{
  "schemaVersion": "1.0",
  "item": {
    "slug": "2026-02-10-clawhub-clawvault-1-5-1",
    "name": "2026 02 10 Clawhub Clawvault 1.5.1",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/pin-alt/2026-02-10-clawhub-clawvault-1-5-1",
    "canonicalUrl": "https://clawhub.ai/pin-alt/2026-02-10-clawhub-clawvault-1-5-1",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/2026-02-10-clawhub-clawvault-1-5-1",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=2026-02-10-clawhub-clawvault-1-5-1",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "bin/clawvault.js",
      "CHANGELOG.md",
      "dist/chunk-42MXU7A6.js",
      "dist/chunk-4KDZZW4X.js",
      "dist/chunk-4VQTUVH7.js",
      "dist/chunk-7766SIJP.js"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/2026-02-10-clawhub-clawvault-1-5-1"
    },
    "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/2026-02-10-clawhub-clawvault-1-5-1",
    "agentPageUrl": "https://openagent3.xyz/skills/2026-02-10-clawhub-clawvault-1-5-1/agent",
    "manifestUrl": "https://openagent3.xyz/skills/2026-02-10-clawhub-clawvault-1-5-1/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/2026-02-10-clawhub-clawvault-1-5-1/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": "ClawVault 🐘",
        "body": "An elephant never forgets. Structured memory for OpenClaw agents.\n\nBuilt for OpenClaw — install via clawhub install clawvault"
      },
      {
        "title": "Install",
        "body": "npm install -g clawvault"
      },
      {
        "title": "Setup",
        "body": "# Initialize vault (creates folder structure + templates)\nclawvault init ~/my-vault\n\n# Or set env var to use existing vault\nexport CLAWVAULT_PATH=/path/to/memory\n\n# Optional: shell integration (aliases + CLAWVAULT_PATH)\nclawvault shell-init >> ~/.bashrc"
      },
      {
        "title": "Quick Start for New Agents",
        "body": "# Start your session (recover + recap + summary)\nclawvault wake\n\n# Capture and checkpoint during work\nclawvault capture \"TODO: Review PR tomorrow\"\nclawvault checkpoint --working-on \"PR review\" --focus \"type guards\"\n\n# End your session with a handoff\nclawvault sleep \"PR review + type guards\" --next \"respond to CI\" --blocked \"waiting for CI\"\n\n# Health check when something feels off\nclawvault doctor"
      },
      {
        "title": "Wake + Sleep (primary)",
        "body": "clawvault wake\nclawvault sleep \"what I was working on\" --next \"ship v1\" --blocked \"waiting for API key\""
      },
      {
        "title": "Store memories by type",
        "body": "# Types: fact, feeling, decision, lesson, commitment, preference, relationship, project\nclawvault remember decision \"Use Postgres over SQLite\" --content \"Need concurrent writes for multi-agent setup\"\nclawvault remember lesson \"Context death is survivable\" --content \"Checkpoint before heavy work\"\nclawvault remember relationship \"Justin Dukes\" --content \"Client contact at Hale Pet Door\""
      },
      {
        "title": "Quick capture to inbox",
        "body": "clawvault capture \"TODO: Review PR tomorrow\""
      },
      {
        "title": "Search (requires qmd installed)",
        "body": "# Keyword search (fast)\nclawvault search \"client contacts\"\n\n# Semantic search (slower, more accurate)\nclawvault vsearch \"what did we decide about the database\""
      },
      {
        "title": "Wake (start of session)",
        "body": "clawvault wake"
      },
      {
        "title": "Sleep (end of session)",
        "body": "clawvault sleep \"what I was working on\" --next \"finish docs\" --blocked \"waiting for review\""
      },
      {
        "title": "Checkpoint (save state frequently)",
        "body": "clawvault checkpoint --working-on \"PR review\" --focus \"type guards\" --blocked \"waiting for CI\""
      },
      {
        "title": "Recover (manual check)",
        "body": "clawvault recover --clear\n# Shows: death time, last checkpoint, recent handoff"
      },
      {
        "title": "Handoff (manual session end)",
        "body": "clawvault handoff \\\n  --working-on \"ClawVault improvements\" \\\n  --blocked \"npm token\" \\\n  --next \"publish to npm, create skill\" \\\n  --feeling \"productive\""
      },
      {
        "title": "Recap (bootstrap new session)",
        "body": "clawvault recap\n# Shows: recent handoffs, active projects, pending commitments, lessons"
      },
      {
        "title": "Auto-linking",
        "body": "Wiki-link entity mentions in markdown files:\n\n# Link all files\nclawvault link --all\n\n# Link single file\nclawvault link memory/2024-01-15.md"
