{
  "schemaVersion": "1.0",
  "item": {
    "slug": "clawzembic",
    "name": "Clawzempic",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/anna-claudette/clawzembic",
    "canonicalUrl": "https://clawhub.ai/anna-claudette/clawzembic",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/clawzembic",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawzembic",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "lean-audit.sh",
      "lean-report.py"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "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/clawzembic"
    },
    "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/clawzembic",
    "agentPageUrl": "https://openagent3.xyz/skills/clawzembic/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawzembic/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawzembic/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": "Clawzembic — Weight Loss for Your OpenClaw Instance",
        "body": "Lighthouse-style audit for OpenClaw efficiency. Run it, get a grade (A+ to F), shed the bloat.\n\nScans your installation and scores it across six critical categories: context injection, cron health, session bloat, config health, skill bloat, and transcript size. You get one overall letter grade plus category-by-category breakdown with actionable findings.\n\nZero dependencies. Python 3.8+ stdlib only."
      },
      {
        "title": "Quick Start",
        "body": "# Audit this machine\nbash skills/clawzembic/lean-audit.sh\n\n# Audit a remote instance (VM, etc.)\nbash skills/clawzembic/lean-audit.sh --remote user@host\n\n# JSON output for dashboards/integrations\nbash skills/clawzembic/lean-audit.sh --json\n\n# Show automated fix suggestions\nbash skills/clawzembic/lean-audit.sh --fix\n\n# Custom .openclaw directory\nbash skills/clawzembic/lean-audit.sh --dir /path/to/.openclaw"
      },
      {
        "title": "What It Checks",
        "body": "CategoryWeightWhat Gets FlaggedContext Injection25%Oversized MEMORY.md, bloated workspace files eating tokensCron Health25%Wrong models, high thinking on routine tasks, main-session pollutionSession Bloat20%Stale sessions hogging context, waste ratio above 35%Config Health15%Heartbeat too frequent, subagent defaults, missing compactionSkill Bloat10%Too many skills injected, unused skills inflating system promptTranscript Size5%Disk hogs, oversized transcripts (>10MB files)"
      },
      {
        "title": "Grade Scale",
        "body": "A+/A (90-100): Lean machine 💪\nB+/B (75-89): Good shape, minor tweaks\nC+/C (60-74): Needs a diet 🍕\nD+/D (45-59): Significant bloat 🫠\nF (<45): Emergency Clawzembic needed 💊"
      },
      {
        "title": "Agent Usage",
        "body": "When Jeffrey asks you to audit or optimize an OpenClaw instance:\n\nRun bash skills/clawzembic/lean-audit.sh (or --remote user@claudette for the VM)\nReview the report and present key findings with context\nOffer --fix mode for automated remediation if score < 75\n\nFor remote instances, ensure SSH key-based auth is configured. The skill uses SSH to execute the audit remotely — no agent installation needed on the target."
      }
    ],
    "body": "Clawzembic — Weight Loss for Your OpenClaw Instance\n\nLighthouse-style audit for OpenClaw efficiency. Run it, get a grade (A+ to F), shed the bloat.\n\nScans your installation and scores it across six critical categories: context injection, cron health, session bloat, config health, skill bloat, and transcript size. You get one overall letter grade plus category-by-category breakdown with actionable findings.\n\nZero dependencies. Python 3.8+ stdlib only.\n\nQuick Start\n# Audit this machine\nbash skills/clawzembic/lean-audit.sh\n\n# Audit a remote instance (VM, etc.)\nbash skills/clawzembic/lean-audit.sh --remote user@host\n\n# JSON output for dashboards/integrations\nbash skills/clawzembic/lean-audit.sh --json\n\n# Show automated fix suggestions\nbash skills/clawzembic/lean-audit.sh --fix\n\n# Custom .openclaw directory\nbash skills/clawzembic/lean-audit.sh --dir /path/to/.openclaw\n\nWhat It Checks\nCategory\tWeight\tWhat Gets Flagged\nContext Injection\t25%\tOversized MEMORY.md, bloated workspace files eating tokens\nCron Health\t25%\tWrong models, high thinking on routine tasks, main-session pollution\nSession Bloat\t20%\tStale sessions hogging context, waste ratio above 35%\nConfig Health\t15%\tHeartbeat too frequent, subagent defaults, missing compaction\nSkill Bloat\t10%\tToo many skills injected, unused skills inflating system prompt\nTranscript Size\t5%\tDisk hogs, oversized transcripts (>10MB files)\nGrade Scale\nA+/A (90-100): Lean machine 💪\nB+/B (75-89): Good shape, minor tweaks\nC+/C (60-74): Needs a diet 🍕\nD+/D (45-59): Significant bloat 🫠\nF (<45): Emergency Clawzembic needed 💊\nAgent Usage\n\nWhen Jeffrey asks you to audit or optimize an OpenClaw instance:\n\nRun bash skills/clawzembic/lean-audit.sh (or --remote user@claudette for the VM)\nReview the report and present key findings with context\nOffer --fix mode for automated remediation if score < 75\n\nFor remote instances, ensure SSH key-based auth is configured. The skill uses SSH to execute the audit remotely — no agent installation needed on the target."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/anna-claudette/clawzembic",
    "publisherUrl": "https://clawhub.ai/anna-claudette/clawzembic",
    "owner": "anna-claudette",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/clawzembic",
    "downloadUrl": "https://openagent3.xyz/downloads/clawzembic",
    "agentUrl": "https://openagent3.xyz/skills/clawzembic/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawzembic/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawzembic/agent.md"
  }
}