{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skill-finder",
    "name": "Skill Finder",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/skill-finder",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/skill-finder",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skill-finder",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-finder",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "categories.md",
      "evaluate.md",
      "memory-template.md",
      "migration.md",
      "search.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",
      "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-finder"
    },
    "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-finder",
    "agentPageUrl": "https://openagent3.xyz/skills/skill-finder/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-finder/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-finder/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": "When to Use",
        "body": "User asks how to do something, wonders whether a skill exists, wants a new capability, or asks for the best skill for a job. Use before solving manually when an installable skill could extend the agent, replace a weak skill, or offer a safer alternative."
      },
      {
        "title": "Architecture",
        "body": "Memory lives in ~/skill-finder/. If ~/skill-finder/ does not exist or is empty, run setup.md.\n\n~/skill-finder/\n├── memory.md     # Source mode + preferences + liked/passed skills\n└── searches.md   # Recent search history (optional)"
      },
      {
        "title": "Migration",
        "body": "If upgrading from a previous version, see migration.md for data migration steps.\nThe agent MUST check for legacy memory structure before proceeding."
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileSetupsetup.mdMemory templatememory-template.mdSearch strategiessearch.mdEvaluation criteriaevaluate.mdSkill categoriescategories.mdEdge casestroubleshooting.md"
      },
      {
        "title": "Activation Signals",
        "body": "Activate when the user says things like:\n\n\"How do I do X?\"\n\"Is there a skill for this?\"\n\"Can you do this better?\"\n\"Find a skill for X\"\n\"I need a safer or more maintained option\"\n\"What should I install for this task?\"\n\nAlso activate when the user describes a missing capability, a repetitive workflow, or frustration with a current skill."
      },
      {
        "title": "Search Sources",
        "body": "This skill can search two ecosystems:\n\nSourceSearchInstallBest forClawHubnpx clawhub search \"query\"npx clawhub install <slug>Curated registry search with built-in inspectionSkills.shnpx skills find [query]npx skills add <owner/repo@skill>Broad open ecosystem from the skills CLI\n\nDefault mode: search both sources, then compare results together.\n\nConfigurable modes:\n\nboth — recommended default\nclawhub — only search ClawHub\nskills.sh — only search the Skills.sh ecosystem\n\nStore the current mode in ~/skill-finder/memory.md. If the user has no saved preference yet, explain the two sources once, recommend both, and save the explicit choice."
      },
      {
        "title": "Security Note",
        "body": "This skill uses npx clawhub and npx skills to discover and install skills from two different ecosystems. Review candidates before installation, keep installs opt-in, and keep the source attached to every recommendation."
      },
      {
        "title": "Data Storage",
        "body": "This skill stores local preference data in ~/skill-finder/:\n\nSource mode, explicit preferences, liked skills, and passed skills in the local memory file inside ~/skill-finder/\nOptional recent search history in a local search log inside ~/skill-finder/\n\nCreate on first use: mkdir -p ~/skill-finder"
      },
      {
        "title": "1. Search Both Sources by Default",
        "body": "Unless the user has explicitly chosen otherwise, search ClawHub and Skills.sh for the same need, then compare the strongest results together.\n\nNever assume a Skills.sh result can be installed with clawhub, or the reverse. Keep the source and install command attached to every recommendation."
      },
      {
        "title": "2. Trigger on Capability Gaps, Not Just Explicit Search Requests",
        "body": "Do not wait only for \"find a skill.\" Activate when the user describes missing functionality, asks how to do a task faster, or wants a better tool for a job."
      },
      {
        "title": "3. Search by Need, Not Name",
        "body": "User says \"help with PDFs\" - think about what they actually need:\n\nEdit? -> npx clawhub search \"pdf edit\" and npx skills find pdf edit\nCreate? -> npx clawhub search \"pdf generate\" and npx skills find pdf generate\nExtract? -> npx clawhub search \"pdf parse\" and npx skills find pdf parse"
      },
      {
        "title": "4. Evaluate Before Recommending",
        "body": "Never recommend blindly. Inspect strong candidates and check evaluate.md criteria:\n\nDescription clarity\nDownload count (popularity = maintenance)\nLast update (recent = active)\nAuthor or repository reputation\nInstall scope and friction\n\nFor Skills.sh candidates, pay attention to the package source and install string the CLI returns."
