{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skill-priority-setup",
    "name": "Skill Priority Setup",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/halfmoon82/skill-priority-setup",
    "canonicalUrl": "https://clawhub.ai/halfmoon82/skill-priority-setup",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skill-priority-setup",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-priority-setup",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "clawhub.yaml",
      "scripts/generate_docx.py",
      "scripts/generate_docx_cn.py",
      "scripts/setup.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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/skill-priority-setup"
    },
    "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/skill-priority-setup",
    "agentPageUrl": "https://openagent3.xyz/skills/skill-priority-setup/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-priority-setup/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-priority-setup/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": "Skill Priority Setup",
        "body": "Automated skill tiering and injection policy configuration for OpenClaw."
      },
      {
        "title": "What This Skill Does",
        "body": "Discovery Phase: Scans all installed skills across standard directories\nAnalysis Phase: Suggests L0-L3 tier assignments based on skill characteristics\nConfiguration Phase: Applies the tiered architecture to your setup\nValidation Phase: Verifies configuration and estimates token savings"
      },
      {
        "title": "Quick Start",
        "body": "# Run the interactive setup wizard\npython3 ~/.openclaw/workspace/skills/skill-priority-setup/scripts/setup.py\n\n# Or non-interactive mode with defaults\npython3 ~/.openclaw/workspace/skills/skill-priority-setup/scripts/setup.py --auto"
      },
      {
        "title": "When to Use",
        "body": "New Setup: Just installed multiple skills and want optimal configuration\nPerformance Issues: High token usage or slow responses\nMigration: Upgrading from flat skill structure to tiered architecture\nAudit: Reviewing and optimizing existing skill priorities"
      },
      {
        "title": "Architecture Overview",
        "body": "This skill implements a 4-tier priority system:"
      },
      {
        "title": "L0 - ROM Core (Always Active)",
        "body": "semantic-system: Semantic routing (message injector)\nagent-evolution: Self-improvement behaviors (SOUL.md)\nconfig-modification: Config safety (on-demand)\nskill-safe-install: Installation safety (on-demand)"
      },
      {
        "title": "L1 - Routing Layer (Task-Triggered)",
        "body": "browser-automation: Web automation\nfind-skills: Skill discovery\nteamtask: Multi-agent coordination"
      },
      {
        "title": "L2 - Domain Skills (Keyword-Triggered)",
        "body": "Document: word-docx, tesseract-ocr\nMedia: youtube-transcript\nPlatform: discord, wechat-suite, evomap\nAutomation: automation-workflows"
      },
      {
        "title": "L3 - Extensions (Manual/On-Demand)",
        "body": "Third-party integrations: notion, slack, github, etc."
      },
      {
        "title": "Workflow",
        "body": "┌─────────────────┐\n│ 1. Scan Skills  │ → Find all SKILL.md files\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 2. Analyze      │ → Detect skill types & dependencies\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 3. Suggest Tiers│ → Propose L0-L3 assignments\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 4. User Review  │ → Confirm or modify suggestions\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 5. Apply Config │ → Update AGENTS.md, SOUL.md, etc.\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 6. Validate     │ → Check JSON, test injection\n└─────────────────┘"
      },
      {
        "title": "Token Budget",
        "body": "L0 Core: ≤300 tokens/round (minimal rules)\nL1 Triggered: ≤400 tokens per injection\nTotal Budget: ≤900 tokens/round\nOverflow Strategy: Inject summary + file path only"
      },
      {
        "title": "Safety Features",
        "body": "Backup before any configuration changes\nJSON validation before applying\nDry-run mode (--dry-run)\nRollback capability"
      },
      {
        "title": "Files Created",
        "body": "SKILL_PRIORITY_POLICY.md: Your custom policy document\nAGENTS.md updates: Core constraints added\nSOUL.md updates: Agent evolution behaviors\nBackup files: .backup/*.timestamp"
      },
      {
        "title": "Configuration",
        "body": "Edit ~/.openclaw/workspace/skills/skill-priority-setup/config.yaml to customize:\n\n# Default tier assignments (override per skill)\ndefault_tiers:\n  semantic-router: L0\n  browser: L1\n  word-docx: L2\n  \n# Token budgets\ntoken_budget:\n  l0_max: 300\n  l1_max: 400\n  total_max: 900\n  \n# Safety settings\nbackup_before_change: true\nvalidate_json: true\nauto_rollback: true"