      },
      {
        "title": "Folder Structure",
        "body": "vault/\n├── .clawvault/           # Internal state\n│   ├── last-checkpoint.json\n│   └── dirty-death.flag\n├── decisions/            # Key choices with reasoning\n├── lessons/              # Insights and patterns\n├── people/               # One file per person\n├── projects/             # Active work tracking\n├── handoffs/             # Session continuity\n├── inbox/                # Quick captures\n└── templates/            # Document templates"
      },
      {
        "title": "Best Practices",
        "body": "Wake at session start — clawvault wake restores context\nCheckpoint every 10-15 min during heavy work\nSleep before session end — clawvault sleep captures next steps\nUse types — knowing WHAT you're storing helps WHERE to put it\nWiki-link liberally — [[person-name]] builds your knowledge graph"
      },
      {
        "title": "Checklist for AGENTS.md",
        "body": "## Memory Checklist\n- [ ] Run `clawvault wake` at session start\n- [ ] Checkpoint during heavy work\n- [ ] Capture key decisions/lessons with `clawvault remember`\n- [ ] Use wiki-links like `[[person-name]]`\n- [ ] End with `clawvault sleep \"...\" --next \"...\" --blocked \"...\"`\n- [ ] Run `clawvault doctor` when something feels off"
      },
      {
        "title": "Session Transcript Repair (v1.5.0+)",
        "body": "When the Anthropic API rejects with \"unexpected tool_use_id found in tool_result blocks\", use:\n\n# See what's wrong (dry-run)\nclawvault repair-session --dry-run\n\n# Fix it\nclawvault repair-session\n\n# Repair a specific session\nclawvault repair-session --session <id> --agent <agent-id>\n\n# List available sessions\nclawvault repair-session --list\n\nWhat it fixes:\n\nOrphaned tool_result blocks referencing non-existent tool_use IDs\nAborted tool calls with partial JSON\nBroken parent chain references\n\nBackups are created automatically (use --no-backup to skip)."
      },
      {
        "title": "Troubleshooting",
        "body": "qmd not installed — run bun install -g github:tobi/qmd or npm install -g qmd\nNo ClawVault found — run clawvault init or set CLAWVAULT_PATH\nCLAWVAULT_PATH missing — run clawvault shell-init and add to shell rc\nToo many orphan links — run clawvault link --orphans\nInbox backlog warning — process or archive inbox items\n\"unexpected tool_use_id\" error — run clawvault repair-session"
      },
      {
        "title": "Integration with qmd",
        "body": "ClawVault uses qmd for search:\n\n# Install qmd\nbun install -g github:tobi/qmd\n\n# Add vault as collection\nqmd collection add /path/to/vault --name my-memory --mask \"**/*.md\"\n\n# Update index\nqmd update && qmd embed"
      },
      {
        "title": "Environment Variables",
        "body": "CLAWVAULT_PATH — Default vault path (skips auto-discovery)"
      },
      {
        "title": "Links",
        "body": "npm: https://www.npmjs.com/package/clawvault\nGitHub: https://github.com/Versatly/clawvault\nIssues: https://github.com/Versatly/clawvault/issues"
      }
    ],
    "body": "ClawVault 🐘\n\nAn elephant never forgets. Structured memory for OpenClaw agents.\n\nBuilt for OpenClaw — install via clawhub install clawvault\n\nInstall\nnpm install -g clawvault\n\nSetup\n# Initialize vault (creates folder structure + templates)\nclawvault init ~/my-vault\n\n# Or set env var to use existing vault\nexport CLAWVAULT_PATH=/path/to/memory\n\n# Optional: shell integration (aliases + CLAWVAULT_PATH)\nclawvault shell-init >> ~/.bashrc\n\nQuick Start for New Agents\n# Start your session (recover + recap + summary)\nclawvault wake\n\n# Capture and checkpoint during work\nclawvault capture \"TODO: Review PR tomorrow\"\nclawvault checkpoint --working-on \"PR review\" --focus \"type guards\"\n\n# End your session with a handoff\nclawvault sleep \"PR review + type guards\" --next \"respond to CI\" --blocked \"waiting for CI\"\n\n# Health check when something feels off\nclawvault doctor\n\nCore Commands\nWake + Sleep (primary)\nclawvault wake\nclawvault sleep \"what I was working on\" --next \"ship v1\" --blocked \"waiting for API key\"\n\nStore memories by type\n# Types: fact, feeling, decision, lesson, commitment, preference, relationship, project\nclawvault remember decision \"Use Postgres over SQLite\" --content \"Need concurrent writes for multi-agent setup\"\nclawvault remember lesson \"Context death is survivable\" --content \"Checkpoint before heavy work\"\nclawvault remember relationship \"Justin Dukes\" --content \"Client contact at Hale Pet Door\"\n\nQuick capture to inbox\nclawvault capture \"TODO: Review PR tomorrow\"\n\nSearch (requires qmd installed)\n# Keyword search (fast)\nclawvault search \"client contacts\"\n\n# Semantic search (slower, more accurate)\nclawvault vsearch \"what did we decide about the database\"\n\nContext Death Resilience\nWake (start of session)\nclawvault wake\n\nSleep (end of session)\nclawvault sleep \"what I was working on\" --next \"finish docs\" --blocked \"waiting for review\"\n\nCheckpoint (save state frequently)\nclawvault checkpoint --working-on \"PR review\" --focus \"type guards\" --blocked \"waiting for CI\"\n\nRecover (manual check)\nclawvault recover --clear\n# Shows: death time, last checkpoint, recent handoff\n\nHandoff (manual session end)\nclawvault handoff \\\n  --working-on \"ClawVault improvements\" \\\n  --blocked \"npm token\" \\\n  --next \"publish to npm, create skill\" \\\n  --feeling \"productive\"\n\nRecap (bootstrap new session)\nclawvault recap\n# Shows: recent handoffs, active projects, pending commitments, lessons\n\nAuto-linking\n\nWiki-link entity mentions in markdown files:\n\n# Link all files\nclawvault link --all\n\n# Link single file\nclawvault link memory/2024-01-15.md\n\nFolder Structure\nvault/\n├── .clawvault/           # Internal state\n│   ├── last-checkpoint.json\n│   └── dirty-death.flag\n├── decisions/            # Key choices with reasoning\n├── lessons/              # Insights and patterns\n├── people/               # One file per person\n├── projects/             # Active work tracking\n├── handoffs/             # Session continuity\n├── inbox/                # Quick captures\n└── templates/            # Document templates\n\nBest Practices\nWake at session start — clawvault wake restores context\nCheckpoint every 10-15 min during heavy work\nSleep before session end — clawvault sleep captures next steps\nUse types — knowing WHAT you're storing helps WHERE to put it\nWiki-link liberally — [[person-name]] builds your knowledge graph\nChecklist for AGENTS.md\n## Memory Checklist\n- [ ] Run `clawvault wake` at session start\n- [ ] Checkpoint during heavy work\n- [ ] Capture key decisions/lessons with `clawvault remember`\n- [ ] Use wiki-links like `[[person-name]]`\n- [ ] End with `clawvault sleep \"...\" --next \"...\" --blocked \"...\"`\n- [ ] Run `clawvault doctor` when something feels off\n\nSession Transcript Repair (v1.5.0+)\n\nWhen the Anthropic API rejects with \"unexpected tool_use_id found in tool_result blocks\", use:\n\n# See what's wrong (dry-run)\nclawvault repair-session --dry-run\n\n# Fix it\nclawvault repair-session\n\n# Repair a specific session\nclawvault repair-session --session <id> --agent <agent-id>\n\n# List available sessions\nclawvault repair-session --list\n\n\nWhat it fixes:\n\nOrphaned tool_result blocks referencing non-existent tool_use IDs\nAborted tool calls with partial JSON\nBroken parent chain references\n\nBackups are created automatically (use --no-backup to skip).\n\nTroubleshooting\nqmd not installed — run bun install -g github:tobi/qmd or npm install -g qmd\nNo ClawVault found — run clawvault init or set CLAWVAULT_PATH\nCLAWVAULT_PATH missing — run clawvault shell-init and add to shell rc\nToo many orphan links — run clawvault link --orphans\nInbox backlog warning — process or archive inbox items\n\"unexpected tool_use_id\" error — run clawvault repair-session\nIntegration with qmd\n\nClawVault uses qmd for search:\n\n# Install qmd\nbun install -g github:tobi/qmd\n\n# Add vault as collection\nqmd collection add /path/to/vault --name my-memory --mask \"**/*.md\"\n\n# Update index\nqmd update && qmd embed\n\nEnvironment Variables\nCLAWVAULT_PATH — Default vault path (skips auto-discovery)\nLinks\nnpm: https://www.npmjs.com/package/clawvault\nGitHub: https://github.com/Versatly/clawvault\nIssues: https://github.com/Versatly/clawvault/issues"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/pin-alt/2026-02-10-clawhub-clawvault-1-5-1",
    "publisherUrl": "https://clawhub.ai/pin-alt/2026-02-10-clawhub-clawvault-1-5-1",
    "owner": "pin-alt",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/2026-02-10-clawhub-clawvault-1-5-1",
    "downloadUrl": "https://openagent3.xyz/downloads/2026-02-10-clawhub-clawvault-1-5-1",
    "agentUrl": "https://openagent3.xyz/skills/2026-02-10-clawhub-clawvault-1-5-1/agent",
    "manifestUrl": "https://openagent3.xyz/skills/2026-02-10-clawhub-clawvault-1-5-1/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/2026-02-10-clawhub-clawvault-1-5-1/agent.md"
  }
}