      },
      {
        "title": "5. Present a Decision, Not a Dump",
        "body": "Don't just list skills. Explain why each fits, who it is best for, and why the winner wins:\n\n\"Best fit: pdf-editor from ClawHub — handles form filling and annotations, 2.3k downloads, updated last week. Matches your need for editing contracts better than the Skills.sh options.\"\n\nWhen there are multiple good fits, rank the top 1-3 and call out tradeoffs clearly."
      },
      {
        "title": "6. Learn Preferences and Source Mode",
        "body": "When user explicitly states what they value, confirm and update ~/skill-finder/memory.md:\n\n\"Search both by default\" -> set source mode to both\n\"Only use Skills.sh for this workspace\" -> set source mode to skills.sh\n\"Only check ClawHub\" -> set source mode to clawhub\n\"I prefer minimal skills\" -> add to Preferences\n\"This one is great\" -> add to Liked with reason\n\"Too verbose\" -> add to Passed with reason\n\nDo not infer hidden preferences from behavior-only signals."
      },
      {
        "title": "7. Check Memory First",
        "body": "Before recommending, read memory.md:\n\nRespect saved source mode unless the user overrides it\nSkip skills similar to Passed ones\nFavor qualities from Liked ones\nApply stated Preferences"
      },
      {
        "title": "8. Respect Installation and Security Boundaries",
        "body": "If a candidate skill is marked risky by scanner output, or the install path is unclear:\n\nExplain the warning or ambiguity first\nPrefer a safer alternative\nDo not run force-install flags for the user\nDo not auto-accept install prompts with -y\nDo not choose global install scope unless the user explicitly wants it\nInstall only with explicit user consent"
      },
      {
        "title": "9. Fallback Gracefully",
        "body": "If nothing is strong enough:\n\nSay what was searched\nSay which source mode was used\nExplain why the matches are weak\nHelp directly or suggest creating a purpose-built skill"
      },
      {
        "title": "Search Commands",
        "body": "# ClawHub search and inspect\nnpx clawhub search \"query\"\nnpx clawhub inspect <slug>\nnpx clawhub install <slug>\nnpx clawhub list\n\n# Skills.sh ecosystem\nnpx skills find [query]\nnpx skills add <owner/repo@skill>\nnpx skills list\nnpx skills check\nnpx skills update\n\n# Example install string returned by `npx skills find`\nnpx skills add vercel-labs/agent-skills@vercel-react-best-practices"
      },
      {
        "title": "Workflow",
        "body": "Detect - Is the user describing a capability gap or installable need?\nLoad memory - Read ~/skill-finder/memory.md for source mode and preferences\nUnderstand - What does user actually need?\nSearch - Use both by default, or the saved single-source mode\nEvaluate - Check quality signals (see evaluate.md)\nCompare - Rank results across both sources by fit + quality\nRecommend - Top 1-3 with clear reasoning and a winner\nInstall or fallback - Install only with consent, otherwise help directly\nLearn - Store explicit feedback in memory"
      },
      {
        "title": "Recommendation Format",
        "body": "When presenting results, prefer this structure:\n\nBest fit: <slug or owner/repo@skill>\nSource: <ClawHub or Skills.sh>\nWhy it wins: <1-2 lines>\nInstall: <exact command>\nTradeoffs: <what it does not cover or where alternative is stronger>\nAlternatives: <slug>, <slug>\nNext step: Install now or continue without installing"
      },
      {
        "title": "Common Traps",
        "body": "Waiting for the exact phrase \"find a skill\" -> misses proactive discovery moments\nSearching generic terms -> gets noise. Be specific: \"react testing\" not \"testing\"\nSearching only one ecosystem when the saved mode is both\nRecommending by name match only -> misses better alternatives with different names\nMixing install commands between ClawHub and Skills.sh\nIgnoring download counts -> low downloads often means abandoned\nNot checking last update -> outdated skills cause problems"
      },
      {
        "title": "Security & Privacy",
        "body": "Data that leaves your machine:\n\nSearch queries sent to ClawHub registry (public search)\nSearch queries sent through the skills CLI / Skills.sh ecosystem\n\nData that stays local:\n\nAll preferences in ~/skill-finder/memory.md\nSearch history (if enabled)\n\nThis skill does NOT:\n\nInstall skills without user consent\nUse force-install flags to skip scanner warnings\nAuto-confirm npx skills add with -y\nSwitch to global install scope silently\nCollect hidden behavior data\nAccess files outside ~/skill-finder/"
