{
  "schemaVersion": "1.0",
  "item": {
    "slug": "brain-search",
    "name": "Brain Search",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ryandeangraves/brain-search",
    "canonicalUrl": "https://clawhub.ai/ryandeangraves/brain-search",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/brain-search",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=brain-search",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/brain-search"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/brain-search",
    "agentPageUrl": "https://openagent3.xyz/skills/brain-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/brain-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/brain-search/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "CRITICAL RULE — NO FABRICATION",
        "body": "You MUST actually execute every curl command using your shell/exec tool. Read the real HTTP response. NEVER generate a fake response, placeholder ID, or simulated output. If the API call fails, report the actual error to Boss Man. If you cannot execute shell commands right now, say so — do not pretend you ran them."
      },
      {
        "title": "Purpose",
        "body": "Search and interact with Frank's Second Brain — the persistent knowledge base that stores conversation logs, research, journal entries, job results, and long-term memory."
      },
      {
        "title": "When to Use",
        "body": "Boss Man asks \"what did we talk about on Monday?\" or \"find that research on X\"\nYou need context from previous sessions or completed jobs\nLogging noteworthy activity outside of normal Telegram conversation\nChecking job queue status or delegating tasks to sub-agents\nCreating, updating, or managing tasks on the Kanban board"
      },
      {
        "title": "API Base",
        "body": "https://second-brain-chi-umber.vercel.app\n\nAll requests require header: x-api-key: frank-sb-2026"
      },
      {
        "title": "Search Entries",
        "body": "Find past conversations, research, notes, and logged activity.\n\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/entries?q=SEARCH_TERM&limit=10\" \\\n  -H \"x-api-key: frank-sb-2026\""
      },
      {
        "title": "Search with Tag Filter",
        "body": "curl -s \"https://second-brain-chi-umber.vercel.app/api/entries?q=SEARCH_TERM&tag=TAG_NAME&limit=10\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nCommon tags: daily-journal, telegram, research, market-analysis, advisory-council"
      },
      {
        "title": "Create Entry",
        "body": "Store a new knowledge entry (research results, analysis, etc.).\n\ncurl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/entries\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"title\": \"Entry Title\",\n    \"content\": \"Full content here\",\n    \"tags\": [\"tag1\", \"tag2\"],\n    \"source\": \"telegram-frank\"\n  }'"
      },
      {
        "title": "Log Activity",
        "body": "Record noteworthy events, decisions, or results.\n\ncurl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/log\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"action\": \"ACTION_TYPE\",\n    \"summary\": \"Brief description of what happened\",\n    \"source\": \"telegram-frank\",\n    \"details\": {}\n  }'"
      },
      {
        "title": "Create a Task",
        "body": "curl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/tasks\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"title\": \"Task Title\",\n    \"description\": \"What needs to be done\",\n    \"status\": \"backlog\",\n    \"priority\": \"medium\",\n    \"tags\": [\"tag1\"]\n  }'\n\nValid statuses: backlog, in_progress, done\nValid priorities: low, medium, high\nNote: project_id is validated — create projects first via POST /api/projects before referencing them."
      },
      {
        "title": "Update Task Status (Move on Kanban)",
        "body": "curl -s -X PATCH \"https://second-brain-chi-umber.vercel.app/api/tasks/TASK_ID\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"status\": \"in_progress\"}'"
      },
      {
        "title": "List Tasks",
        "body": "curl -s \"https://second-brain-chi-umber.vercel.app/api/tasks?status=backlog&limit=20\" \\\n  -H \"x-api-key: frank-sb-2026\""
      },
      {
        "title": "Check Activity Log",
        "body": "curl -s \"https://second-brain-chi-umber.vercel.app/api/activity\" \\\n  -H \"x-api-key: frank-sb-2026\""
      },
      {
        "title": "Upload a File",
        "body": "curl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/upload\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -F \"file=@/path/to/file.jpg\" \\\n  -F \"title=My File\" \\\n  -F \"tags=upload,test\"\n\nOptional fields: entry_id, title, tags, description. If no entry_id, auto-creates a file type entry."
