{ "schemaVersion": "1.0", "item": { "slug": "crowterminal", "name": "CrowTerminal", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/WillNigri/crowterminal", "canonicalUrl": "https://clawhub.ai/WillNigri/crowterminal", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/crowterminal", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=crowterminal", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "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/crowterminal" }, "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/crowterminal", "agentPageUrl": "https://openagent3.xyz/skills/crowterminal/agent", "manifestUrl": "https://openagent3.xyz/skills/crowterminal/agent.json", "briefUrl": "https://openagent3.xyz/skills/crowterminal/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": "CrowTerminal - External Brain for AI Agents", "body": "\"Agents are ephemeral. We are persistent.\"\n\nWhile your agent stores 10-50 lines of context, CrowTerminal stores 6 months of versioned history for each creator." }, { "title": "What It Does", "body": "CrowTerminal is a persistent memory layer for AI agents working with influencers/creators:\n\nVersioned Memory - Track what works across sessions (hook patterns, engagement, posting times)\nPattern Detection - See trends over months, not single data points\nEngagement Analysis - Know what configuration performed best historically\nValidation - Check if your changes will repeat past mistakes\nData Ingestion - Push platform data we can't access (retention curves, demographics)\nLLM-Native API - Schema discovery, semantic field aliases, natural language queries" }, { "title": "1. Get API Key (Self-Registration)", "body": "curl -X POST \"https://api.crowterminal.com/api/agent/register\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"agentName\": \"OpenClaw\", \"agentDescription\": \"My personal AI agent\"}'\n\nSave the returned API key as CROWTERMINAL_API_KEY." }, { "title": "2. Read Creator Memory", "body": "curl https://api.crowterminal.com/api/agent/memory/client_123 \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\"\n\nReturns versioned skill data:\n\n{\n \"version\": 47,\n \"skill\": {\n \"primaryNiche\": \"fitness\",\n \"hookPatterns\": [\"confession\", \"transformation\"],\n \"avgEngagement\": 4.2,\n \"bestPostingTimes\": [{\"day\": 2, \"hour\": 7, \"score\": 0.89}]\n }\n}" }, { "title": "Schema Discovery (LLM-Friendly)", "body": "These endpoints help agents understand what data is available without hardcoding field names:\n\nEndpointDescriptionGET /memory/schemaFull schema with field descriptions, types, and semantic aliasesGET /memory/schema/:categorySchema filtered by category (content, performance, timing, audience, history)POST /memory/resolveResolve natural language queries to field names\n\nExample: Discover available fields\n\ncurl https://api.crowterminal.com/api/agent/memory/schema \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\"\n\nReturns field definitions with semantic aliases:\n\n{\n \"fields\": {\n \"avgEngagement\": {\n \"type\": \"number\",\n \"description\": \"Average engagement rate\",\n \"aliases\": [\"engagement\", \"engagement rate\", \"interaction rate\"],\n \"category\": \"performance\"\n }\n }\n}" }, { "title": "Smart Query (Natural Language)", "body": "Query data using natural language instead of exact field names:\n\nEndpointDescriptionPOST /memory/:clientId/queryQuery with natural language (\"engagement and hooks\")GET /memory/:clientId/overviewHuman-readable summary of the creatorGET /memory/:clientId/changesNatural language summary of recent changesGET /memory/:clientId/insightsAI-friendly performance insights\n\nExample: Natural language query\n\ncurl -X POST \"https://api.crowterminal.com/api/agent/memory/client_123/query\" \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"query\": \"engagement and hooks\"}'\n\nReturns matched data:\n\n{\n \"results\": {\n \"matchedFields\": [\"avgEngagement\", \"hookPatterns\"],\n \"data\": {\n \"avgEngagement\": 4.2,\n \"hookPatterns\": [\"confession\", \"POV\"]\n },\n \"context\": \"avgEngagement: Average engagement rate; hookPatterns: Effective hook types\"\n }\n}\n\nExample: Get natural language overview\n\ncurl https://api.crowterminal.com/api/agent/memory/client_123/overview \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\"\n\nReturns:\n\n{\n \"overview\": \"FitnessGuru is a fitness creator averaging 125,000 views per video with 4.2% engagement and is currently growing. Their best-performing hooks are: confession, transformation, POV.