{
  "schemaVersion": "1.0",
  "item": {
    "slug": "knowledge-management",
    "name": "Knowledge Management",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ClaireAICodes/knowledge-management",
    "canonicalUrl": "https://clawhub.ai/ClaireAICodes/knowledge-management",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/knowledge-management",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=knowledge-management",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "index-local.js",
      "package.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/knowledge-management"
    },
    "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/knowledge-management",
    "agentPageUrl": "https://openagent3.xyz/skills/knowledge-management/agent",
    "manifestUrl": "https://openagent3.xyz/skills/knowledge-management/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/knowledge-management/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Knowledge Management Skill (Local Storage)",
        "body": "Organize your OpenClaw memory files into a structured local knowledge base. Automatically parses MEMORY.md and daily memory files, classifies entries by content type, and stores each as a timestamped markdown file in the appropriate folder."
      },
      {
        "title": "Core Commands",
        "body": "km sync [options] - Sync memory entries to local files\nkm classify [options] - Parse and classify without storing (JSON output)\nkm summarize [options] - Generate index files for each content type\nkm cleanup [options] - Remove orphaned files\nkm list_types - List all available content types"
      },
      {
        "title": "Setup",
        "body": "No API keys needed! The skill uses two locations:\n\nInput Workspace: Where MEMORY.md and memory/ daily files are read from.\nOutput Directory: Where organized folders (Research/, Decision/, etc.) are written.\n\nBoth are detected automatically:"
      },
      {
        "title": "Input Workspace (source files)",
        "body": "OPENCLAWORKSPACE environment variable\n--workspace <path> CLI argument\nCurrent working directory (if it contains MEMORY.md)\nDefault: ~/.openclaw/workspace"
      },
      {
        "title": "Output Directory (organized files)",
        "body": "--output-dir <path> CLI argument (relative to workspace or absolute)\nDefault: <workspace>/memory/KM\n\nThe skill will create the output directory and all content-type folders automatically.\n\nIf you want to pre-create:\n\nmkdir -p ~/.openclaw/workspace/memory/KM/{Research,Decision,Insight,Lesson,Pattern,Project,Reference,Tutorial}"
      },
      {
        "title": "Default locations (input at workspace root, output in memory/KM)",
        "body": "# From any directory (workspace auto-detected)\nkm sync --days_back 7 --cleanup"
      },
      {
        "title": "Custom input workspace and output directory",
        "body": "km sync --workspace /custom/input/workspace --output-dir /custom/output/KM --days_back 7"
      },
      {
        "title": "Using environment variables",
        "body": "export OPENCLAWORKSPACE=/custom/input/workspace\nkm sync --output-dir /custom/output/KM --days_back 7"
      },
      {
        "title": "Dry run (preview only)",
        "body": "km sync --dry_run --days_back 1"
      },
      {
        "title": "Classify entries and export JSON",
        "body": "km classify --days_back 3 > entries.json"
      },
      {
        "title": "Generate index files (default: output directory)",
        "body": "km summarize\n# or specify different location\nkm summarize --output_dir ~/some/other/folder"
      },
      {
        "title": "Preview orphan cleanup",
        "body": "km cleanup --dry_run"
      },
      {
        "title": "List content types",
        "body": "km list_types"
      },
      {
        "title": "Storage Structure",
        "body": "Assuming default configuration:\n\nInput workspace: ~/.openclaw/workspace\nOutput directory: ~/.openclaw/workspace/memory/KM\n\n~/.openclaw/workspace/\n├── MEMORY.md                (source file - you edit this)\n├── memory/                  (daily memory files)\n│   ├── 2025-02-11.md\n│   ├── 2025-02-12.md\n│   └── ...\n└── memory/KM/               (organized output by the skill)\n    ├── local-sync-state.json\n    ├── local-sync-log.md\n    ├── Research/\n    │   ├── 20260215T1448_Title_Here_HASH.md\n    │   └── ...\n    ├── Decision/\n    ├── Insight/\n    ├── Lesson/\n    ├── Pattern/\n    ├── Project/\n    ├── Reference/\n    ├── Tutorial/\n    ├── Research_Index.md\n    ├── Decision_Index.md\n    └── ... (other index files)"
      },
      {
        "title": "File Naming",
        "body": "Format: YYYYMMDDTHHMM_Title_With_Underscores_8CHARHASH.md\n\nThe 8-character content hash suffix prevents filename collisions when titles are identical but content differs."
      },
      {
        "title": "File Content (YAML Frontmatter)",
        "body": "---\ntitle: \"Protocol Name\"\ncontent_type: \"Research\"\ndomain: \"OpenClaw\"\ncertainty: \"Verified\"\nimpact: \"Medium\"\nconfidence_score: 8\ntags: [\"AI\", \"Automation\"]\nsource: \"MEMORY.md\"\nsource_file: \"MEMORY.md\"\ndate: \"2026-02-11\"\ncontent_hash: \"e4b30e75d0f5a662\"\n---\n\nEntry body content starts here..."
