{
  "schemaVersion": "1.0",
  "item": {
    "slug": "auto-skill-hunter",
    "name": "Auto Skill Hunter",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/wanng-ide/auto-skill-hunter",
    "canonicalUrl": "https://clawhub.ai/wanng-ide/auto-skill-hunter",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/auto-skill-hunter",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=auto-skill-hunter",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "claw.json",
      "src/hunt.js"
    ],
    "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/auto-skill-hunter"
    },
    "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/auto-skill-hunter",
    "agentPageUrl": "https://openagent3.xyz/skills/auto-skill-hunter/agent",
    "manifestUrl": "https://openagent3.xyz/skills/auto-skill-hunter/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/auto-skill-hunter/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": "Auto Skill Hunter",
        "body": "Auto Skill Hunter continuously expands an agent's capability stack with task-relevant skills, then explains why each selected skill is worth trying."
      },
      {
        "title": "When to Use",
        "body": "Use this skill when at least one of the following is true:\n\nThe user asks for a task that current skills cannot solve reliably.\nSimilar issues keep appearing across recent sessions.\nThe user explicitly asks to discover/install better skills.\nThe agent needs proactive capability growth on a timer."
      },
      {
        "title": "High-Value Outcomes",
        "body": "Faster discovery of practical skills for real unresolved tasks.\nLower manual browsing effort on ClawHub.\nBetter skill stack diversity through complementarity scoring.\nSafer adoption via bounded install count and runnable checks."
      },
      {
        "title": "Usage",
        "body": "node skills/skill-hunter/src/hunt.js"
      },
      {
        "title": "Common Commands",
        "body": "# 1) Full automatic patrol\nnode skills/skill-hunter/src/hunt.js --auto\n\n# 2) Targeted hunt for a specific unresolved problem\nnode skills/skill-hunter/src/hunt.js --query \"Cannot reliably fetch web pages and summarize key insights\"\n\n# 3) Preview only (no write/install)\nnode skills/skill-hunter/src/hunt.js --dry-run\n\n# 4) Cap per-run installation count\nnode skills/skill-hunter/src/hunt.js --max-install 2"
      },
      {
        "title": "Core Workflow",
        "body": "Extract unresolved problems and topic signals from recent chat/session memory.\nSearch ClawHub with trending feeds and query endpoints.\nScore candidates with multi-factor ranking:\n\nissue relevance\nprofile and personality fit (USER.md + personality state)\ncomplementarity with already installed skills\nquality signals such as stars/downloads (when available)\n\n\nInstall top candidates with a runnable entry and self-test fallback.\nProduce a concise recommendation report with strengths, scenarios, and selection reasons."
      },
      {
        "title": "Best-Fit Scenarios",
        "body": "A user asks for a task that current skills cannot solve well.\nRecent sessions show repeated failures or unresolved tickets.\nThe agent needs proactive capability growth without manual curation.\nThe team wants a lightweight \"discover -> test -> keep/remove\" loop."
      },
      {
        "title": "Operating Modes",
        "body": "Auto patrol mode: --auto for periodic capability growth.\nTargeted mode: --query \"...\" when a specific user problem is known.\nSafe preview mode: --dry-run before enabling real installs."
      },
      {
        "title": "Recommended Execution Policy",
        "body": "Start with --dry-run in new environments.\nUse --max-install 1~2 to avoid noisy bulk installs.\nRe-run with a focused --query when no candidate passes threshold.\nKeep only skills that survive at least one real task run."
      },
      {
        "title": "Scheduled Trigger Recommendation",
        "body": "For continuous value, run Auto Skill Hunter on a timer:\n\nEvery 30 min for high-change or fast-moving projects\nEvery 60 min for normal workflows\nEvery 120 min for stable environments\n\nThis cadence keeps capability coverage fresh and reduces reaction lag when new user needs appear."
      },
      {
        "title": "Suggested Cron-Style Routine",
        "body": "# High-change projects\n*/30 * * * * node /path/to/workspace/skills/skill-hunter/src/hunt.js --auto --max-install 1\n\n# Normal projects\n0 * * * * node /path/to/workspace/skills/skill-hunter/src/hunt.js --auto --max-install 2"
      },
      {
        "title": "Installation Policy",
        "body": "Defaults to max 2 installations per run (configurable with --max-install or env).\nSkips already-installed skills.\nFalls back to scaffold mode when remote clone fails."
