glm-eyes
Skill1 starsChanged 3 months agoGPL-3.0View on GitHub
当主模型（如 GLM-5.2）无法读取图片时，用 sub-agent 调起任意多模态 Claude provider 来理解图片并返回文字描述。模型无关：不写死 Kimi，自动在 CC-Switch 路由中找一个已知的视觉模型，也可显式指定 provider。触发场景："图片读不了 / image read failed / 需要看图但当前模型不支持视觉 / 用 kimi 看图 / 用 glm-eyes 读图 / 描述这张截图 / 识别这张图片"。
In this repository21 other files it gives its agents.
- image-gen-rightcodesSkill
- image-ocrSkill
- knowledge-baseSkill
- llm-wiki-initSkill
- local-audio-transcriberSkill
- subtitle-proofreaderSkill
- video-downloaderSkill
- baoyu-translateSkill
- baoyu-format-markdownSkill
- baoyu-markdown-to-htmlSkill
- skill-lifecycleSkill
- storyweaveSkill
- check-ai-writeSkill
- correct-wrong-wordsSkill
- paper-rewriteSkill
- agent-dispatchSkill
- code-reviewerSkill
- codexSkill
- docs-writerSkill
- geminiSkill
- opencodeSkill
The file
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.