look-at

Installation
SKILL.md

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 trivial extraction Delegate to look_at

Red Flags - STOP Immediately When Thinking:

Related skills

More from edwinhu/workflows

Installs
2
GitHub Stars
13
First Seen
Mar 17, 2026