 50KB → 判定为黑图/损坏图
- 自动重试：换一个随机seed重新生成
- 最多重试3次
- 如果3次都失败，报告错误并建议用户重启ComfyUI
检测命令示例：
```bash
FILE_SIZE=$(stat -f%z "$IMAGE_PATH" 2>/dev/null || stat -c%s "$IMAGE_PATH" 2>/dev/null)
if [ "$FILE_SIZE" -lt 50000 ]; then
echo "黑图检测：文件仅${FILE_SIZE}字节，判定为损坏，准备重试"
fi
```Related Skills
gotchi-3d-custom-render
Render custom Aavegotchi 3D images from arbitrary trait and wearable combinations. Use when the user describes a synthetic or hypothetical gotchi look in plain language, asks for an outfit preview, headshot, or full-body image, and is not asking for an existing onchain token by tokenId or inventory URL.
agent-render-linking
Create zero-retention agent-render.com links for markdown, code, diffs, CSV, or JSON artifacts. Use when an agent needs to share a nicely rendered artifact in the browser instead of pasting raw content into chat. Trigger for requests like "share this as a link", "make a diff link", "render this markdown/code/csv/json", or when chat rendering is weak. Agent Render is open source, hosted on Cloudflare Pages, and self-hostable. Use platform-specific linked-text syntax only on surfaces that support it cleanly, such as Discord Markdown links, Telegram HTML links, or Slack mrkdwn links; otherwise send a short summary plus the raw URL.
renderkit
Render structured data as beautiful hosted web pages, and create hosted forms for data collection, using the RenderKit API. Use this for visual pages, surveys, RSVPs, feedback forms, or any structured data.
render-stl-png
Render an STL to a PNG from a nice, consistent 3D angle ("Blender-ish" default perspective) with a solid color.
render
Render cloud platform — manage services, deployments, databases, environment groups, and custom domains via the Render API. Deploy web services, static sites, cron jobs, and databases with automatic scaling. Built for AI agents — Python stdlib only, zero dependencies. Use for cloud deployment, service management, database provisioning, CI/CD automation, and infrastructure management.
slug-font-rendering
Reference HLSL shader implementations for the Slug font rendering algorithm, enabling high-quality GPU-accelerated vector font and glyph rendering.
json-render-generative-ui
Generative UI framework that renders AI-generated JSON specs into type-safe UI components across React, Vue, Svelte, Solid, React Native, video, PDF, and email.
---
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.