      },
      {
        "title": "Related Skills",
        "body": "Install with npx clawhub install <slug> if user confirms:\n\nskill-manager — manages installed skills, suggests updates\nskill-builder — creates new skills from scratch\nskill-update — updates existing skills"
      },
      {
        "title": "Feedback",
        "body": "If useful: clawhub star skill-finder\nStay updated: clawhub sync"
      }
    ],
    "body": "When to Use\n\nUser asks how to do something, wonders whether a skill exists, wants a new capability, or asks for the best skill for a job. Use before solving manually when an installable skill could extend the agent, replace a weak skill, or offer a safer alternative.\n\nArchitecture\n\nMemory lives in ~/skill-finder/. If ~/skill-finder/ does not exist or is empty, run setup.md.\n\n~/skill-finder/\n├── memory.md     # Source mode + preferences + liked/passed skills\n└── searches.md   # Recent search history (optional)\n\nMigration\n\nIf upgrading from a previous version, see migration.md for data migration steps. The agent MUST check for legacy memory structure before proceeding.\n\nQuick Reference\nTopic\tFile\nSetup\tsetup.md\nMemory template\tmemory-template.md\nSearch strategies\tsearch.md\nEvaluation criteria\tevaluate.md\nSkill categories\tcategories.md\nEdge cases\ttroubleshooting.md\nActivation Signals\n\nActivate when the user says things like:\n\n\"How do I do X?\"\n\"Is there a skill for this?\"\n\"Can you do this better?\"\n\"Find a skill for X\"\n\"I need a safer or more maintained option\"\n\"What should I install for this task?\"\n\nAlso activate when the user describes a missing capability, a repetitive workflow, or frustration with a current skill.\n\nSearch Sources\n\nThis skill can search two ecosystems:\n\nSource\tSearch\tInstall\tBest for\nClawHub\tnpx clawhub search \"query\"\tnpx clawhub install <slug>\tCurated registry search with built-in inspection\nSkills.sh\tnpx skills find [query]\tnpx skills add <owner/repo@skill>\tBroad open ecosystem from the skills CLI\n\nDefault mode: search both sources, then compare results together.\n\nConfigurable modes:\n\nboth — recommended default\nclawhub — only search ClawHub\nskills.sh — only search the Skills.sh ecosystem\n\nStore the current mode in ~/skill-finder/memory.md. If the user has no saved preference yet, explain the two sources once, recommend both, and save the explicit choice.\n\nSecurity Note\n\nThis skill uses npx clawhub and npx skills to discover and install skills from two different ecosystems. Review candidates before installation, keep installs opt-in, and keep the source attached to every recommendation.\n\nData Storage\n\nThis skill stores local preference data in ~/skill-finder/:\n\nSource mode, explicit preferences, liked skills, and passed skills in the local memory file inside ~/skill-finder/\nOptional recent search history in a local search log inside ~/skill-finder/\n\nCreate on first use: mkdir -p ~/skill-finder\n\nCore Rules\n1. Search Both Sources by Default\n\nUnless the user has explicitly chosen otherwise, search ClawHub and Skills.sh for the same need, then compare the strongest results together.\n\nNever assume a Skills.sh result can be installed with clawhub, or the reverse. Keep the source and install command attached to every recommendation.\n\n2. Trigger on Capability Gaps, Not Just Explicit Search Requests\n\nDo not wait only for \"find a skill.\" Activate when the user describes missing functionality, asks how to do a task faster, or wants a better tool for a job.\n\n3. Search by Need, Not Name\n\nUser says \"help with PDFs\" - think about what they actually need:\n\nEdit? -> npx clawhub search \"pdf edit\" and npx skills find pdf edit\nCreate? -> npx clawhub search \"pdf generate\" and npx skills find pdf generate\nExtract? -> npx clawhub search \"pdf parse\" and npx skills find pdf parse\n4. Evaluate Before Recommending\n\nNever recommend blindly. Inspect strong candidates and check evaluate.md criteria:\n\nDescription clarity\nDownload count (popularity = maintenance)\nLast update (recent = active)\nAuthor or repository reputation\nInstall scope and friction\n\nFor Skills.sh candidates, pay attention to the package source and install string the CLI returns.\n\n5. Present a Decision, Not a Dump\n\nDon't just list skills. Explain why each fits, who it is best for, and why the winner wins:\n\n\"Best fit: pdf-editor from ClawHub — handles form filling and annotations, 2.3k downloads, updated last week. Matches your need for editing contracts better than the Skills.sh options.