{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-agent-optimize",
    "name": "Openclaw Agent Optimize",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/phenomenoner/openclaw-agent-optimize",
    "canonicalUrl": "https://clawhub.ai/phenomenoner/openclaw-agent-optimize",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-agent-optimize",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-agent-optimize",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "references/agent-orchestration.md",
      "references/context-management.md",
      "references/continuous-learning.md",
      "references/cron-optimization.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. 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",
      "slug": "openclaw-agent-optimize",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T17:11:45.730Z",
      "expiresAt": "2026-05-07T17:11:45.730Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-agent-optimize",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-agent-optimize",
        "contentDisposition": "attachment; filename=\"openclaw-agent-optimize-1.2.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "openclaw-agent-optimize"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/openclaw-agent-optimize"
    },
    "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/openclaw-agent-optimize",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-agent-optimize/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-agent-optimize/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-agent-optimize/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": "OpenClaw Agent Optimization",
        "body": "Use this skill to tune an OpenClaw workspace for cost-aware routing, parallel-first delegation, and lean context."
      },
      {
        "title": "Default posture",
        "body": "This skill is advisory first.\nIt should produce:\n\naudit,\noptions,\nrecommended plan,\nexact patch proposal,\nrollback,\nverification plan.\n\nNo persistent mutations without explicit approval."
      },
      {
        "title": "Quick start",
        "body": "Full audit (safe, no changes)\n\nAudit my OpenClaw setup for cost, reliability, and context bloat. Output a prioritized plan with rollback notes. Do NOT apply changes.\n\nContext bloat / transcript noise\n\nMy OpenClaw context is bloating (slow replies / high cost / lots of transcript noise). Identify the top offenders (tools, crons, bootstrap files, skills) and propose the smallest reversible fixes first. Do NOT apply changes.\n\nModel routing / delegation posture\n\nPropose a model routing plan for (a) coding/engineering, (b) short notifications/reminders, (c) reasoning-heavy research/writing. Include an exact config patch + rollback plan, but do NOT apply changes."
      },
      {
        "title": "What good output looks like",
        "body": "Executive summary\nTop drivers\n\ncost\ncontext\nreliability\noperator friction\n\n\nOptions A/B/C with tradeoffs\nRecommended plan (smallest safe change first)\nExact proposals + rollback + verify"
      },
      {
        "title": "Safety contract",
        "body": "Do not mutate persistent settings without explicit approval.\nDo not create/update/remove cron jobs without explicit approval.\nIf an optimization reduces monitoring coverage, present options and require choice.\nBefore any approved change, show:\n\nexact change,\nexpected impact,\nrollback plan,\npost-change verification."
      },
      {
        "title": "1) Output discipline for automation",
        "body": "Make maintenance loops truly silent on success."
      },
      {
        "title": "2) Separate work from notification",
        "body": "If you want alerts but want interactive context lean:\n\ndo the work quietly\nnotify out-of-band with a short human receipt"
      },
      {
        "title": "3) Bootstrap discipline",
        "body": "Keep always-injected files short and load-bearing only.\nMove long runbooks into references/ or adjacent notes."
      },
      {
        "title": "4) Ambient specialist surface reduction",
        "body": "A common hidden tax is too many always-visible specialist skills.\nIf a workflow is low-frequency or specialist:\n\nprefer on-demand worker/subagent usage,\ndo not keep it permanently ambient in main-chat prompt surface."
      },
      {
        "title": "5) Measure optimizations authoritatively",
        "body": "Prefer fresh-session /context json or equivalent receipts over “feels better”.\nHigh-signal fields include:\n\neligible skills\nskills.promptChars\nprojectContextChars\nsystemPrompt.chars\npromptTokens"
      },
      {
        "title": "6) Verification-first ops hygiene",
        "body": "After any approved optimization, verify:\n\ncore chat still works\nrecall/behavior did not degrade\nnew session actually picks up the change\nrollback path is proven, not theoretical"
      },
      {
        "title": "Workflow (concise)",
        "body": "Audit rules + memory: keep restart-critical facts only.\nAudit skill surface: trim ambient specialists before touching tool surface.\nAudit transcripts/noise: silence cron and heartbeat success paths.\nAudit model routing and delegation posture.\nRecommend the smallest viable change first.\nVerify on a new session when skill/bootstrap snapshotting exists."
      },
      {
        "title": "Notes",
        "body": "Some runtimes snapshot skills/config per session. If you install/update skills and do not see changes, start a new session.\nPrefer short SKILL.md + references/ for long runbooks.\nIf context bloat is the main complaint, pair this skill with context-clean-up (audit-only)."
