{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skillsindex-mcp",
    "name": "Skills Indec MCP",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/thomasblc/skillsindex-mcp",
    "canonicalUrl": "https://clawhub.ai/thomasblc/skillsindex-mcp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skillsindex-mcp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillsindex-mcp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "skill.json"
    ],
    "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/skillsindex-mcp"
    },
    "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/skillsindex-mcp",
    "agentPageUrl": "https://openagent3.xyz/skills/skillsindex-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skillsindex-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skillsindex-mcp/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": "SkillsIndex MCP",
        "body": "Search, score, and submit AI agent tools from SkillsIndex"
      },
      {
        "title": "What this skill does",
        "body": "Gives your AI agent read/write access to the SkillsIndex public directory — 11,000+ MCP servers, Claude skills, GPT actions, and IDE plugins, each scored on security, utility, maintenance, and uniqueness."
      },
      {
        "title": "Security & transparency",
        "body": "No credentials required — no API keys, no GitHub tokens, no secrets\nNo local file access — the skill makes no filesystem operations\nNetwork calls only — all calls go to skillsindex.dev (public REST API over HTTPS) and npmjs.com (for npx to download the package)\nRead-only by default — search, get_tool, get_top_rated, check_security are all read-only\nWrite operations — submit_tool POSTs a tool name + URL to skillsindex.dev/api/mcp/submit (public endpoint, no auth); subscribe POSTs an email to skillsindex.dev/api/subscribe\nOpen source — full source code at https://github.com/thomasblc/skillsindex in the mcp/ directory\nNo data exfiltration — the skill never reads or transmits your local files, environment variables, or system data"
      },
      {
        "title": "How it works",
        "body": "The skill runs as a local stdio MCP server via npx skillsindex-mcp. It bundles the compiled TypeScript and calls the SkillsIndex public API endpoints. No server is installed permanently — npx runs the package on demand.\n\nExact network endpoints called:\n\nToolEndpointMethodsearch_toolshttps://skillsindex.dev (Supabase REST API, anon key)GETget_toolhttps://skillsindex.dev (Supabase REST API, anon key)GETget_top_ratedhttps://skillsindex.dev (Supabase REST API, anon key)GETcheck_securityhttps://skillsindex.dev (Supabase REST API, anon key)GETsubmit_toolhttps://skillsindex.dev/api/mcp/submitPOSTsubscribehttps://skillsindex.dev/api/subscribePOST\n\nThe Supabase anon key is a public read-only key — it only allows reading published tool data. This is the same key embedded in every SkillsIndex web page."
      },
      {
        "title": "search_tools",
        "body": "Search by keyword, ecosystem, or category. Returns tools ranked by overall score.\n\nquery:      \"postgres database MCP server\"\necosystem:  mcp_server | claude_skill | gpt_action | openclaw_skill | plugin\ncategory:   databases-storage | browser-automation | code-execution | ...\nlimit:      1–20"
      },
      {
        "title": "get_tool",
        "body": "Full details for a tool by slug: security score, GitHub stats, pricing, install difficulty.\n\nslug:  \"filesystem-mcp-server\""
      },
      {
        "title": "get_top_rated",
        "body": "Top-scored tools, optionally filtered by ecosystem or category."
      },
      {
        "title": "check_security",
        "body": "Security audit report: score (0–5), risk flags, audit notes based on static source analysis.\n\nslug:  \"tool-slug\"     (preferred)\nname:  \"Tool Name\"     (fuzzy match)"
      },
      {
        "title": "submit_tool",
        "body": "Submit a new tool for indexing. Sends name, URL, description to SkillsIndex review queue.\n\nname:         \"My MCP Server\"\ngithub_url:   \"https://github.com/user/repo\"\ndescription:  \"What the tool does\"\necosystem:    \"mcp_server\"\ncategory:     \"databases-storage\""
      },
      {
        "title": "subscribe",
        "body": "Subscribe an email to The Weekly Index — new tools + security alerts every Thursday."
      },
      {
        "title": "Installation",
        "body": "No configuration needed. Add to claude_desktop_config.json:\n\n{\n  \"mcpServers\": {\n    \"skillsindex\": {\n      \"command\": \"npx\",\n      \"args\": [\"skillsindex-mcp\"]\n    }\n  }\n}"
      },
      {
        "title": "Data",
        "body": "11,000+ tools across 5 ecosystems\nScoring formula: security (30%) + utility (30%) + maintenance (25%) + uniqueness (15%)\nRefreshed weekly via GitHub API\nSecurity scores from static analysis of open-source code (no proprietary data)"
      },
      {
        "title": "Source code",
        "body": "https://github.com/thomasblc/skillsindex → mcp/src/index.ts\n\nFull source is auditable. The compiled output in dist/index.js matches the TypeScript source exactly."
