- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add oxbshw/watch-skill --skill configuring-vision -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add oxbshw/watch-skill --skill configuring-vision -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add oxbshw/watch-skill --skill configuring-vision -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add oxbshw/watch-skill --skill configuring-vision -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/oxbshw/watch-skill/tree/HEAD/skills/configuring-visionFrom the publisher
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.
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.
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.
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.
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 th
---name: configuring-visiondescription: The user wants to connect an LLM or vision provider, already has an API key, asks "can I use…---# skills/configuring-vision/SKILL.mdOverview
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.
FAQ
Download skills/configuring-vision/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/oxbshw/watch-skill.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.