      },
      {
        "title": "References",
        "body": "references/optimization-playbook.md\nreferences/model-selection.md\nreferences/context-management.md\nreferences/agent-orchestration.md\nreferences/cron-optimization.md\nreferences/heartbeat-optimization.md\nreferences/memory-patterns.md\nreferences/continuous-learning.md\nreferences/safeguards.md"
      }
    ],
    "body": "OpenClaw Agent Optimization\n\nUse this skill to tune an OpenClaw workspace for cost-aware routing, parallel-first delegation, and lean context.\n\nDefault posture\n\nThis skill is advisory first. It should produce:\n\naudit,\noptions,\nrecommended plan,\nexact patch proposal,\nrollback,\nverification plan.\n\nNo persistent mutations without explicit approval.\n\nQuick start\nFull audit (safe, no changes)\n\nAudit my OpenClaw setup for cost, reliability, and context bloat. Output a prioritized plan with rollback notes. Do NOT apply changes.\n\nContext bloat / transcript noise\n\nMy OpenClaw context is bloating (slow replies / high cost / lots of transcript noise). Identify the top offenders (tools, crons, bootstrap files, skills) and propose the smallest reversible fixes first. Do NOT apply changes.\n\nModel routing / delegation posture\n\nPropose a model routing plan for (a) coding/engineering, (b) short notifications/reminders, (c) reasoning-heavy research/writing. Include an exact config patch + rollback plan, but do NOT apply changes.\n\nWhat good output looks like\nExecutive summary\nTop drivers\ncost\ncontext\nreliability\noperator friction\nOptions A/B/C with tradeoffs\nRecommended plan (smallest safe change first)\nExact proposals + rollback + verify\nSafety contract\nDo not mutate persistent settings without explicit approval.\nDo not create/update/remove cron jobs without explicit approval.\nIf an optimization reduces monitoring coverage, present options and require choice.\nBefore any approved change, show:\nexact change,\nexpected impact,\nrollback plan,\npost-change verification.\nHigh-ROI optimization levers\n1) Output discipline for automation\n\nMake maintenance loops truly silent on success.\n\n2) Separate work from notification\n\nIf you want alerts but want interactive context lean:\n\ndo the work quietly\nnotify out-of-band with a short human receipt\n3) Bootstrap discipline\n\nKeep always-injected files short and load-bearing only. Move long runbooks into references/ or adjacent notes.\n\n4) Ambient specialist surface reduction\n\nA common hidden tax is too many always-visible specialist skills. If a workflow is low-frequency or specialist:\n\nprefer on-demand worker/subagent usage,\ndo not keep it permanently ambient in main-chat prompt surface.\n5) Measure optimizations authoritatively\n\nPrefer fresh-session /context json or equivalent receipts over “feels better”. High-signal fields include:\n\neligible skills\nskills.promptChars\nprojectContextChars\nsystemPrompt.chars\npromptTokens\n6) Verification-first ops hygiene\n\nAfter any approved optimization, verify:\n\ncore chat still works\nrecall/behavior did not degrade\nnew session actually picks up the change\nrollback path is proven, not theoretical\nWorkflow (concise)\nAudit rules + memory: keep restart-critical facts only.\nAudit skill surface: trim ambient specialists before touching tool surface.\nAudit transcripts/noise: silence cron and heartbeat success paths.\nAudit model routing and delegation posture.\nRecommend the smallest viable change first.\nVerify on a new session when skill/bootstrap snapshotting exists.\nNotes\nSome runtimes snapshot skills/config per session. If you install/update skills and do not see changes, start a new session.\nPrefer short SKILL.md + references/ for long runbooks.\nIf context bloat is the main complaint, pair this skill with context-clean-up (audit-only).\nReferences\nreferences/optimization-playbook.md\nreferences/model-selection.md\nreferences/context-management.md\nreferences/agent-orchestration.md\nreferences/cron-optimization.md\nreferences/heartbeat-optimization.md\nreferences/memory-patterns.md\nreferences/continuous-learning.md\nreferences/safeguards.md"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/phenomenoner/openclaw-agent-optimize",
    "publisherUrl": "https://clawhub.ai/phenomenoner/openclaw-agent-optimize",
    "owner": "phenomenoner",
    "version": "1.2.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-agent-optimize",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-agent-optimize",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-agent-optimize/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-agent-optimize/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-agent-optimize/agent.md"
  }
}