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€” 3475 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 3475 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†’