      },
      {
        "title": "Safety and Quality Guardrails",
        "body": "Never overwrite existing skill folders.\nPrefer small, frequent patrols over large one-shot installs.\nKeep report output concise and action-oriented.\nDisable outbound reporting during local tests with SKILL_HUNTER_NO_REPORT=1."
      }
    ],
    "body": "Auto Skill Hunter\n\nAuto Skill Hunter continuously expands an agent's capability stack with task-relevant skills, then explains why each selected skill is worth trying.\n\nWhen to Use\n\nUse this skill when at least one of the following is true:\n\nThe user asks for a task that current skills cannot solve reliably.\nSimilar issues keep appearing across recent sessions.\nThe user explicitly asks to discover/install better skills.\nThe agent needs proactive capability growth on a timer.\nHigh-Value Outcomes\nFaster discovery of practical skills for real unresolved tasks.\nLower manual browsing effort on ClawHub.\nBetter skill stack diversity through complementarity scoring.\nSafer adoption via bounded install count and runnable checks.\nUsage\nnode skills/skill-hunter/src/hunt.js\n\nCommon Commands\n# 1) Full automatic patrol\nnode skills/skill-hunter/src/hunt.js --auto\n\n# 2) Targeted hunt for a specific unresolved problem\nnode skills/skill-hunter/src/hunt.js --query \"Cannot reliably fetch web pages and summarize key insights\"\n\n# 3) Preview only (no write/install)\nnode skills/skill-hunter/src/hunt.js --dry-run\n\n# 4) Cap per-run installation count\nnode skills/skill-hunter/src/hunt.js --max-install 2\n\nCore Workflow\nExtract unresolved problems and topic signals from recent chat/session memory.\nSearch ClawHub with trending feeds and query endpoints.\nScore candidates with multi-factor ranking:\nissue relevance\nprofile and personality fit (USER.md + personality state)\ncomplementarity with already installed skills\nquality signals such as stars/downloads (when available)\nInstall top candidates with a runnable entry and self-test fallback.\nProduce a concise recommendation report with strengths, scenarios, and selection reasons.\nBest-Fit Scenarios\nA user asks for a task that current skills cannot solve well.\nRecent sessions show repeated failures or unresolved tickets.\nThe agent needs proactive capability growth without manual curation.\nThe team wants a lightweight \"discover -> test -> keep/remove\" loop.\nOperating Modes\nAuto patrol mode: --auto for periodic capability growth.\nTargeted mode: --query \"...\" when a specific user problem is known.\nSafe preview mode: --dry-run before enabling real installs.\nRecommended Execution Policy\nStart with --dry-run in new environments.\nUse --max-install 1~2 to avoid noisy bulk installs.\nRe-run with a focused --query when no candidate passes threshold.\nKeep only skills that survive at least one real task run.\nScheduled Trigger Recommendation\n\nFor continuous value, run Auto Skill Hunter on a timer:\n\nEvery 30 min for high-change or fast-moving projects\nEvery 60 min for normal workflows\nEvery 120 min for stable environments\n\nThis cadence keeps capability coverage fresh and reduces reaction lag when new user needs appear.\n\nSuggested Cron-Style Routine\n# High-change projects\n*/30 * * * * node /path/to/workspace/skills/skill-hunter/src/hunt.js --auto --max-install 1\n\n# Normal projects\n0 * * * * node /path/to/workspace/skills/skill-hunter/src/hunt.js --auto --max-install 2\n\nInstallation Policy\nDefaults to max 2 installations per run (configurable with --max-install or env).\nSkips already-installed skills.\nFalls back to scaffold mode when remote clone fails.\nSafety and Quality Guardrails\nNever overwrite existing skill folders.\nPrefer small, frequent patrols over large one-shot installs.\nKeep report output concise and action-oriented.\nDisable outbound reporting during local tests with SKILL_HUNTER_NO_REPORT=1."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wanng-ide/auto-skill-hunter",
    "publisherUrl": "https://clawhub.ai/wanng-ide/auto-skill-hunter",
    "owner": "wanng-ide",
    "version": "1.0.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/auto-skill-hunter",
    "downloadUrl": "https://openagent3.xyz/downloads/auto-skill-hunter",
    "agentUrl": "https://openagent3.xyz/skills/auto-skill-hunter/agent",
    "manifestUrl": "https://openagent3.xyz/skills/auto-skill-hunter/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/auto-skill-hunter/agent.md"
  }
}