\"\n\nWhen there are multiple good fits, rank the top 1-3 and call out tradeoffs clearly.\n\n6. Learn Preferences and Source Mode\n\nWhen user explicitly states what they value, confirm and update ~/skill-finder/memory.md:\n\n\"Search both by default\" -> set source mode to both\n\"Only use Skills.sh for this workspace\" -> set source mode to skills.sh\n\"Only check ClawHub\" -> set source mode to clawhub\n\"I prefer minimal skills\" -> add to Preferences\n\"This one is great\" -> add to Liked with reason\n\"Too verbose\" -> add to Passed with reason\n\nDo not infer hidden preferences from behavior-only signals.\n\n7. Check Memory First\n\nBefore recommending, read memory.md:\n\nRespect saved source mode unless the user overrides it\nSkip skills similar to Passed ones\nFavor qualities from Liked ones\nApply stated Preferences\n8. Respect Installation and Security Boundaries\n\nIf a candidate skill is marked risky by scanner output, or the install path is unclear:\n\nExplain the warning or ambiguity first\nPrefer a safer alternative\nDo not run force-install flags for the user\nDo not auto-accept install prompts with -y\nDo not choose global install scope unless the user explicitly wants it\nInstall only with explicit user consent\n9. Fallback Gracefully\n\nIf nothing is strong enough:\n\nSay what was searched\nSay which source mode was used\nExplain why the matches are weak\nHelp directly or suggest creating a purpose-built skill\nSearch Commands\n# ClawHub search and inspect\nnpx clawhub search \"query\"\nnpx clawhub inspect <slug>\nnpx clawhub install <slug>\nnpx clawhub list\n\n# Skills.sh ecosystem\nnpx skills find [query]\nnpx skills add <owner/repo@skill>\nnpx skills list\nnpx skills check\nnpx skills update\n\n# Example install string returned by `npx skills find`\nnpx skills add vercel-labs/agent-skills@vercel-react-best-practices\n\nWorkflow\nDetect - Is the user describing a capability gap or installable need?\nLoad memory - Read ~/skill-finder/memory.md for source mode and preferences\nUnderstand - What does user actually need?\nSearch - Use both by default, or the saved single-source mode\nEvaluate - Check quality signals (see evaluate.md)\nCompare - Rank results across both sources by fit + quality\nRecommend - Top 1-3 with clear reasoning and a winner\nInstall or fallback - Install only with consent, otherwise help directly\nLearn - Store explicit feedback in memory\nRecommendation Format\n\nWhen presenting results, prefer this structure:\n\nBest fit: <slug or owner/repo@skill>\nSource: <ClawHub or Skills.sh>\nWhy it wins: <1-2 lines>\nInstall: <exact command>\nTradeoffs: <what it does not cover or where alternative is stronger>\nAlternatives: <slug>, <slug>\nNext step: Install now or continue without installing\n\nCommon Traps\nWaiting for the exact phrase \"find a skill\" -> misses proactive discovery moments\nSearching generic terms -> gets noise. Be specific: \"react testing\" not \"testing\"\nSearching only one ecosystem when the saved mode is both\nRecommending by name match only -> misses better alternatives with different names\nMixing install commands between ClawHub and Skills.sh\nIgnoring download counts -> low downloads often means abandoned\nNot checking last update -> outdated skills cause problems\nSecurity & Privacy\n\nData that leaves your machine:\n\nSearch queries sent to ClawHub registry (public search)\nSearch queries sent through the skills CLI / Skills.sh ecosystem\n\nData that stays local:\n\nAll preferences in ~/skill-finder/memory.md\nSearch history (if enabled)\n\nThis skill does NOT:\n\nInstall skills without user consent\nUse force-install flags to skip scanner warnings\nAuto-confirm npx skills add with -y\nSwitch to global install scope silently\nCollect hidden behavior data\nAccess files outside ~/skill-finder/\nRelated Skills\n\nInstall with npx clawhub install <slug> if user confirms:\n\nskill-manager — manages installed skills, suggests updates\nskill-builder — creates new skills from scratch\nskill-update — updates existing skills\nFeedback\nIf useful: clawhub star skill-finder\nStay updated: clawhub sync"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/skill-finder",
    "publisherUrl": "https://clawhub.ai/ivangdavila/skill-finder",
    "owner": "ivangdavila",
    "version": "1.1.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skill-finder",
    "downloadUrl": "https://openagent3.xyz/downloads/skill-finder",
    "agentUrl": "https://openagent3.xyz/skills/skill-finder/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-finder/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-finder/agent.md"
  }
}