\"\n}" }, { "title": "Memory Layer (Core)", "body": "EndpointDescriptionGET /memory/:clientIdCurrent skill versionGET /memory/:clientId/versionsVersion historyGET /memory/:clientId/diff?from=5&to=10Compare versionsGET /memory/:clientId/pattern?field=engagementTrack field over time with trend analysisPOST /memory/:clientId/validateCheck before changingPOST /memory/:clientId/engagement-analysisTHE KILLER ENDPOINT" }, { "title": "The Killer Endpoint: Engagement Analysis", "body": "Send your current learnings, get back what configuration performed best:\n\ncurl -X POST \"https://api.crowterminal.com/api/agent/memory/client_123/engagement-analysis\" \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"agentMd\": {\n \"hookPatterns\": [\"confession\"],\n \"contentStyle\": \"casual\"\n }\n }'\n\nReturns:\n\n{\n \"overallStats\": {\n \"peakEngagement\": 6.2,\n \"yourSimilarityToTop\": \"65%\"\n },\n \"recommendations\": [\n \"Change hookPatterns to [\\\"POV\\\",\\\"confession\\\"] (+51% potential)\"\n ]\n}" }, { "title": "Data Ingestion (Push Your Data)", "body": "Push platform data we can't access via API:\n\ncurl -X POST \"https://api.crowterminal.com/api/agent/data/ingest\" \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"clientId\": \"client_123\",\n \"platform\": \"TIKTOK\",\n \"dataType\": \"retention\",\n \"data\": {\n \"retentionCurve\": [100, 95, 88, 75, 60, 45, 30],\n \"avgWatchTime\": 12.5\n }\n }'" }, { "title": "Webhooks (Async Notifications)", "body": "curl -X POST \"https://api.crowterminal.com/api/agent/webhooks\" \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"url\": \"https://your-server.com/webhook\",\n \"events\": [\"skill.updated\", \"data.ingested\"]\n }'" }, { "title": "Service Status (No Auth)", "body": "curl https://api.crowterminal.com/api/agent/status" }, { "title": "Sandbox (Test Without Auth)", "body": "Test endpoints without affecting real data:\n\nMemory & Schema:\n\nGET /api/agent/sandbox/client - Mock client data\nGET /api/agent/sandbox/memory - Mock memory/skill\nGET /api/agent/sandbox/schema - Schema discovery\nPOST /api/agent/sandbox/resolve - Resolve field aliases\n\nSmart Query:\n\nPOST /api/agent/sandbox/query - Natural language queries\nGET /api/agent/sandbox/overview - Creator overview\nGET /api/agent/sandbox/changes - Recent changes summary\nGET /api/agent/sandbox/insights - Performance insights\n\nAnalysis:\n\nPOST /api/agent/sandbox/validate - Validate changes\nPOST /api/agent/sandbox/engagement-analysis - Engagement analysis\nPOST /api/agent/sandbox/ingest - Data ingestion" }, { "title": "Why Use CrowTerminal?", "body": "Your agent learns → forgets → relearns - We remember\nOne bad video ≠ pattern change - We track across versions\nData you can't get via API - We accept it via ingestion\nBYOK - Use your own LLM, we just provide context\nLLM-Native - No hardcoding field names, use natural language queries\nSelf-Documenting - Schema endpoint tells you what data exists" }, { "title": "Pricing", "body": "FREE during beta. We want agents to test and give feedback.\n\nTierPriceMemory Read/WriteFREEData IngestionFREEBYOK (your LLM)FREEFull ServiceFREE" }, { "title": "Documentation", "body": "Full Docs: https://crowterminal.com/llms.txt\nMCP Manifest: https://crowterminal.com/.well-known/mcp.json\nOpenAPI: https://api.crowterminal.com/api/docs.json\nSDKs: Python (pip install crowterminal), TypeScript (npm install crowterminal)" }, { "title": "Support", "body": "Email: agents@crowterminal.com\nGitHub: https://github.com/WillNigri/FluxOps\n\n\"Your agent's external hard drive. Because context windows aren't long-term memory.