Update to Visual Sandbox

{
  "description": "Send feedback to the Visual Sandbox team with the MCP tool submit_feedback or `vsb feedback`: a bug, a result that missed what was asked, a missing feature or model, something confusing, or praise. Trigger when the person says \"tell them\", \"report this\", \"send feedback\", \"this is broken\", \"this should exist\", \"I love this\", or when a tool fails in a way that is not the person's input or your own mistake. One report for each issue, never when the person asks you not to send one.\n",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 280
    }
  ],
  "name": "vsb-feedback",
  "skill_md_contents": "---\nname: vsb-feedback\ndescription: >\n  Send feedback to the Visual Sandbox team with the MCP tool submit_feedback\n  or `vsb feedback`: a bug, a result that missed what was asked, a missing\n  feature or model, something confusing, or praise. Trigger when the person\n  says \"tell them\", \"report this\", \"send feedback\", \"this is broken\", \"this\n  should exist\", \"I love this\", or when a tool fails in a way that is not\n  the person's input or your own mistake. One report for each issue, never\n  when the person asks you not to send one.\nlicense: Proprietary. See LICENSE for the terms.\n---\n\n# Send feedback\n\nFeedback goes to the team that builds Visual Sandbox. It is free, and it is\nhow a defect gets fixed.\n\n## When to send\n\n- **The person asks.** Send what they say, as `source: \"user\"`.\n- **You see a defect yourself.** A tool fails with a server error, a result\n  breaks the model's own rules, an error message is wrong, or a documented\n  field does not work. Send it as `source: \"agent\"`, then tell the person in\n  one line that you sent it.\n\nDo not send:\n\n- Your own mistakes: a wrong field, a wrong slug, a file that was not there.\n- An expected refusal, such as too little credit or a field out of range.\n- Anything when the person asks you not to.\n- A refund request. Feedback starts no refund and no new run. Send the person\n  to hello@visualsandbox.com for a refund.\n\n## How to send\n\nOver MCP:\n\n```json\n{\n  \"category\": \"generation_quality\",\n  \"source\": \"agent\",\n  \"message\": \"Asked for a 9:16 clip of a red mug; got 16:9 with a blue mug. The prompt named the color twice.\",\n  \"attempted_task\": \"A product video for a mug\",\n  \"tool_name\": \"video_p_video\",\n  \"job_id\": \"8f3…\"\n}\n```\n\nWith the CLI: `vsb feedback \"<message>\" --kind generation_quality --json`.\n\n| `category` | Use it for |\n|------------|------------|\n| `bug` | An error, a crash, a tool that does not do what its description says |\n| `generation_quality` | A result that missed the prompt, the reference or the model's own promise |\n| `missing_feature` | A model, a field or a tool that the person needed and is not there |\n| `confusing` | A message, a price or a step that the person or you could not understand |\n| `praise` | Something that worked well |\n| `other` | Anything else |\n\n## Write the message\n\n- What was asked, what came back, and what was expected. Two or three\n  sentences.\n- The exact error text and the job id, when there is one.\n- No passwords, payment details, private files or the person's own words that\n  they did not want shared.\n\nSend one report for each issue. A second failure of the same kind in the same\ntask is not a new report.\n"
}