look-at
This skill should be used when the user asks to 'look at', 'analyze', 'describe', 'extract from', or 'what's in' media files like PDFs, images, diagrams, screenshots, or charts. Triggers include: 'what does this image show', 'extract the table from this PDF', 'describe this diagram', 'what's in this screenshot', 'analyze this chart', 'read this image', 'get text from this PDF', 'summarize this document', or requests for specific data extraction from visual or document files. Use when analyzed/interpreted content is needed rather than literal file reading (which uses Read tool).
npx skills add majiayu000/claude-skill-registry --skill look-at-edwinhu-workflows-3 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Look At - Multimodal File Analysis Fast, cost-effective file analysis using Google's Gemini 2.5 Flash Lite model for PDFs, images, diagrams, and other media files. ## Tool Selection Enforcement ### Rationalization Table - STOP When Thinking: | Excuse | Reality | Do Instead | |--------|---------|------------| | "I can read images directly with Read" | You'll waste thousands of context tokens showing the full image | Use look_at for analysis | | "I'll use Read for this PDF" | You'll lose table structure and visual information by extracting raw text | Use look_at for PDFs with tables/charts/diagrams | | "Just a quick glance at the file" | Your quick glances still consume full context tokens | Use look_at for targeted extraction | | "I need exact text, so Read is required" | Gemini's extraction is accurate for most use cases | Use look_at first, Read only if extraction insufficient | | "look_at adds complexity" | You gain context savings and faster processing | Use look_at for media files | | "The file is small" | Your small files still waste context if uninterpreted | Size doesn't determine tool choice, content type does | | "I'll process it myself" | You waste reasoning tokens on t
- Tool Selection Enforcement
- Rationalization Table - STOP When Thinking:
- Red Flags - STOP Immediately When Thinking:
- Cost & Context Benefits
- When to Use
- How It Works
- Usage Pattern
- Response Rules
- Supported File Types
- Model Options
- Agentic Vision Mode
- Common Patterns
- Extract Specific Information
- Describe Visual Content
Discover script path from plugin cache (run inline with each command) Basic usage python3 "$LOOK_AT" \ With custom model Bash tool call with: export GOOGLE_API_KEY="your-api-key-here" pip install google-genai
What does the look-at skill do?
This skill should be used when the user asks to 'look at', 'analyze', 'describe', 'extract from', or 'what's in' media files like PDFs, images, diagrams, screenshots, or charts. Triggers include: 'what does this image show', 'extract the table from this PDF', 'describe this diagram', 'what's in this screenshot', 'analyze this chart', 'read this image', 'get text from this PDF', 'summarize this document', or requests for specific data extraction from visual or document files. Use when analyzed/interpreted content is needed rather than literal file reading (which uses Read tool).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill look-at-edwinhu-workflows-3 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.