{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agent-registry",
    "name": "Agent Registry",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/MaTriXy/agent-registry",
    "canonicalUrl": "https://clawhub.ai/MaTriXy/agent-registry",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agent-registry",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-registry",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CLAUDE.md",
      "README.md",
      "SKILL.md",
      "bin/build-release-artifact.sh",
      "bin/cli.js",
      "bin/get.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/agent-registry"
    },
    "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/agent-registry",
    "agentPageUrl": "https://openagent3.xyz/skills/agent-registry/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-registry/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-registry/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": "Agent Registry",
        "body": "Lazy-loading system for Claude Code agents. Eliminates the \"~16k tokens\" warning by loading agents on-demand."
      },
      {
        "title": "CRITICAL RULE",
        "body": "NEVER assume agents are pre-loaded. Always use this registry to discover and load agents."
      },
      {
        "title": "Workflow",
        "body": "User Request → search_agents(intent) → select best match → get_agent(name) → execute with agent"
      },
      {
        "title": "Available Commands",
        "body": "CommandWhen to UseExamplelist.jsUser asks \"what agents do I have\" or needs overviewbun bin/list.jssearch.jsFind agents matching user intent (ALWAYS do this first)bun bin/search.js \"code review security\"search-paged.jsPaged search for large registries (300+ agents)bun bin/search-paged.js \"query\" --page 1 --page-size 10get.jsLoad a specific agent's full instructionsbun bin/get.js code-reviewer"
      },
      {
        "title": "Search First Pattern",
        "body": "Extract intent keywords from user request\nRun search: bun bin/search.js \"<keywords>\"\nReview results: Check relevance scores (0.0-1.0)\nLoad if needed: bun bin/get.js <agent-name>\nExecute: Follow the loaded agent's instructions"
      },
      {
        "title": "Example",
        "body": "User: \"Can you review my authentication code for security issues?\"\n\n# Step 1: Search for relevant agents\nbun bin/search.js \"code review security authentication\"\n\n# Output:\n# Found 2 matching agents:\n#   1. security-auditor (score: 0.89) - Analyzes code for security vulnerabilities\n#   2. code-reviewer (score: 0.71) - General code review and best practices\n\n# Step 2: Load the best match\nbun bin/get.js security-auditor\n\n# Step 3: Follow loaded agent instructions for the task"
      },
      {
        "title": "Step 1: Install the Skill",
        "body": "Quick Install (Recommended):\n\n# Using Skills CLI (recommended)\nnpx skills add MaTriXy/Agent-Registry@agent-registry\n\n# Discover skills interactively\nnpx skills find\n\n# Update existing skills\nnpx skills update\n\nTraditional Install:\n\n# User-level installation\n./install.sh\n\n# OR project-level installation\n./install.sh --project\n\n# Optional: install enhanced interactive UI dependency\n./install.sh --install-deps\n\nWhat install.sh does:\n\nCopies skill files to ~/.claude/skills/agent-registry/\nCreates empty registry structure\nOptionally installs dependencies via --install-deps (@clack/prompts for enhanced UI)"
      },
      {
        "title": "Step 2: Migrate Your Agents",
        "body": "Run the interactive migration script:\n\ncd ~/.claude/skills/agent-registry\nbun bin/init.js\n# Optional destructive mode:\nbun bin/init.js --move\n\nInteractive selection modes:\n\nWith @clack/prompts (default): Beautiful checkbox UI with category grouping, token indicators, and paging\n\nArrow keys navigate, Space toggle, Enter confirm\nVisual indicators: [green] <1k tokens, [yellow] 1-3k, [red] >3k\nGrouped by subdirectory\n\n\n\nFallback: Text-based number input\n\nEnter comma-separated numbers (e.g., 1,3,5)\nType all to migrate everything\n\nWhat init.js does:\n\nScans ~/.claude/agents/ and .claude/agents/ for agent files\nDisplays available agents with metadata\nLets you interactively select which to migrate\nCopies selected agents to the registry by default (--move is explicit opt-in)\nBuilds search index (registry.json)"
      },
      {
        "title": "Dependencies",
        "body": "Bun (ships with Claude Code) — zero additional dependencies for core functionality\n@clack/prompts: Optional enhanced interactive selection UI (install via ./install.sh --install-deps)"
      },
      {
        "title": "Registry Location",
        "body": "Global: ~/.claude/skills/agent-registry/\nProject: .claude/skills/agent-registry/ (optional override)\n\nAgents not migrated remain in their original locations and load normally (contributing to token overhead)."