\"" } ], "body": "CrowTerminal - External Brain for AI Agents\n\n\"Agents are ephemeral. We are persistent.\"\n\nWhile your agent stores 10-50 lines of context, CrowTerminal stores 6 months of versioned history for each creator.\n\nWhat It Does\n\nCrowTerminal is a persistent memory layer for AI agents working with influencers/creators:\n\nVersioned Memory - Track what works across sessions (hook patterns, engagement, posting times)\nPattern Detection - See trends over months, not single data points\nEngagement Analysis - Know what configuration performed best historically\nValidation - Check if your changes will repeat past mistakes\nData Ingestion - Push platform data we can't access (retention curves, demographics)\nLLM-Native API - Schema discovery, semantic field aliases, natural language queries\nQuick Start\n1. Get API Key (Self-Registration)\ncurl -X POST \"https://api.crowterminal.com/api/agent/register\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"agentName\": \"OpenClaw\", \"agentDescription\": \"My personal AI agent\"}'\n\n\nSave the returned API key as CROWTERMINAL_API_KEY.\n\n2. Read Creator Memory\ncurl https://api.crowterminal.com/api/agent/memory/client_123 \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\"\n\n\nReturns versioned skill data:\n\n{\n \"version\": 47,\n \"skill\": {\n \"primaryNiche\": \"fitness\",\n \"hookPatterns\": [\"confession\", \"transformation\"],\n \"avgEngagement\": 4.2,\n \"bestPostingTimes\": [{\"day\": 2, \"hour\": 7, \"score\": 0.89}]\n }\n}\n\nKey Endpoints\nSchema Discovery (LLM-Friendly)\n\nThese endpoints help agents understand what data is available without hardcoding field names:\n\nEndpoint\tDescription\nGET /memory/schema\tFull schema with field descriptions, types, and semantic aliases\nGET /memory/schema/:category\tSchema filtered by category (content, performance, timing, audience, history)\nPOST /memory/resolve\tResolve natural language queries to field names\n\nExample: Discover available fields\n\ncurl https://api.crowterminal.com/api/agent/memory/schema \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\"\n\n\nReturns field definitions with semantic aliases:\n\n{\n \"fields\": {\n \"avgEngagement\": {\n \"type\": \"number\",\n \"description\": \"Average engagement rate\",\n \"aliases\": [\"engagement\", \"engagement rate\", \"interaction rate\"],\n \"category\": \"performance\"\n }\n }\n}\n\nSmart Query (Natural Language)\n\nQuery data using natural language instead of exact field names:\n\nEndpoint\tDescription\nPOST /memory/:clientId/query\tQuery with natural language (\"engagement and hooks\")\nGET /memory/:clientId/overview\tHuman-readable summary of the creator\nGET /memory/:clientId/changes\tNatural language summary of recent changes\nGET /memory/:clientId/insights\tAI-friendly performance insights\n\nExample: Natural language query\n\ncurl -X POST \"https://api.crowterminal.com/api/agent/memory/client_123/query\" \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"query\": \"engagement and hooks\"}'\n\n\nReturns matched data:\n\n{\n \"results\": {\n \"matchedFields\": [\"avgEngagement\", \"hookPatterns\"],\n \"data\": {\n \"avgEngagement\": 4.2,\n \"hookPatterns\": [\"confession\", \"POV\"]\n },\n \"context\": \"avgEngagement: Average engagement rate; hookPatterns: Effective hook types\"\n }\n}\n\n\nExample: Get natural language overview\n\ncurl https://api.crowterminal.com/api/agent/memory/client_123/overview \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\"\n\n\nReturns:\n\n{\n \"overview\": \"FitnessGuru is a fitness creator averaging 125,000 views per video with 4.2% engagement and is currently growing. Their best-performing hooks are: confession, transformation, POV.