      },
      {
        "title": "How It Works",
        "body": "Parses MEMORY.md and recent daily memory/*.md files\nClassifies each entry (content type, domain, certainty, impact, tags, confidence)\nComputes content hash for deduplication\nChecks sync state (memory/local-sync-state.json) to skip already synced entries\nWrites to appropriate folder with timestamp + hash filename\nUpdates state mapping (hash → filepath)\nOptional cleanup removes files not in state"
      },
      {
        "title": "Classification Logic",
        "body": "Content Type: Keyword matching (Research, Lesson, Decision, Pattern, Tutorial, Reference, Insight)\nDomain: Contextual inference (AI Models, OpenClaw, Cost, Trading, etc.)\nCertainty: Based on language (Verified, Likely, Speculative, Opinion)\nImpact: Importance indicators (High, Medium, Low, Negligible)\nTags: Auto-extracted from predefined keyword map\nConfidence Score: 1–10 heuristic (source credibility, length, data mentions)\n\nCustomize by editing the EntryClassifier class in index-local.js."
      },
      {
        "title": "State Management",
        "body": "memory/local-sync-state.json maps content hashes to file paths:\n\n{\n  \"e4b30e75d0f5a662\": \"/path/to/Research/202602151440_Title_e4b30e75.md\"\n}\n\nThis enables idempotent syncs and fast duplicate detection.\n\nDo not edit manually unless recovering from corruption."
      },
      {
        "title": "Cron Integration",
        "body": "Automate daily syncs:\n\nopenclaw cron add \\\n  --name \"Daily Knowledge Sync\" \\\n  --cron \"0 5 * * *\" \\\n  --tz \"Asia/Singapore\" \\\n  --session isolated \\\n  --message \"km sync --days_back 7\"\n\nNote: By default, the skill reads MEMORY.md from ~/.openclaw/workspace and writes organized files to ~/.openclaw/workspace/memory/KM. Use --workspace or --output-dir to customize these locations."
      },
      {
        "title": "Troubleshooting",
        "body": "\"km: command not found\"\n\nRun npm link in the skill directory, or add ~/workspace/bin to PATH.\n\nNo entries found\n\nEnsure MEMORY.md uses ## section headers and ### entry titles within recognized sections.\n\nFiles not created\n\nCheck write permissions; run with --verbose.\n\nOld entries not syncing\n\nThey may already be in state. Clear memory/KM/local-sync-state.json to force re-sync (caution: may duplicate files).\n\nDuplicate files\n\nRun km cleanup to remove orphans, then km sync to create missing files.\n\nVersion: 2.0.0\nChanged: 2026-02-15 — Switched from Notion to local storage, added hash suffixes for uniqueness.\nAuthor: Claire (OpenClaw Agent)\nLicense: MIT"
      }
    ],
    "body": "Knowledge Management Skill (Local Storage)\n\nOrganize your OpenClaw memory files into a structured local knowledge base. Automatically parses MEMORY.md and daily memory files, classifies entries by content type, and stores each as a timestamped markdown file in the appropriate folder.\n\nAvailable Tools\nCore Commands\nkm sync [options] - Sync memory entries to local files\nkm classify [options] - Parse and classify without storing (JSON output)\nkm summarize [options] - Generate index files for each content type\nkm cleanup [options] - Remove orphaned files\nkm list_types - List all available content types\nSetup\n\nNo API keys needed! The skill uses two locations:\n\nInput Workspace: Where MEMORY.md and memory/ daily files are read from.\nOutput Directory: Where organized folders (Research/, Decision/, etc.) are written.\n\nBoth are detected automatically:\n\nInput Workspace (source files)\nOPENCLAWORKSPACE environment variable\n--workspace <path> CLI argument\nCurrent working directory (if it contains MEMORY.md)\nDefault: ~/.openclaw/workspace\nOutput Directory (organized files)\n--output-dir <path> CLI argument (relative to workspace or absolute)\nDefault: <workspace>/memory/KM\n\nThe skill will create the output directory and all content-type folders automatically.\n\nIf you want to pre-create:\n\nmkdir -p ~/.openclaw/workspace/memory/KM/{Research,Decision,Insight,Lesson,Pattern,Project,Reference,Tutorial}\n\nUsage Examples\nDefault locations (input at workspace root, output in memory/KM)\n# From any directory (workspace auto-detected)\nkm sync --days_back 7 --cleanup\n\nCustom input workspace and output directory\nkm sync --workspace /custom/input/workspace --output-dir /custom/output/KM --days_back 7\n\nUsing environment variables\nexport OPENCLAWORKSPACE=/custom/input/workspace\nkm sync --output-dir /custom/output/KM --days_back 7\n\nDry run (preview only)\nkm sync --dry_run --days_back 1\n\nClassify entries and export JSON\nkm classify --days_back 3 > entries.json\n\nGenerate index files (default: output directory)\nkm summarize\n# or specify different location\nkm summarize --output_dir ~/some/other/folder\n\nPreview orphan cleanup\nkm cleanup --dry_run\n\nList content types\nkm list_types\n\nStorage Structure\n\nAssuming default configuration:\n\nInput workspace: ~/.openclaw/workspace\nOutput directory: ~/.openclaw/workspace/memory/KM\n~/.openclaw/workspace/\n├── MEMORY.md                (source file - you edit this)\n├── memory/                  (daily memory files)\n│   ├── 2025-02-11.md\n│   ├── 2025-02-12.md\n│   └── ...