{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skill-evaluator",
    "name": "Skill Evaluator",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Terwox/skill-evaluator",
    "canonicalUrl": "https://clawhub.ai/Terwox/skill-evaluator",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skill-evaluator",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-evaluator",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "assets/EVAL-TEMPLATE.md",
      "references/rubric.md",
      "scripts/eval-skill.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. 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": "2026-05-07T17:22:31.273Z",
      "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-evaluator"
    },
    "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-evaluator",
    "agentPageUrl": "https://openagent3.xyz/skills/skill-evaluator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-evaluator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-evaluator/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": "Skill Evaluator",
        "body": "Evaluate skills across 25 criteria using a hybrid automated + manual approach."
      },
      {
        "title": "1. Run automated checks",
        "body": "python3 scripts/eval-skill.py /path/to/skill\npython3 scripts/eval-skill.py /path/to/skill --json    # machine-readable\npython3 scripts/eval-skill.py /path/to/skill --verbose  # show all details\n\nChecks: file structure, frontmatter, description quality, script syntax, dependency audit, credential scan, env var documentation."
      },
      {
        "title": "2. Manual assessment",
        "body": "Use the rubric at references/rubric.md to score 25 criteria across 8 categories (0–4 each, 100 total). Each criterion has concrete descriptions per score level."
      },
      {
        "title": "3. Write the evaluation",
        "body": "Copy assets/EVAL-TEMPLATE.md to the skill directory as EVAL.md. Fill in automated results + manual scores."
      },
      {
        "title": "Evaluation Process",
        "body": "Run eval-skill.py — get the automated structural score\nRead the skill's SKILL.md — understand what it does\nRead/skim the scripts — assess code quality, error handling, testability\nScore each manual criterion using references/rubric.md — concrete criteria per level\nPrioritize findings as P0 (blocks publishing) / P1 (should fix) / P2 (nice to have)\nWrite EVAL.md in the skill directory with scores + findings"
      },
      {
        "title": "Categories (8 categories, 25 criteria)",
        "body": "#CategorySource FrameworkCriteria1Functional SuitabilityISO 25010Completeness, Correctness, Appropriateness2ReliabilityISO 25010Fault Tolerance, Error Reporting, Recoverability3Performance / ContextISO 25010 + AgentToken Cost, Execution Efficiency4Usability — AI AgentShneiderman, Gerhardt-PowalsLearnability, Consistency, Feedback, Error Prevention5Usability — HumanTognazzini, NormanDiscoverability, Forgiveness6SecurityISO 25010 + OpenSSFCredentials, Input Validation, Data Safety7MaintainabilityISO 25010Modularity, Modifiability, Testability8Agent-SpecificNovelTrigger Precision, Progressive Disclosure, Composability, Idempotency, Escape Hatches"
      },
      {
        "title": "Interpreting Scores",
        "body": "RangeVerdictAction90–100ExcellentPublish confidently80–89GoodPublishable, note known issues70–79AcceptableFix P0s before publishing60–69Needs WorkFix P0+P1 before publishing<60Not ReadySignificant rework needed"
      },
      {
        "title": "Deeper Security Scanning",
        "body": "This evaluator covers security basics (credentials, input validation, data safety) but for thorough security audits of skills under development, consider SkillLens (npx skilllens scan <path>). It checks for exfiltration, code execution, persistence, privilege bypass, and prompt injection — complementary to the quality focus here."
      },
      {
        "title": "Dependencies",
        "body": "Python 3.6+ (for eval-skill.py)\nPyYAML (pip install pyyaml) — for frontmatter parsing in automated checks"
      }
    ],
    "body": "Skill Evaluator\n\nEvaluate skills across 25 criteria using a hybrid automated + manual approach.\n\nQuick Start\n1. Run automated checks\npython3 scripts/eval-skill.py /path/to/skill\npython3 scripts/eval-skill.py /path/to/skill --json    # machine-readable\npython3 scripts/eval-skill.py /path/to/skill --verbose  # show all details\n\n\nChecks: file structure, frontmatter, description quality, script syntax, dependency audit, credential scan, env var documentation.\n\n2. Manual assessment\n\nUse the rubric at references/rubric.md to score 25 criteria across 8 categories (0–4 each, 100 total). Each criterion has concrete descriptions per score level.\n\n3. Write the evaluation\n\nCopy assets/EVAL-TEMPLATE.md to the skill directory as EVAL.md. Fill in automated results + manual scores.\n\nEvaluation Process\nRun eval-skill.py — get the automated structural score\nRead the skill's SKILL.md — understand what it does\nRead/skim the scripts — assess code quality, error handling, testability\nScore each manual criterion using references/rubric.md — concrete criteria per level\nPrioritize findings as P0 (blocks publishing) / P1 (should fix) / P2 (nice to have)\nWrite EVAL.md in the skill directory with scores + findings\nCategories (8 categories, 25 criteria)\n#\tCategory\tSource Framework\tCriteria\n1\tFunctional Suitability\tISO 25010\tCompleteness, Correctness, Appropriateness\n2\tReliability\tISO 25010\tFault Tolerance, Error Reporting, Recoverability\n3\tPerformance / Context\tISO 25010 + Agent\tToken Cost, Execution Efficiency\n4\tUsability — AI Agent\tShneiderman, Gerhardt-Powals\tLearnability, Consistency, Feedback, Error Prevention\n5\tUsability — Human\tTognazzini, Norman\tDiscoverability, Forgiveness\n6\tSecurity\tISO 25010 + OpenSSF\tCredentials, Input Validation, Data Safety\n7\tMaintainability\tISO 25010\tModularity, Modifiability, Testability\n8\tAgent-Specific\tNovel\tTrigger Precision, Progressive Disclosure, Composability, Idempotency, Escape Hatches\nInterpreting Scores\nRange\tVerdict\tAction\n90–100\tExcellent\tPublish confidently\n80–89\tGood\tPublishable, note known issues\n70–79\tAcceptable\tFix P0s before publishing\n60–69\tNeeds Work\tFix P0+P1 before publishing\n<60\tNot Ready\tSignificant rework needed\nDeeper Security Scanning\n\nThis evaluator covers security basics (credentials, input validation, data safety) but for thorough security audits of skills under development, consider SkillLens (npx skilllens scan <path>). It checks for exfiltration, code execution, persistence, privilege bypass, and prompt injection — complementary to the quality focus here.\n\nDependencies\nPython 3.6+ (for eval-skill.py)\nPyYAML (pip install pyyaml) — for frontmatter parsing in automated checks"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Terwox/skill-evaluator",
    "publisherUrl": "https://clawhub.ai/Terwox/skill-evaluator",
    "owner": "Terwox",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skill-evaluator",
    "downloadUrl": "https://openagent3.xyz/downloads/skill-evaluator",
    "agentUrl": "https://openagent3.xyz/skills/skill-evaluator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-evaluator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-evaluator/agent.md"
  }
}