agentleFS
yaokai123yaokai123/AgentPaw/skills/vision-analysis/SKILL.md

vision-analysis

Skill1 starsChanged 3 months agoApache-2.0View on GitHub

图片视觉分析技能。当主模型不支持多模态时,用于分析图片内容。

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

图片视觉分析(Vision Analysis)

当主模型不支持多模态图片识别时,使用此技能分析图片内容。

硬规则

  1. 配置优先:每次执行前必须检查配置是否完整
  2. 缺失配置时:返回明确的缺失信息列表,不要执行读图
  3. 环境隔离:不使用任何环境变量,配置全部来自 SKILL.md 的 config 参数
  4. 错误处理:读图失败时返回清晰错误信息

分步执行流程

Step 1:检查配置

检查 config 是否包含以下必填项:

配置项说明检查方式
provider模型提供商anthropic / openai
api_keyAPI Key非空字符串
model模型名称非空字符串

如果缺少任何必填项,立即返回:

{
  "status": "config_incomplete",
  "missing": ["api_key", "model"]
}

Step 2:执行读图(如配置完整)

  1. 读取图片文件
  2. 压缩为适合 API 的格式
  3. 调用视觉模型分析

Step 3:返回结果

成功时:

{
  "status": "success",
  "analysis": "图片分析内容...",
  "model_used": "claude-3-5-sonnet-20240620"
}

失败时:

{
  "status": "error",
  "error": "错误原因"
}

配置参数说明

参数必填默认值说明
provider是-模型提供商:anthropic 或 openai
api_key是-API Key(不要用环境变量)
model是-视觉模型名称
base_url否官方默认API 端点
analysis_prompt否请详细描述这张图片分析提示词
max_tokens否1024最大返回 token 数

使用示例

/vision-analysis /path/to/image.png
/vision-analysis /path/to/image.png 分析这张截图的功能

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.