      }
    ],
    "body": "Agent Registry\n\nLazy-loading system for Claude Code agents. Eliminates the \"~16k tokens\" warning by loading agents on-demand.\n\nCRITICAL RULE\n\nNEVER assume agents are pre-loaded. Always use this registry to discover and load agents.\n\nWorkflow\nUser Request → search_agents(intent) → select best match → get_agent(name) → execute with agent\n\nAvailable Commands\nCommand\tWhen to Use\tExample\nlist.js\tUser asks \"what agents do I have\" or needs overview\tbun bin/list.js\nsearch.js\tFind agents matching user intent (ALWAYS do this first)\tbun bin/search.js \"code review security\"\nsearch-paged.js\tPaged search for large registries (300+ agents)\tbun bin/search-paged.js \"query\" --page 1 --page-size 10\nget.js\tLoad a specific agent's full instructions\tbun bin/get.js code-reviewer\nSearch First Pattern\nExtract intent keywords from user request\nRun search: bun bin/search.js \"<keywords>\"\nReview results: Check relevance scores (0.0-1.0)\nLoad if needed: bun bin/get.js <agent-name>\nExecute: Follow the loaded agent's instructions\nExample\n\nUser: \"Can you review my authentication code for security issues?\"\n\n# Step 1: Search for relevant agents\nbun bin/search.js \"code review security authentication\"\n\n# Output:\n# Found 2 matching agents:\n#   1. security-auditor (score: 0.89) - Analyzes code for security vulnerabilities\n#   2. code-reviewer (score: 0.71) - General code review and best practices\n\n# Step 2: Load the best match\nbun bin/get.js security-auditor\n\n# Step 3: Follow loaded agent instructions for the task\n\nInstallation\nStep 1: Install the Skill\n\nQuick Install (Recommended):\n\n# Using Skills CLI (recommended)\nnpx skills add MaTriXy/Agent-Registry@agent-registry\n\n# Discover skills interactively\nnpx skills find\n\n# Update existing skills\nnpx skills update\n\n\nTraditional Install:\n\n# User-level installation\n./install.sh\n\n# OR project-level installation\n./install.sh --project\n\n# Optional: install enhanced interactive UI dependency\n./install.sh --install-deps\n\n\nWhat install.sh does:\n\nCopies skill files to ~/.claude/skills/agent-registry/\nCreates empty registry structure\nOptionally installs dependencies via --install-deps (@clack/prompts for enhanced UI)\nStep 2: Migrate Your Agents\n\nRun the interactive migration script:\n\ncd ~/.claude/skills/agent-registry\nbun bin/init.js\n# Optional destructive mode:\nbun bin/init.js --move\n\n\nInteractive selection modes:\n\nWith @clack/prompts (default): Beautiful checkbox UI with category grouping, token indicators, and paging\n\nArrow keys navigate, Space toggle, Enter confirm\nVisual indicators: [green] <1k tokens, [yellow] 1-3k, [red] >3k\nGrouped by subdirectory\n\nFallback: Text-based number input\n\nEnter comma-separated numbers (e.g., 1,3,5)\nType all to migrate everything\n\nWhat init.js does:\n\nScans ~/.claude/agents/ and .claude/agents/ for agent files\nDisplays available agents with metadata\nLets you interactively select which to migrate\nCopies selected agents to the registry by default (--move is explicit opt-in)\nBuilds search index (registry.json)\nDependencies\nBun (ships with Claude Code) — zero additional dependencies for core functionality\n@clack/prompts: Optional enhanced interactive selection UI (install via ./install.sh --install-deps)\nRegistry Location\nGlobal: ~/.claude/skills/agent-registry/\nProject: .claude/skills/agent-registry/ (optional override)\n\nAgents not migrated remain in their original locations and load normally (contributing to token overhead)."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/MaTriXy/agent-registry",
    "publisherUrl": "https://clawhub.ai/MaTriXy/agent-registry",
    "owner": "MaTriXy",
    "version": "2.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agent-registry",
    "downloadUrl": "https://openagent3.xyz/downloads/agent-registry",
    "agentUrl": "https://openagent3.xyz/skills/agent-registry/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-registry/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-registry/agent.md"
  }
}