\n└── memory/KM/               (organized output by the skill)\n    ├── local-sync-state.json\n    ├── local-sync-log.md\n    ├── Research/\n    │   ├── 20260215T1448_Title_Here_HASH.md\n    │   └── ...\n    ├── Decision/\n    ├── Insight/\n    ├── Lesson/\n    ├── Pattern/\n    ├── Project/\n    ├── Reference/\n    ├── Tutorial/\n    ├── Research_Index.md\n    ├── Decision_Index.md\n    └── ... (other index files)\n\nFile Naming\n\nFormat: YYYYMMDDTHHMM_Title_With_Underscores_8CHARHASH.md\n\nThe 8-character content hash suffix prevents filename collisions when titles are identical but content differs.\n\nFile Content (YAML Frontmatter)\n---\ntitle: \"Protocol Name\"\ncontent_type: \"Research\"\ndomain: \"OpenClaw\"\ncertainty: \"Verified\"\nimpact: \"Medium\"\nconfidence_score: 8\ntags: [\"AI\", \"Automation\"]\nsource: \"MEMORY.md\"\nsource_file: \"MEMORY.md\"\ndate: \"2026-02-11\"\ncontent_hash: \"e4b30e75d0f5a662\"\n---\n\nEntry body content starts here...\n\nHow It Works\nParses MEMORY.md and recent daily memory/*.md files\nClassifies each entry (content type, domain, certainty, impact, tags, confidence)\nComputes content hash for deduplication\nChecks sync state (memory/local-sync-state.json) to skip already synced entries\nWrites to appropriate folder with timestamp + hash filename\nUpdates state mapping (hash → filepath)\nOptional cleanup removes files not in state\nClassification Logic\nContent Type: Keyword matching (Research, Lesson, Decision, Pattern, Tutorial, Reference, Insight)\nDomain: Contextual inference (AI Models, OpenClaw, Cost, Trading, etc.)\nCertainty: Based on language (Verified, Likely, Speculative, Opinion)\nImpact: Importance indicators (High, Medium, Low, Negligible)\nTags: Auto-extracted from predefined keyword map\nConfidence Score: 1–10 heuristic (source credibility, length, data mentions)\n\nCustomize by editing the EntryClassifier class in index-local.js.\n\nState Management\n\nmemory/local-sync-state.json maps content hashes to file paths:\n\n{\n  \"e4b30e75d0f5a662\": \"/path/to/Research/202602151440_Title_e4b30e75.md\"\n}\n\n\nThis enables idempotent syncs and fast duplicate detection.\n\nDo not edit manually unless recovering from corruption.\n\nCron Integration\n\nAutomate daily syncs:\n\nopenclaw cron add \\\n  --name \"Daily Knowledge Sync\" \\\n  --cron \"0 5 * * *\" \\\n  --tz \"Asia/Singapore\" \\\n  --session isolated \\\n  --message \"km sync --days_back 7\"\n\n\nNote: By default, the skill reads MEMORY.md from ~/.openclaw/workspace and writes organized files to ~/.openclaw/workspace/memory/KM. Use --workspace or --output-dir to customize these locations.\n\nTroubleshooting\n\n\"km: command not found\"\n\nRun npm link in the skill directory, or add ~/workspace/bin to PATH.\n\nNo entries found\n\nEnsure MEMORY.md uses ## section headers and ### entry titles within recognized sections.\n\nFiles not created\n\nCheck write permissions; run with --verbose.\n\nOld entries not syncing\n\nThey may already be in state. Clear memory/KM/local-sync-state.json to force re-sync (caution: may duplicate files).\n\nDuplicate files\n\nRun km cleanup to remove orphans, then km sync to create missing files.\n\nVersion: 2.0.0 Changed: 2026-02-15 — Switched from Notion to local storage, added hash suffixes for uniqueness. Author: Claire (OpenClaw Agent) License: MIT"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ClaireAICodes/knowledge-management",
    "publisherUrl": "https://clawhub.ai/ClaireAICodes/knowledge-management",
    "owner": "ClaireAICodes",
    "version": "2.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/knowledge-management",
    "downloadUrl": "https://openagent3.xyz/downloads/knowledge-management",
    "agentUrl": "https://openagent3.xyz/skills/knowledge-management/agent",
    "manifestUrl": "https://openagent3.xyz/skills/knowledge-management/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/knowledge-management/agent.md"
  }
}