๐Ÿ‘๏ธ
AI EngineeringJavaScript

At Vision

by kairyou

At Vision is an AI Engineering skill for Claude Code, published by kairyou in agent-tools.

178 stars0 forkson kairyou/agent-toolsAdded 2026/09/07+2% in starsRepository updated 2026/08/31
agent-hooksagent-skillsclaude-codecodexcoding-agentsdeveloper-toolsopencodestatuslineusage-monitoring
Install in seconds
Install At Vision
Copy At Vision into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/kairyou/agent-tools/tree/main/capabilities/vision/skills/at-vision ~/.claude/skills/at-vision

Requires Node.js. Downloads this skill only โ€” not the rest of the repository โ€” into your Claude Code skills folder.

Without Node.js

git clone https://github.com/kairyou/agent-tools.git

Clones the whole repository, then copy the skillโ€™s own directory into your skills folder yourself.

In this catalog

Source file
capabilities/vision/skills/at-vision/SKILL.md in kairyou/agent-tools
Installs to
~/.claude/skills/at-vision
Collection
One of 8 skills cataloged from this repository
Category
AI Engineering โ€” 3670 skills

What At Vision does

At Vision inspects screenshots, photos, diagrams, and image paths or URLs when a task depends on visible content. Use it when direct inspection fails or when you need the inspect_image provider or CLI fallback.

At Vision is cataloged under AI Engineering on DirSkills. At Vision comes from a repository tagged agent-hooks, agent-skills, claude-code, codex and coding-agents.

Documentation

README

Visual Reasoning Policy

If the prompt already contains actual image content, or a host image viewer returned that content, inspect it directly and do not call inspect_image. A file path or URL alone is not image content.

When only a file path or URL is available, direct inspection fails, or the user explicitly requests the provider, the inspect_image MCP tool (server agent-tools-vision) sends one image plus narrow factual questions to a configured vision model. You stay in charge of reasoning and the final answer; the vision model only reports observations.

inspect_image is a callable MCP tool, not an MCP resource. Call the tool directly. Never call list_mcp_resources or read_mcp_resource for images, and never use inspect_image as a resource URI.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about At Vision

  • What else does kairyou publish alongside At Vision?

    At Vision is one of 8 skills that DirSkills catalogs from kairyou/agent-tools, the repository it ships in. Its siblings there include At Commit, At Usage and Code Review. Each one is a separate skill with its own page in this directory, installs the same way At Vision does, and is maintained by kairyou in that same repository. The rest of the collection is listed on the kairyou/agent-tools page.

  • How does At Vision compare to other AI Engineering skills?

    At Vision ranks #3128 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of At Vision against them. Open each page to compare what they document and how they install.

More from kairyou/agent-tools

At Vision is one of 8 skills cataloged on DirSkills from kairyou/agent-tools.

See all 8 skills โ†’
๐Ÿ“
2026/09/07

At Commit

At Commit generates a Conventional Commits title from staged changes and waits for confirmation before committing. Use it when you want a commit message or need to review the wording before `git commit`.
Automation
1780
๐Ÿ“Š
2026/09/07

At Usage

At Usage queries the current API provider balance and recent usage from a local installed command. Use it when you need to surface usage status without formatting or extra explanation.
DevOps
1780
๐Ÿ”
2026/09/07

Code Review

Code Review reviews diffs, PRs, branches, and working-tree changes for bugs, regressions, convention violations, and cleanup opportunities. Use it when you need a careful pass over code changes before merging.
Quality
1780
๐Ÿ“
2026/09/07

Daily Work Log

Daily Work Log summarizes each dayโ€™s Git activity into a concise work log for a date or range. It uses the current repository, configured projects, or paths mentioned in conversation without requiring configuration.
Writing
1780
๐Ÿ“
2026/09/07

Self Evaluation Summary

Self Evaluation Summary turns Git history, work logs, or both into a concise self-evaluation for quarterly, semi-annual, or promotion reviews. It is used to group evidence into review-ready outcomes by author and date window.
Writing
1780
๐Ÿงน
2026/09/07

Simplify

Simplify reviews changed code for duplication, complexity, efficiency, and architecture fit, then applies cleanup fixes. Use it on diffs, commit ranges, PRs, paths, staged changes, or working-tree changes.
Quality
1780