      },
      {
        "title": "Links",
        "body": "Directory: skillsindex.dev\nnpm: npmjs.com/package/skillsindex-mcp\nSource: github.com/thomasblc/skillsindex\nScoring methodology: skillsindex.dev/methodology/"
      }
    ],
    "body": "SkillsIndex MCP\n\nSearch, score, and submit AI agent tools from SkillsIndex\n\nWhat this skill does\n\nGives your AI agent read/write access to the SkillsIndex public directory — 11,000+ MCP servers, Claude skills, GPT actions, and IDE plugins, each scored on security, utility, maintenance, and uniqueness.\n\nSecurity & transparency\nNo credentials required — no API keys, no GitHub tokens, no secrets\nNo local file access — the skill makes no filesystem operations\nNetwork calls only — all calls go to skillsindex.dev (public REST API over HTTPS) and npmjs.com (for npx to download the package)\nRead-only by default — search, get_tool, get_top_rated, check_security are all read-only\nWrite operations — submit_tool POSTs a tool name + URL to skillsindex.dev/api/mcp/submit (public endpoint, no auth); subscribe POSTs an email to skillsindex.dev/api/subscribe\nOpen source — full source code at https://github.com/thomasblc/skillsindex in the mcp/ directory\nNo data exfiltration — the skill never reads or transmits your local files, environment variables, or system data\nHow it works\n\nThe skill runs as a local stdio MCP server via npx skillsindex-mcp. It bundles the compiled TypeScript and calls the SkillsIndex public API endpoints. No server is installed permanently — npx runs the package on demand.\n\nExact network endpoints called:\n\nTool\tEndpoint\tMethod\nsearch_tools\thttps://skillsindex.dev (Supabase REST API, anon key)\tGET\nget_tool\thttps://skillsindex.dev (Supabase REST API, anon key)\tGET\nget_top_rated\thttps://skillsindex.dev (Supabase REST API, anon key)\tGET\ncheck_security\thttps://skillsindex.dev (Supabase REST API, anon key)\tGET\nsubmit_tool\thttps://skillsindex.dev/api/mcp/submit\tPOST\nsubscribe\thttps://skillsindex.dev/api/subscribe\tPOST\n\nThe Supabase anon key is a public read-only key — it only allows reading published tool data. This is the same key embedded in every SkillsIndex web page.\n\nTools\nsearch_tools\n\nSearch by keyword, ecosystem, or category. Returns tools ranked by overall score.\n\nquery:      \"postgres database MCP server\"\necosystem:  mcp_server | claude_skill | gpt_action | openclaw_skill | plugin\ncategory:   databases-storage | browser-automation | code-execution | ...\nlimit:      1–20\n\nget_tool\n\nFull details for a tool by slug: security score, GitHub stats, pricing, install difficulty.\n\nslug:  \"filesystem-mcp-server\"\n\nget_top_rated\n\nTop-scored tools, optionally filtered by ecosystem or category.\n\ncheck_security\n\nSecurity audit report: score (0–5), risk flags, audit notes based on static source analysis.\n\nslug:  \"tool-slug\"     (preferred)\nname:  \"Tool Name\"     (fuzzy match)\n\nsubmit_tool\n\nSubmit a new tool for indexing. Sends name, URL, description to SkillsIndex review queue.\n\nname:         \"My MCP Server\"\ngithub_url:   \"https://github.com/user/repo\"\ndescription:  \"What the tool does\"\necosystem:    \"mcp_server\"\ncategory:     \"databases-storage\"\n\nsubscribe\n\nSubscribe an email to The Weekly Index — new tools + security alerts every Thursday.\n\nInstallation\n\nNo configuration needed. Add to claude_desktop_config.json:\n\n{\n  \"mcpServers\": {\n    \"skillsindex\": {\n      \"command\": \"npx\",\n      \"args\": [\"skillsindex-mcp\"]\n    }\n  }\n}\n\nData\n11,000+ tools across 5 ecosystems\nScoring formula: security (30%) + utility (30%) + maintenance (25%) + uniqueness (15%)\nRefreshed weekly via GitHub API\nSecurity scores from static analysis of open-source code (no proprietary data)\nSource code\n\nhttps://github.com/thomasblc/skillsindex → mcp/src/index.ts\n\nFull source is auditable. The compiled output in dist/index.js matches the TypeScript source exactly.\n\nLinks\nDirectory: skillsindex.dev\nnpm: npmjs.com/package/skillsindex-mcp\nSource: github.com/thomasblc/skillsindex\nScoring methodology: skillsindex.dev/methodology/"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/thomasblc/skillsindex-mcp",
    "publisherUrl": "https://clawhub.ai/thomasblc/skillsindex-mcp",
    "owner": "thomasblc",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skillsindex-mcp",
    "downloadUrl": "https://openagent3.xyz/downloads/skillsindex-mcp",
    "agentUrl": "https://openagent3.xyz/skills/skillsindex-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skillsindex-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skillsindex-mcp/agent.md"
  }
}