{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skillbench",
    "name": "SkillBench",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/G9Pedro/skillbench",
    "canonicalUrl": "https://clawhub.ai/G9Pedro/skillbench",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skillbench",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillbench",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.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. 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",
      "slug": "skillbench",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T05:32:59.113Z",
      "expiresAt": "2026-05-08T05:32:59.113Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillbench",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillbench",
        "contentDisposition": "attachment; filename=\"skillbench-2.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "skillbench"
      },
      "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/skillbench"
    },
    "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/skillbench",
    "agentPageUrl": "https://openagent3.xyz/skills/skillbench/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skillbench/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skillbench/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": "skillbench Skill",
        "body": "Self-improving skill ecosystem for AI agents.\n\nTrack skill versions, benchmark performance, compare improvements, and get signals on what to fix next.\n\nPart of the ClawVault ecosystem | tasktime | ClawHub"
      },
      {
        "title": "Installation",
        "body": "npm install -g @versatly/skillbench"
      },
      {
        "title": "The Loop",
        "body": "1. Use a skill    → skillbench use github@1.0.0\n2. Do the task    → tt start \"Create PR\" && ... && tt stop\n3. Record result  → skillbench record \"Create PR\" --success\n4. Check scores   → skillbench score github\n5. Improve skill  → Update skill, bump version\n6. Repeat         → Compare v1.0.0 vs v1.1.0"
      },
      {
        "title": "Track Skills",
        "body": "skillbench use github@1.2.0            # Set active skill version\nskillbench skills                       # List tracked skills + signals"
      },
      {
        "title": "Record Benchmarks",
        "body": "# Auto-pulls duration from tasktime\nskillbench record \"Create PR\" --success\n\n# Manual duration\nskillbench record \"Create PR\" --duration 45s --success\n\n# Record failures\nskillbench record \"Create PR\" --fail --error-type \"auth-error\""
      },
      {
        "title": "Score & Compare",
        "body": "skillbench score                        # All skills with grades\nskillbench score github                 # Single skill\nskillbench compare github@1.0.0 github@1.1.0"
      },
      {
        "title": "Export & Dashboard",
        "body": "skillbench export --format markdown\nskillbench export --format json\nskillbench dashboard                    # Generate HTML dashboard\nskillbench dashboard --open             # Generate and open in browser"
      },
      {
        "title": "Automated Testing",
        "body": "skillbench test tasktime@1.1.0          # Run smoke test\nskillbench test tasktime@1.1.0 --suite full  # Run named suite\nskillbench test tasktime@1.1.0 --dry-run     # Test without recording"
      },
      {
        "title": "Sync",
        "body": "skillbench sync --clawhub               # Import installed skills\nskillbench sync --vault                 # Sync to ClawVault\nskillbench sync --all                   # Everything"
      },
      {
        "title": "Health & Monitoring",
        "body": "skillbench health                       # Overall health report with alerts\nskillbench watch --once                 # Run all test suites once\nskillbench watch --interval 300         # Continuous monitoring every 5 min"
      },
      {
        "title": "Analysis & Improvement",
        "body": "skillbench improve                      # Get suggestions for weakest skill\nskillbench improve github               # Improvement plan for specific skill\nskillbench trend tasktime --days 30     # Performance trend over time\nskillbench leaderboard                  # Compare agents (multi-agent setups)\nskillbench schedule --interval 60       # Generate cron config for auto-testing"
      },
      {
        "title": "Baselines & Regression Detection",
        "body": "skillbench baseline tasktime --set      # Set baseline from current performance\nskillbench baseline --list              # List all baselines\nskillbench baseline --check             # Check all baselines (CI-friendly, exits 1 if failing)\nskillbench baseline tasktime --remove   # Remove a baseline"
      },
      {
        "title": "CI/CD Integration",
        "body": "skillbench ci                           # Run all tests + baseline checks\nskillbench ci --json                    # JSON output for automation\nskillbench badge                        # Generate shields.io badges for README\n\nCopy examples/github-action.yml for ready-to-use GitHub Actions workflow."
      },
      {
        "title": "Grading System",
        "body": "GradeScoreMeaning🏆 A+95-100Elite performance✅ A85-94Excellent👍 B70-84Good⚠️ C50-69Needs work❌ D<50Broken\n\nBased on: Success Rate (40%), Avg Duration (30%), Consistency (20%), Trend (10%)"
      },
      {
        "title": "tasktime Integration",
        "body": "When you omit --duration, skillbench pulls from tasktime:\n\ntt start \"Create PR\" -c git\n# ... do work ...\ntt stop\nskillbench record --success   # Duration auto-pulled"
      },
      {
        "title": "ClawVault Integration",
        "body": "Benchmarks sync to ClawVault automatically."