\"\n}\n\nMemory Layer (Core)\nEndpoint\tDescription\nGET /memory/:clientId\tCurrent skill version\nGET /memory/:clientId/versions\tVersion history\nGET /memory/:clientId/diff?from=5&to=10\tCompare versions\nGET /memory/:clientId/pattern?field=engagement\tTrack field over time with trend analysis\nPOST /memory/:clientId/validate\tCheck before changing\nPOST /memory/:clientId/engagement-analysis\tTHE KILLER ENDPOINT\nThe Killer Endpoint: Engagement Analysis\n\nSend your current learnings, get back what configuration performed best:\n\ncurl -X POST \"https://api.crowterminal.com/api/agent/memory/client_123/engagement-analysis\" \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"agentMd\": {\n \"hookPatterns\": [\"confession\"],\n \"contentStyle\": \"casual\"\n }\n }'\n\n\nReturns:\n\n{\n \"overallStats\": {\n \"peakEngagement\": 6.2,\n \"yourSimilarityToTop\": \"65%\"\n },\n \"recommendations\": [\n \"Change hookPatterns to [\\\"POV\\\",\\\"confession\\\"] (+51% potential)\"\n ]\n}\n\nData Ingestion (Push Your Data)\n\nPush platform data we can't access via API:\n\ncurl -X POST \"https://api.crowterminal.com/api/agent/data/ingest\" \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"clientId\": \"client_123\",\n \"platform\": \"TIKTOK\",\n \"dataType\": \"retention\",\n \"data\": {\n \"retentionCurve\": [100, 95, 88, 75, 60, 45, 30],\n \"avgWatchTime\": 12.5\n }\n }'\n\nWebhooks (Async Notifications)\ncurl -X POST \"https://api.crowterminal.com/api/agent/webhooks\" \\\n -H \"Authorization: Bearer $CROWTERMINAL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"url\": \"https://your-server.com/webhook\",\n \"events\": [\"skill.updated\", \"data.ingested\"]\n }'\n\nService Status (No Auth)\ncurl https://api.crowterminal.com/api/agent/status\n\nSandbox (Test Without Auth)\n\nTest endpoints without affecting real data:\n\nMemory & Schema:\n\nGET /api/agent/sandbox/client - Mock client data\nGET /api/agent/sandbox/memory - Mock memory/skill\nGET /api/agent/sandbox/schema - Schema discovery\nPOST /api/agent/sandbox/resolve - Resolve field aliases\n\nSmart Query:\n\nPOST /api/agent/sandbox/query - Natural language queries\nGET /api/agent/sandbox/overview - Creator overview\nGET /api/agent/sandbox/changes - Recent changes summary\nGET /api/agent/sandbox/insights - Performance insights\n\nAnalysis:\n\nPOST /api/agent/sandbox/validate - Validate changes\nPOST /api/agent/sandbox/engagement-analysis - Engagement analysis\nPOST /api/agent/sandbox/ingest - Data ingestion\nWhy Use CrowTerminal?\nYour agent learns → forgets → relearns - We remember\nOne bad video ≠ pattern change - We track across versions\nData you can't get via API - We accept it via ingestion\nBYOK - Use your own LLM, we just provide context\nLLM-Native - No hardcoding field names, use natural language queries\nSelf-Documenting - Schema endpoint tells you what data exists\nPricing\n\nFREE during beta. We want agents to test and give feedback.\n\nTier\tPrice\nMemory Read/Write\tFREE\nData Ingestion\tFREE\nBYOK (your LLM)\tFREE\nFull Service\tFREE\nDocumentation\nFull Docs: https://crowterminal.com/llms.txt\nMCP Manifest: https://crowterminal.com/.well-known/mcp.json\nOpenAPI: https://api.crowterminal.com/api/docs.json\nSDKs: Python (pip install crowterminal), TypeScript (npm install crowterminal)\nSupport\nEmail: agents@crowterminal.com\nGitHub: https://github.com/WillNigri/FluxOps\n\n\"Your agent's external hard drive. Because context windows aren't long-term memory.\"" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/WillNigri/crowterminal", "publisherUrl": "https://clawhub.ai/WillNigri/crowterminal", "owner": "WillNigri", "version": "2.3.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/crowterminal", "downloadUrl": "https://openagent3.xyz/downloads/crowterminal", "agentUrl": "https://openagent3.xyz/skills/crowterminal/agent", "manifestUrl": "https://openagent3.xyz/skills/crowterminal/agent.json", "briefUrl": "https://openagent3.xyz/skills/crowterminal/agent.md" } }