{
  "schemaVersion": "1.0",
  "item": {
    "slug": "percept-summarize",
    "name": "Percept Summarize",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/jarvis563/percept-summarize",
    "canonicalUrl": "https://clawhub.ai/jarvis563/percept-summarize",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/percept-summarize",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=percept-summarize",
    "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/percept-summarize"
    },
    "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/percept-summarize",
    "agentPageUrl": "https://openagent3.xyz/skills/percept-summarize/agent",
    "manifestUrl": "https://openagent3.xyz/skills/percept-summarize/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/percept-summarize/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": "percept-summarize",
        "body": "Automatic conversation summaries with entity extraction and relationship mapping."
      },
      {
        "title": "What it does",
        "body": "When a conversation ends (60 seconds of silence), Percept generates an AI-powered summary with extracted entities (people, companies, topics), action items, and relationship connections. Summaries are stored locally and searchable."
      },
      {
        "title": "When to use",
        "body": "User asks \"what did we talk about?\" or \"summarize that meeting\"\nUser wants meeting notes or action items from a conversation\nAgent needs context from a recent conversation"
      },
      {
        "title": "Requirements",
        "body": "percept-listen skill installed and running\nOpenClaw agent accessible via CLI (used for LLM summarization)"
      },
      {
        "title": "How it works",
        "body": "Conversation ends (60s silence timeout)\nPercept builds a speaker-tagged transcript\nSends transcript to OpenClaw for AI summarization\nExtracts entities (people, orgs, topics) and relationships\nStores summary + entities in SQLite\nEntities linked via relationship graph (works_on, client_of, mentioned_with)"
      },
      {
        "title": "Entity resolution",
        "body": "5-tier cascade for identifying entities:\n\nExact match (confidence 1.0)\nFuzzy match (0.8) — handles typos, nicknames\nContextual/graph (0.7) — uses relationship connections\nRecency (0.6) — recently mentioned entities ranked higher\nSemantic search (0.5) — vector similarity via LanceDB"
      },
      {
        "title": "Querying summaries",
        "body": "Summaries are searchable via the Percept dashboard (port 8960) or SQLite directly:\n\nSELECT * FROM conversations WHERE summary LIKE '%action items%' ORDER BY end_time DESC;\n\nFull-text search via FTS5:\n\nSELECT * FROM utterances_fts WHERE utterances_fts MATCH 'project deadline';"
      },
      {
        "title": "Data retention",
        "body": "Utterances: 30 days\nSummaries: 90 days\nRelationships: 180 days\nSpeaker profiles: never expire"
      },
      {
        "title": "Links",
        "body": "GitHub: https://github.com/GetPercept/percept"
      }
    ],
    "body": "percept-summarize\n\nAutomatic conversation summaries with entity extraction and relationship mapping.\n\nWhat it does\n\nWhen a conversation ends (60 seconds of silence), Percept generates an AI-powered summary with extracted entities (people, companies, topics), action items, and relationship connections. Summaries are stored locally and searchable.\n\nWhen to use\nUser asks \"what did we talk about?\" or \"summarize that meeting\"\nUser wants meeting notes or action items from a conversation\nAgent needs context from a recent conversation\nRequirements\npercept-listen skill installed and running\nOpenClaw agent accessible via CLI (used for LLM summarization)\nHow it works\nConversation ends (60s silence timeout)\nPercept builds a speaker-tagged transcript\nSends transcript to OpenClaw for AI summarization\nExtracts entities (people, orgs, topics) and relationships\nStores summary + entities in SQLite\nEntities linked via relationship graph (works_on, client_of, mentioned_with)\nEntity resolution\n\n5-tier cascade for identifying entities:\n\nExact match (confidence 1.0)\nFuzzy match (0.8) — handles typos, nicknames\nContextual/graph (0.7) — uses relationship connections\nRecency (0.6) — recently mentioned entities ranked higher\nSemantic search (0.5) — vector similarity via LanceDB\nQuerying summaries\n\nSummaries are searchable via the Percept dashboard (port 8960) or SQLite directly:\n\nSELECT * FROM conversations WHERE summary LIKE '%action items%' ORDER BY end_time DESC;\n\n\nFull-text search via FTS5:\n\nSELECT * FROM utterances_fts WHERE utterances_fts MATCH 'project deadline';\n\nData retention\nUtterances: 30 days\nSummaries: 90 days\nRelationships: 180 days\nSpeaker profiles: never expire\nLinks\nGitHub: https://github.com/GetPercept/percept"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jarvis563/percept-summarize",
    "publisherUrl": "https://clawhub.ai/jarvis563/percept-summarize",
    "owner": "jarvis563",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/percept-summarize",
    "downloadUrl": "https://openagent3.xyz/downloads/percept-summarize",
    "agentUrl": "https://openagent3.xyz/skills/percept-summarize/agent",
    "manifestUrl": "https://openagent3.xyz/skills/percept-summarize/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/percept-summarize/agent.md"
  }
}