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
- martgueritainaccurate875/skillstheir own version, first seen Nov 8, 2026
- idexal/idexal-skillstheir own version, first seen Aug 26, 2026
- timelapsetech/mediaskillstheir own version, first seen Aug 15, 2026
- MiniMax-AI/skillstheir own version, first seen Mar 24, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- MiniMax-AI/skills★ 14ksame name
- martgueritainaccurate875/skills★ 6same name
- idexal/idexal-skills★ 2same name
- timelapsetech/mediaskills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-browserSkill
- background-task-runnerSkill
- officecli-docxSkill
- officecli-pptxSkill
- officecli-xlsxSkill
- rememberSkill
- role-publishSkill
- self-evolutionSkill
- skill-publishSkill
- swebench-correctorSkill
- swebench-recoverySkill
- swebench-reviewerSkill
- swebench-solverSkill
- webcliSkill
The file
Files
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
- 配置优先:每次执行前必须检查配置是否完整
- 缺失配置时:返回明确的缺失信息列表,不要执行读图
- 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
- 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_key | API 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)
- 读取图片文件
- 压缩为适合 API 的格式
- 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
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.