      },
      {
        "title": "List Files",
        "body": "curl -s \"https://second-brain-chi-umber.vercel.app/api/files?limit=50\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nFilters: ?category=image|video|audio|document, ?stats=true"
      },
      {
        "title": "List Attachments on an Entry",
        "body": "curl -s \"https://second-brain-chi-umber.vercel.app/api/entries/ENTRY_ID/attachments\" \\\n  -H \"x-api-key: frank-sb-2026\""
      },
      {
        "title": "Delete a File",
        "body": "curl -s -X DELETE \"https://second-brain-chi-umber.vercel.app/api/attachments/ATTACHMENT_ID\" \\\n  -H \"x-api-key: frank-sb-2026\""
      },
      {
        "title": "Create Job (Delegate)",
        "body": "curl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/jobs\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"type\": \"JOB_TYPE\",\n    \"title\": \"Job Title\",\n    \"description\": \"Detailed instructions\",\n    \"priority\": \"normal\",\n    \"tags\": [\"TAG\"],\n    \"input\": {}\n  }'\n\nRouting Tags for Sub-Agents\n\nTagsPicked Up ByBest For[\"claude\", \"code\"]Claude Opus 4.5Coding, architecture, debugging[\"claude\", \"write\"]Claude Sonnet 4.5LinkedIn posts, articles, email drafts(no claude tag)MiniMax M2.5Research, analysis, batch ops (cheapest)"
      },
      {
        "title": "Check Job Status",
        "body": "curl -s \"https://second-brain-chi-umber.vercel.app/api/jobs/JOB_ID\" \\\n  -H \"x-api-key: frank-sb-2026\""
      },
      {
        "title": "List Running Jobs",
        "body": "curl -s \"https://second-brain-chi-umber.vercel.app/api/jobs?status=running&stats=true\" \\\n  -H \"x-api-key: frank-sb-2026\""
      },
      {
        "title": "Rules",
        "body": "EXECUTE EVERY CURL COMMAND FOR REAL — use your shell/exec tool. Never simulate or fabricate API responses.\nAlways include x-api-key: frank-sb-2026 header\nAlways report the actual HTTP response back to Boss Man\nIf an API call fails, show the error — don't make up a success message\nBoss Man watches the /jobs page and Kanban board live — he will see if you fake it\nWhen delegating: create job as pending → sub-agent picks it up → updates to running → completed\nFor multi-step tasks, ALWAYS use the job queue rather than doing everything inline\nLog activity for anything noteworthy that happens outside of normal Telegram chat"
      }
    ],
    "body": "Skill: brain-search\nCRITICAL RULE — NO FABRICATION\n\nYou MUST actually execute every curl command using your shell/exec tool. Read the real HTTP response. NEVER generate a fake response, placeholder ID, or simulated output. If the API call fails, report the actual error to Boss Man. If you cannot execute shell commands right now, say so — do not pretend you ran them.\n\nPurpose\n\nSearch and interact with Frank's Second Brain — the persistent knowledge base that stores conversation logs, research, journal entries, job results, and long-term memory.\n\nWhen to Use\nBoss Man asks \"what did we talk about on Monday?\" or \"find that research on X\"\nYou need context from previous sessions or completed jobs\nLogging noteworthy activity outside of normal Telegram conversation\nChecking job queue status or delegating tasks to sub-agents\nCreating, updating, or managing tasks on the Kanban board\nAPI Base\nhttps://second-brain-chi-umber.vercel.app\n\n\nAll requests require header: x-api-key: frank-sb-2026\n\nSearch Entries\n\nFind past conversations, research, notes, and logged activity.\n\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/entries?q=SEARCH_TERM&limit=10\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nSearch with Tag Filter\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/entries?q=SEARCH_TERM&tag=TAG_NAME&limit=10\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\n\nCommon tags: daily-journal, telegram, research, market-analysis, advisory-council\n\nCreate Entry\n\nStore a new knowledge entry (research results, analysis, etc.).\n\ncurl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/entries\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"title\": \"Entry Title\",\n    \"content\": \"Full content here\",\n    \"tags\": [\"tag1\", \"tag2\"],\n    \"source\": \"telegram-frank\"\n  }'\n\nLog Activity\n\nRecord noteworthy events, decisions, or results.