seeing-images
Augmented vision tools for analyzing images beyond native visual capabilities. Use when tasked with describing images in detail, reproducing images as SVGs, identifying subtle features, comparing image regions, reading degraded text, or any task requiring careful visual inspection. Also use when the image-to-svg skill needs ground truth about colors, shapes, or boundaries.
npx skills add majiayu000/claude-skill-registry --skill seeing-images --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.
# Seeing Images Compensatory vision tools based on empirically measured blindspots (vision diagnostic v1-v4, 2026-03-25). ## When to Use Activate this skill when: - Describing an uploaded image in detail - Reproducing an image as SVG (use BEFORE drawing to establish ground truth) - Comparing two images or regions for differences - Reading text in degraded/compressed/low-contrast images - Identifying subtle features (gradients, faint overlays, reflections) - Any image task where accuracy matters more than speed ## Known Blindspots (from diagnostics) These are MEASURED limitations — not guesses: | Blindspot | Threshold | Compensatory Tool | |-----------|-----------|-------------------| | Luminance contrast | ~15-20 RGB steps invisible | `enhance`, `histogram`, `sample` | | Gradients | <30-step range invisible | `gradient_map`, `enhance` | | Context color bias | Dress effect, simultaneous contrast | `isolate`, `sample` | | Small elements | <15px effectively invisible | `crop`, `grid` | | Dense counting | Degrades >15 items, ~50% error at 30 | `count_elements` | | Subtle atmospherics | Steam, faint reflections lost in noise | `enhance`, `denoise` | ## Workflow ### Setup (one line, ever
- When to Use
- Known Blindspots (from diagnostics)
- Workflow
- Setup (one line, every time)
- Quick Analysis (2-3 tool calls)
- Deep Analysis (for SVG reproduction, spot-the-difference, etc.)
- Tool Reference
- grid(path, rows=3, cols=3, labels=True)
- sample(path, points, radius=3)
- histogram(path, region=None)
- enhance(path, region=None, factor=2.0, mode='contrast')
- edges(path, threshold=50)
- gradientmap(path, region=None)
- isolate(path, region, padding=20, bg=(128,128,128))
What does the seeing-images skill do?
Augmented vision tools for analyzing images beyond native visual capabilities. Use when tasked with describing images in detail, reproducing images as SVGs, identifying subtle features, comparing image regions, reading degraded text, or any task requiring careful visual inspection. Also use when the image-to-svg skill needs ground truth about colors, shapes, or boundaries.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill seeing-images --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.