      },
      {
        "title": "Improvement Signals",
        "body": "skillbench skills shows:\n\n⚠️ needs work — Success rate below 70%\n🕐 stale — No benchmarks in 7+ days\n↘️ declining — Getting worse over time"
      },
      {
        "title": "Related",
        "body": "ClawVault — Memory system for AI agents\ntasktime — Task timer CLI\nClawHub — Skill marketplace"
      }
    ],
    "body": "skillbench Skill\n\nSelf-improving skill ecosystem for AI agents.\n\nTrack skill versions, benchmark performance, compare improvements, and get signals on what to fix next.\n\nPart of the ClawVault ecosystem | tasktime | ClawHub\n\nInstallation\nnpm install -g @versatly/skillbench\n\nThe Loop\n1. Use a skill    → skillbench use github@1.0.0\n2. Do the task    → tt start \"Create PR\" && ... && tt stop\n3. Record result  → skillbench record \"Create PR\" --success\n4. Check scores   → skillbench score github\n5. Improve skill  → Update skill, bump version\n6. Repeat         → Compare v1.0.0 vs v1.1.0\n\nCommands\nTrack Skills\nskillbench use github@1.2.0            # Set active skill version\nskillbench skills                       # List tracked skills + signals\n\nRecord Benchmarks\n# Auto-pulls duration from tasktime\nskillbench record \"Create PR\" --success\n\n# Manual duration\nskillbench record \"Create PR\" --duration 45s --success\n\n# Record failures\nskillbench record \"Create PR\" --fail --error-type \"auth-error\"\n\nScore & Compare\nskillbench score                        # All skills with grades\nskillbench score github                 # Single skill\nskillbench compare github@1.0.0 github@1.1.0\n\nExport & Dashboard\nskillbench export --format markdown\nskillbench export --format json\nskillbench dashboard                    # Generate HTML dashboard\nskillbench dashboard --open             # Generate and open in browser\n\nAutomated Testing\nskillbench test tasktime@1.1.0          # Run smoke test\nskillbench test tasktime@1.1.0 --suite full  # Run named suite\nskillbench test tasktime@1.1.0 --dry-run     # Test without recording\n\nSync\nskillbench sync --clawhub               # Import installed skills\nskillbench sync --vault                 # Sync to ClawVault\nskillbench sync --all                   # Everything\n\nHealth & Monitoring\nskillbench health                       # Overall health report with alerts\nskillbench watch --once                 # Run all test suites once\nskillbench watch --interval 300         # Continuous monitoring every 5 min\n\nAnalysis & Improvement\nskillbench improve                      # Get suggestions for weakest skill\nskillbench improve github               # Improvement plan for specific skill\nskillbench trend tasktime --days 30     # Performance trend over time\nskillbench leaderboard                  # Compare agents (multi-agent setups)\nskillbench schedule --interval 60       # Generate cron config for auto-testing\n\nBaselines & Regression Detection\nskillbench baseline tasktime --set      # Set baseline from current performance\nskillbench baseline --list              # List all baselines\nskillbench baseline --check             # Check all baselines (CI-friendly, exits 1 if failing)\nskillbench baseline tasktime --remove   # Remove a baseline\n\nCI/CD Integration\nskillbench ci                           # Run all tests + baseline checks\nskillbench ci --json                    # JSON output for automation\nskillbench badge                        # Generate shields.io badges for README\n\n\nCopy examples/github-action.yml for ready-to-use GitHub Actions workflow.\n\nGrading System\nGrade\tScore\tMeaning\n🏆 A+\t95-100\tElite performance\n✅ A\t85-94\tExcellent\n👍 B\t70-84\tGood\n⚠️ C\t50-69\tNeeds work\n❌ D\t<50\tBroken\n\nBased on: Success Rate (40%), Avg Duration (30%), Consistency (20%), Trend (10%)\n\ntasktime Integration\n\nWhen you omit --duration, skillbench pulls from tasktime:\n\ntt start \"Create PR\" -c git\n# ... do work ...\ntt stop\nskillbench record --success   # Duration auto-pulled\n\nClawVault Integration\n\nBenchmarks sync to ClawVault automatically.\n\nImprovement Signals\n\nskillbench skills shows:\n\n⚠️ needs work — Success rate below 70%\n🕐 stale — No benchmarks in 7+ days\n↘️ declining — Getting worse over time\nRelated\nClawVault — Memory system for AI agents\ntasktime — Task timer CLI\nClawHub — Skill marketplace"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/G9Pedro/skillbench",
    "publisherUrl": "https://clawhub.ai/G9Pedro/skillbench",
    "owner": "G9Pedro",
    "version": "2.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skillbench",
    "downloadUrl": "https://openagent3.xyz/downloads/skillbench",
    "agentUrl": "https://openagent3.xyz/skills/skillbench/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skillbench/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skillbench/agent.md"
  }
}