\n\ncurl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/log\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"action\": \"ACTION_TYPE\",\n    \"summary\": \"Brief description of what happened\",\n    \"source\": \"telegram-frank\",\n    \"details\": {}\n  }'\n\nKanban Board — Tasks\nCreate a Task\ncurl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/tasks\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"title\": \"Task Title\",\n    \"description\": \"What needs to be done\",\n    \"status\": \"backlog\",\n    \"priority\": \"medium\",\n    \"tags\": [\"tag1\"]\n  }'\n\n\nValid statuses: backlog, in_progress, done Valid priorities: low, medium, high Note: project_id is validated — create projects first via POST /api/projects before referencing them.\n\nUpdate Task Status (Move on Kanban)\ncurl -s -X PATCH \"https://second-brain-chi-umber.vercel.app/api/tasks/TASK_ID\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"status\": \"in_progress\"}'\n\nList Tasks\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/tasks?status=backlog&limit=20\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nCheck Activity Log\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/activity\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nFile Storage\nUpload a File\ncurl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/upload\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -F \"file=@/path/to/file.jpg\" \\\n  -F \"title=My File\" \\\n  -F \"tags=upload,test\"\n\n\nOptional fields: entry_id, title, tags, description. If no entry_id, auto-creates a file type entry.\n\nList Files\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/files?limit=50\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\n\nFilters: ?category=image|video|audio|document, ?stats=true\n\nList Attachments on an Entry\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/entries/ENTRY_ID/attachments\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nDelete a File\ncurl -s -X DELETE \"https://second-brain-chi-umber.vercel.app/api/attachments/ATTACHMENT_ID\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nJob Queue (Delegate to Sub-Agents)\nCreate Job (Delegate)\ncurl -s -X POST \"https://second-brain-chi-umber.vercel.app/api/jobs\" \\\n  -H \"x-api-key: frank-sb-2026\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"type\": \"JOB_TYPE\",\n    \"title\": \"Job Title\",\n    \"description\": \"Detailed instructions\",\n    \"priority\": \"normal\",\n    \"tags\": [\"TAG\"],\n    \"input\": {}\n  }'\n\nRouting Tags for Sub-Agents\nTags\tPicked Up By\tBest For\n[\"claude\", \"code\"]\tClaude Opus 4.5\tCoding, architecture, debugging\n[\"claude\", \"write\"]\tClaude Sonnet 4.5\tLinkedIn posts, articles, email drafts\n(no claude tag)\tMiniMax M2.5\tResearch, analysis, batch ops (cheapest)\nCheck Job Status\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/jobs/JOB_ID\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nList Running Jobs\ncurl -s \"https://second-brain-chi-umber.vercel.app/api/jobs?status=running&stats=true\" \\\n  -H \"x-api-key: frank-sb-2026\"\n\nRules\nEXECUTE EVERY CURL COMMAND FOR REAL — use your shell/exec tool. Never simulate or fabricate API responses.\nAlways include x-api-key: frank-sb-2026 header\nAlways report the actual HTTP response back to Boss Man\nIf an API call fails, show the error — don't make up a success message\nBoss Man watches the /jobs page and Kanban board live — he will see if you fake it\nWhen delegating: create job as pending → sub-agent picks it up → updates to running → completed\nFor multi-step tasks, ALWAYS use the job queue rather than doing everything inline\nLog activity for anything noteworthy that happens outside of normal Telegram chat"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ryandeangraves/brain-search",
    "publisherUrl": "https://clawhub.ai/ryandeangraves/brain-search",
    "owner": "ryandeangraves",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/brain-search",
    "downloadUrl": "https://openagent3.xyz/downloads/brain-search",
    "agentUrl": "https://openagent3.xyz/skills/brain-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/brain-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/brain-search/agent.md"
  }
}