Skills for Real Engineers. Straight from my .agents directory.
39 skills
vision-skills
Agent skill from
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/html_shot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long screenshots or chat histories, locating elements, comparing, rebuilding as HTML/SVG, digitizing a sketch or diagram, reading values off a chart, operating a GUI from screenshots — and to re-check an image yourself when a description you were given lacks a detail.
How to install vision-skills
install vision-skills
# install the agent-vision-toolkit pack with the skills CLI
npx skills add Anionex/agent-vision-toolkit# or add only this skill to Claude Code: copy the folder
skills/vision-skills/
# into
~/.claude/skills/vision-skills/ (all projects)
.claude/skills/vision-skills/ (one project)
1# vision-skills23Five local CLIs that give a text-only agent eyes. They read one shared4vision config (`VISION_API_KEY` / `VISION_BASE_URL` / `VISION_MODEL` /5`LANG`), plus the optional Python-client settings `VISION_API_PROTOCOL`,6`VISION_REASONING_EFFORT`, and `VISION_USER_AGENT` — no extra credentials.78Pick the tool by the question you are answering:910| Question | Tool |11|---|---|12| "What does this image show / say?" | `glance` |13| "Where is X?" — a thing you can name | `ground` |14| "Where are all the Xs?" — every instance of a kind | `detect` |15| "What is its exact shape, size, offset?" | `trace` |16| "Cut this box out as its own image file" | `crop` |17| "OCR this long screenshot / scrolling page / chat history" | `scripts/long_screenshot_ocr.py` |18| "Extract the icon/logo foreground as transparent PNG — manual region or auto (cropped+scaled screenshots)" | `scripts/extract_fg.py` |19| "Turn this HTML file into a viewport or full-page screenshot" | `scripts/html_shot.py` |20| "Which colours dominate a region, and which palette value fits it?" | `scripts/dominant_colors.py` |21| A relation none of them return — a gap, a distance between two located things | code over the pixels (Pillow) |2223`glance` answers what something is; `ground` and `detect` answer where.24You give `ground` a description of a particular thing; you give `detect` a25kind and it enumerates the instances.2627Both give real coordinates, but they are not pixel-exact: the box arrives28…
Excerpt shown under the repository's MIT license.
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
CCCXCUGH6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills