How do I install the Configuring Vision skill?

Run npx skillmds@latest add oxbshw/configuring-vision in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Configuring Vision safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Configuring Vision?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Configuring Vision free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Configuring Vision?

oxbshw (@oxbshw) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Configuring Vision by oxbshw — Agent Skill

Name: Configuring Vision
Author: oxbshw

Configuring Vision

The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models. Use this to configure provider-neutral visual understanding without tying Watch Skill to one agent or model vendor.

oxbshw 757477b 1.9 KB Updated Sep 17, 2026

File contents

Configuring vision

Watch Skill's agent surface and model backend are separate choices. Claude Code, Codex, Cursor, OpenClaw, framework agents, and REST clients all call the same engine; the engine can send selected frames to any supported vision provider.

Supported providers

watch-skill setup-vision --provider anthropic --api-key <KEY>
watch-skill setup-vision --provider openai --api-key <KEY>
watch-skill setup-vision --provider gemini --api-key <KEY>
watch-skill setup-vision --provider openrouter --api-key <KEY>
watch-skill setup-vision --provider ollama

Prefer a key the user already has. Do not claim Ollama is required, and do not ask the user to reveal a secret in chat. They can set the matching environment variable or run the command privately in their terminal.

Route bulk work and verification separately

One model can serve both tiers:

watch-skill setup-vision --provider openai --api-key <KEY> --model <vision-model>

Or use a cheaper model for scene descriptions and a stronger model for uncertain answers and loop critiques:

watch-skill setup-vision --provider openrouter --api-key <KEY> \
  --cheap-model <fast-vision-model> --strong-model <strong-vision-model>

Add --verify to make one live probe call. If it fails, report the structured error and its fix; never echo the key.

No provider is also valid

Without a vision API, Watch Skill still acquires video, reads captions, runs local transcription and OCR, indexes evidence, and searches it. Visual synthesis degrades to timestamped evidence instead of guessing.

---name: configuring-visiondescription: The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models. Use this to configure provider-neutral visual understanding without tying Watch Skill to one agent or model vendor.license: MIT---# Configuring visionWatch Skill's agent surface and model backend are separate choices. Claude Code,Codex, Cursor, OpenClaw, framework agents, and REST clients all call the same engine;the engine can send selected frames to any supported vision provider.## Supported providers```bashwatch-skill setup-vision --provider anthropic --api-key <KEY>watch-skill setup-vision --provider openai --api-key <KEY>watch-skill setup-vision --provider gemini --api-key <KEY>watch-skill setup-vision --provider openrouter --api-key <KEY>watch-skill setup-vision --provider ollama```Prefer a key the user already has. Do not claim Ollama is required, and do not askthe user to reveal a secret in chat. They can set the matching environment variableor run the command privately in their terminal.## Route bulk work and verification separatelyOne model can serve both tiers:```bashwatch-skill setup-vision --provider openai --api-key <KEY> --model <vision-model>```Or use a cheaper model for scene descriptions and a stronger model for uncertainanswers and loop critiques:```bashwatch-skill setup-vision --provider openrouter --api-key <KEY> \ --cheap-model <fast-vision-model> --strong-model <strong-vision-model>```Add `--verify` to make one live probe call. If it fails, report the structured errorand its `fix`; never echo the key.## No provider is also validWithout a vision API, Watch Skill still acquires video, reads captions, runs localtranscription and OCR, indexes evidence, and searches it. Visual synthesis degradesto timestamped evidence instead of guessing.

Frequently asked questions