{"id":48133,"plugin_id":"plugins_6abffe30af5881919d4fc103b4e6c368","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-24T13:35:32.820Z","digest":"52260c7e2bac4f9846e18da48c25398c3911049be3bea45f9acd546426849019","against":null,"payload":{"description":"Use when the user wants to find DataRobot capabilities — skills, MCP servers, agents, or platform resources — for a task. Fetches the live DataRobot catalog directly so results are always current, regardless of third-party search index lag. Also checks the user's own DataRobot instance if DATAROBOT_ENDPOINT is set.","included_files":[],"name":"datarobot-discover","skill_md_contents":"---\nname: datarobot-discover\ndescription: >-\n  Use when the user wants to find DataRobot capabilities — skills, MCP servers,\n  agents, or platform resources — for a task. Fetches the live DataRobot catalog\n  directly so results are always current, regardless of third-party search index\n  lag. Also checks the user's own DataRobot instance if DATAROBOT_ENDPOINT is set.\n---\n\n# Discover DataRobot Resources\n\nFetch DataRobot catalog and present matching resources for the user's\ntask. Covers resource types including Global MCP Server. Bring resources once DataRobot publishes them without skill update.\n\n## Step 1 — Fetch the public catalog\n\n```bash\ncurl -s https://www.datarobot.com/.well-known/ai-catalog.json\n```\n\nAlways fetch this. It contains all publicly available DataRobot resources.\n\n## Step 2 — Fetch the instance catalog (if DATAROBOT_ENDPOINT is set)\n\n```bash\ncurl -s \\\n  -H \"Authorization: Bearer $DATAROBOT_API_TOKEN\" \\\n  \"$DATAROBOT_ENDPOINT/.well-known/ai-catalog.json\"\n```\n\nThis surfaces resources specific to the user's DataRobot deployment — org-scoped\nMCP servers, deployed agents, private tools. If it returns 404, the instance does\nnot publish a catalog yet; skip silently and continue with the public catalog only.\n\n## Step 3 — Merge and present\n\nCombine both result sets. Deduplicate by `identifier`. Then present as a numbered\nlist grouped by resource type:\n\n| `type` value | Label |\n|---|---|\n| `application/ai-skill` | Skill |\n| `application/mcp-server+json` | MCP Server |\n| `application/ai-agent+json` | Agent |\n| anything else | Resource |\n\nFor each entry show: **name**, **type**, **description**, and whether it came from\nthe public catalog or the user's instance. Relevance to the user's task comes\nfirst — don't just dump the full list alphabetically.\n\n## Step 4 — Install guidance (only when the user asks)\n\nNever install or configure anything automatically. When the user picks a result:\n\n**Skill** — install via the DataRobot skills plugin:\n```bash\nnpx ai-agent-skills install <skill-name>\n```\nOr point directly to the `url` field from the catalog entry (the SKILL.md file).\n\n**MCP Server** — show the MCP connector config using the `url` from the catalog:\n```json\n{\n  \"mcpServers\": {\n    \"datarobot\": {\n      \"url\": \"<url from catalog entry>\"\n    }\n  }\n}\n```\n\n**Agent** — show the A2A endpoint from the catalog entry and instruct the user\nto connect it via their agent framework's standard mechanism.\n\n**Other** — show the `url` and `description` from the catalog entry and let the\nuser decide how to proceed.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}