Analyze images and videos via ZenMux API (Gemini backend). Use for: any video (local or URL), image URLs, webpages with embedded video (e.g. YouTube), or local images when the agent is NOT natively multimodal. TRIGGER on: "帮我看", "看看这个", "分析一下这个视频", any request to view/describe/analyze/summarize visual media. DO NOT TRIGGER for local image files when the agent is natively multimodal (e.g. Claude Code with vision) — use the Read tool directly instead. Never trigger for text, PDFs, or audio.
How to install see?
oil-oil/see
$npx -y skills add oil-oil/see --skill seeInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/oil-oil/see" --skill "oil-oil/see"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/oil-oil/see" that are relevant to the current task. Run `npx skills add "https://github.com/oil-oil/see"` and select the relevant skills, then follow their instructions.
Related
6 picksType
- researchInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.Jul 2026
- analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories.Jul 2026
- paper-context-resolverRigor Paper Context helper for README-first deep learning repo reproduction.Jul 2026
- repo-intake-and-planRigor Intake helper for README-first deep learning repo reproduction.Jul 2026
- firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find…Jul 2026
- customer-researchWhen the user wants to conduct, analyze, or synthesize customer research.Jul 2026
