at-vision
Inspect an image, screenshot, photo, diagram, file path, or image URL for a non-vision main model. Prefer the inspect_image MCP tool; if MCP namespace tools are unsupported, use the installed local vision CLI fallback.
npx skills add kairyou/agent-tools --skill at-vision --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.
# Visual Reasoning Policy You cannot see images directly. The `inspect_image` MCP tool (server `agent-tools-vision`) sends one image plus narrow factual questions to a vision model and returns per-question answers. 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. Prefer `inspect_image`. If it is not exposed as a callable tool, or the host/model gateway cannot invoke MCP namespace tools, use the host's shell/command execution tool to run the installed fallback. First use a structured file-write capability to create a temporary JSON request; do not construct it with shell interpolation. Use the same shape as the MCP input: ```json { "image_source": { "type": "file", "value": "<path>" }, "questions": [{ "id": "q1", "text": "<question>" }] } ``` Choose a temporary request path containing no shell metacharacters, then run: ```text node "{{VISION_CLI_PATH}}" --request-file "<safe-temp-request.json>" --json ``` Delete the temporary request fil
- When to call — and when not to
- How to ask
- Whole-image extraction mode
- Using results
- Limits and failures
What does the at-vision skill do?
Inspect an image, screenshot, photo, diagram, file path, or image URL for a non-vision main model. Prefer the inspect_image MCP tool; if MCP namespace tools are unsupported, use the installed local vision CLI fallback.
How do I install it?
Run `npx skills add kairyou/agent-tools --skill at-vision --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 kairyou/agent-tools, a repository with 159 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.