      },
      {
        "title": "Gateway Won't Start",
        "body": "Check if message injector content exceeds limit\nRun with --diagnose flag"
      },
      {
        "title": "Skills Not Loading",
        "body": "Verify allowBundled list in openclaw.json\nCheck file permissions"
      },
      {
        "title": "High Token Usage",
        "body": "Review L0 assignments (should be minimal)\nConsider moving skills to lower tiers"
      },
      {
        "title": "References",
        "body": "Original Implementation: SKILL_PRIORITY_POLICY.md\nOpenClaw Docs: https://docs.openclaw.ai/skills"
      }
    ],
    "body": "Skill Priority Setup\n\nAutomated skill tiering and injection policy configuration for OpenClaw.\n\nWhat This Skill Does\nDiscovery Phase: Scans all installed skills across standard directories\nAnalysis Phase: Suggests L0-L3 tier assignments based on skill characteristics\nConfiguration Phase: Applies the tiered architecture to your setup\nValidation Phase: Verifies configuration and estimates token savings\nQuick Start\n# Run the interactive setup wizard\npython3 ~/.openclaw/workspace/skills/skill-priority-setup/scripts/setup.py\n\n# Or non-interactive mode with defaults\npython3 ~/.openclaw/workspace/skills/skill-priority-setup/scripts/setup.py --auto\n\nWhen to Use\nNew Setup: Just installed multiple skills and want optimal configuration\nPerformance Issues: High token usage or slow responses\nMigration: Upgrading from flat skill structure to tiered architecture\nAudit: Reviewing and optimizing existing skill priorities\nArchitecture Overview\n\nThis skill implements a 4-tier priority system:\n\nL0 - ROM Core (Always Active)\nsemantic-system: Semantic routing (message injector)\nagent-evolution: Self-improvement behaviors (SOUL.md)\nconfig-modification: Config safety (on-demand)\nskill-safe-install: Installation safety (on-demand)\nL1 - Routing Layer (Task-Triggered)\nbrowser-automation: Web automation\nfind-skills: Skill discovery\nteamtask: Multi-agent coordination\nL2 - Domain Skills (Keyword-Triggered)\nDocument: word-docx, tesseract-ocr\nMedia: youtube-transcript\nPlatform: discord, wechat-suite, evomap\nAutomation: automation-workflows\nL3 - Extensions (Manual/On-Demand)\nThird-party integrations: notion, slack, github, etc.\nWorkflow\n┌─────────────────┐\n│ 1. Scan Skills  │ → Find all SKILL.md files\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 2. Analyze      │ → Detect skill types & dependencies\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 3. Suggest Tiers│ → Propose L0-L3 assignments\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 4. User Review  │ → Confirm or modify suggestions\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 5. Apply Config │ → Update AGENTS.md, SOUL.md, etc.\n└────────┬────────┘\n         ▼\n┌─────────────────┐\n│ 6. Validate     │ → Check JSON, test injection\n└─────────────────┘\n\nToken Budget\nL0 Core: ≤300 tokens/round (minimal rules)\nL1 Triggered: ≤400 tokens per injection\nTotal Budget: ≤900 tokens/round\nOverflow Strategy: Inject summary + file path only\nSafety Features\nBackup before any configuration changes\nJSON validation before applying\nDry-run mode (--dry-run)\nRollback capability\nFiles Created\nSKILL_PRIORITY_POLICY.md: Your custom policy document\nAGENTS.md updates: Core constraints added\nSOUL.md updates: Agent evolution behaviors\nBackup files: .backup/*.timestamp\nConfiguration\n\nEdit ~/.openclaw/workspace/skills/skill-priority-setup/config.yaml to customize:\n\n# Default tier assignments (override per skill)\ndefault_tiers:\n  semantic-router: L0\n  browser: L1\n  word-docx: L2\n  \n# Token budgets\ntoken_budget:\n  l0_max: 300\n  l1_max: 400\n  total_max: 900\n  \n# Safety settings\nbackup_before_change: true\nvalidate_json: true\nauto_rollback: true\n\nTroubleshooting\nGateway Won't Start\nCheck if message injector content exceeds limit\nRun with --diagnose flag\nSkills Not Loading\nVerify allowBundled list in openclaw.json\nCheck file permissions\nHigh Token Usage\nReview L0 assignments (should be minimal)\nConsider moving skills to lower tiers\nReferences\nOriginal Implementation: SKILL_PRIORITY_POLICY.md\nOpenClaw Docs: https://docs.openclaw.ai/skills"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/halfmoon82/skill-priority-setup",
    "publisherUrl": "https://clawhub.ai/halfmoon82/skill-priority-setup",
    "owner": "halfmoon82",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skill-priority-setup",
    "downloadUrl": "https://openagent3.xyz/downloads/skill-priority-setup",
    "agentUrl": "https://openagent3.xyz/skills/skill-priority-setup/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-priority-setup/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-priority-setup/agent.md"
  }
}