Update to Radarkit

{
  "name": "manage-prompts",
  "description": "Add the questions (prompts) a Radarkit project tracks, group them into topics, and re-ask a prompt to every AI model right now. Use when the user wants to track new questions, organise prompts into topics, or get a fresh answer for a prompt immediately instead of waiting for the next scheduled run.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 271
    }
  ],
  "skill_md_contents": "---\nname: manage-prompts\ndescription: Add the questions (prompts) a Radarkit project tracks, group them into topics, and re-ask a prompt to every AI model right now. Use when the user wants to track new questions, organise prompts into topics, or get a fresh answer for a prompt immediately instead of waiting for the next scheduled run.\n---\n\nUse this skill when the user wants to add, group, or immediately re-run tracked prompts. It needs a key or connection with the Write permission; if the tools are not listed, say so.\n\n1. Call `list_projects` and pick the project (ask if there are several and none was named).\n2. Call `list_topics`. Reuse an existing topic when its name fits. Create one with `add_topic`\n   only when nothing fits; the server refuses duplicates and returns the existing topic id.\n3. Turn the user's request into prompt texts written the way a real person would ask an AI\n   assistant: one question each, under 255 characters, no numbering. Show the list and ask\n   for confirmation before adding.\n4. Call `add_prompts` once with the topic id and up to 50 prompts. Report what was added and\n   what was skipped as a duplicate. New prompts are answered on the project's next scheduled\n   run; say when that is (`next_run_at` from `get_project`).\n5. Only when the user explicitly asks for an answer now, call `run_prompt_now` for that one\n   prompt. It spends one realtime credit from the project owner's balance, so confirm first.\n   Afterwards, the fresh answers appear in `list_responses` with `realtime: true` within a few\n   minutes; poll `list_prompts` until the prompt's model states read `completed`.\n\nDo not add prompts the user did not confirm. Do not run a prompt now on the user's behalf as\na side effect of adding it. Do not run the same prompt again while it is still processing;\nthe server answers PROMPT_PROCESSING, wait for it to finish.\n"
}