{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agentskills-io",
    "name": "agentskills-io",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/killerapp/agentskills-io",
    "canonicalUrl": "https://clawhub.ai/killerapp/agentskills-io",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agentskills-io",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentskills-io",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "assets/skill-template.md",
      "references/best-practices.md",
      "references/examples.md",
      "references/specification.md",
      "references/validation.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/agentskills-io"
    },
    "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/agentskills-io",
    "agentPageUrl": "https://openagent3.xyz/skills/agentskills-io/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agentskills-io/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agentskills-io/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": "Agent Skills (agentskills.io)",
        "body": "Create portable skills for AI agents. Works with Claude Code, Cursor, GitHub Copilot, OpenAI integrations, VS Code (symlinks enable sharing across tools)."
      },
      {
        "title": "Resources",
        "body": "Specification: https://agentskills.io/specification | Validator: https://github.com/agentskills/agentskills"
      },
      {
        "title": "Structure",
        "body": "skill-name/\n├── SKILL.md          # Required (frontmatter + instructions, <5000 tokens activation)\n├── scripts/          # Optional: executable code\n├── references/       # Optional: detailed docs\n└── assets/           # Optional: templates, static files\n\nRules: Dir name = frontmatter name:. Only 3 subdirs. SKILL.md <500 lines. ~100 tokens for discovery (name+desc)."
      },
      {
        "title": "Required",
        "body": "name: 1-64 chars, lowercase alphanumeric-hyphens (^[a-z0-9]+(-[a-z0-9]+)*$)\ndescription: 1-1024 chars, include \"Use when...\" (discovery budget: ~100 tokens)"
      },
      {
        "title": "Optional",
        "body": "license: SPDX identifier (Apache-2.0, MIT) | compatibility: Environment reqs (<500 chars)\nmetadata: Key-value pairs (author, version, tags) | allowed-tools: Space-delimited tool list"
      },
      {
        "title": "Validation",
        "body": "# Install permanently (vs ephemeral uvx)\nuv tool install git+https://github.com/agentskills/agentskills#subdirectory=skills-ref\n# Or use uvx for one-shot validation\nuvx --from git+https://github.com/agentskills/agentskills#subdirectory=skills-ref skills-ref validate ./skill\n\nCommandDescriptionskills-ref validate <path>Check structure, frontmatter, token budgetsskills-ref read-properties <path>Extract metadataskills-ref to-prompt <path>Generate prompt format"
      },
      {
        "title": "Writing Rules",
        "body": "Imperative language: \"Check: command\" not \"You might want to...\"\nConcrete examples with expected output; handle common errors with solutions\nProgressive disclosure: core in SKILL.md (<5000 tokens), details in references/"
      },
      {
        "title": "Common Errors",
        "body": "ErrorFixInvalid nameLowercase alphanumeric-hyphens onlyMissing descriptionAdd description: field with \"Use when...\"Description too long<1024 chars, move details to bodyInvalid YAMLCheck indentation, quote special charsMissing SKILL.mdFilename must be exactly SKILL.mdDir name mismatchDirectory name must match name: field"
      },
      {
        "title": "Quick Workflow",
        "body": "Create: mkdir skill-name && touch skill-name/SKILL.md\nAdd frontmatter (name, description with \"Use when...\")\nWrite instructions (bullets, not prose); validate: skills-ref validate ./skill-name\nTest with AI agent, iterate; add LICENSE, push to repository"
      },
      {
        "title": "Plugin Structure (Claude Code)",
        "body": "plugin-name/\n├── .claude-plugin/plugin.json\n├── README.md, LICENSE, CHANGELOG.md  # CHANGELOG.md tracks versions\n├── skills/skill-name/SKILL.md\n├── agents/     # Optional: subagents (.md files)\n└── examples/   # Optional: full demo projects\n\nDistinctions: Plugin examples/ = runnable projects. Skill assets/ = static resources only."
      },
      {
        "title": "Batch Validation & Versioning",
        "body": "bash scripts/validate-skills-repo.sh     # Validate all skills in repo\nbash scripts/bump-changed-plugins.sh     # Auto-bump only changed plugins (semver)"
      },
      {
        "title": "Minimal Example",
        "body": "---\nname: example-skill\ndescription: Brief description. Use when doing X.\n---\n# Example Skill\n## Prerequisites\n- Required tools\n## Instructions\n1. First step: `command`\n2. Second step with example\n## Troubleshooting\n**Error**: Message → **Fix**: Solution"
      },
      {
        "title": "Symlink Sharing",
        "body": "Share skills across Claude Code, Cursor, VS Code: ln -s /path/to/skills ~/.cursor/skills"
      },
      {
        "title": "References",
        "body": "specification.md - Full YAML schema, token budgets\nexamples.md - Complete examples across platforms\nvalidation.md - Error troubleshooting\nbest-practices.md - Advanced patterns, symlink setup"
      }
    ],
    "body": "Agent Skills (agentskills.io)\n\nCreate portable skills for AI agents. Works with Claude Code, Cursor, GitHub Copilot, OpenAI integrations, VS Code (symlinks enable sharing across tools).\n\nResources\nSpecification: https://agentskills.io/specification | Validator: https://github.com/agentskills/agentskills\nStructure\nskill-name/\n├── SKILL.md          # Required (frontmatter + instructions, <5000 tokens activation)\n├── scripts/          # Optional: executable code\n├── references/       # Optional: detailed docs\n└── assets/           # Optional: templates, static files\n\n\nRules: Dir name = frontmatter name:. Only 3 subdirs. SKILL.md <500 lines. ~100 tokens for discovery (name+desc).\n\nFrontmatter\nRequired\nname: 1-64 chars, lowercase alphanumeric-hyphens (^[a-z0-9]+(-[a-z0-9]+)*$)\ndescription: 1-1024 chars, include \"Use when...\" (discovery budget: ~100 tokens)\nOptional\nlicense: SPDX identifier (Apache-2.0, MIT) | compatibility: Environment reqs (<500 chars)\nmetadata: Key-value pairs (author, version, tags) | allowed-tools: Space-delimited tool list\nValidation\n# Install permanently (vs ephemeral uvx)\nuv tool install git+https://github.com/agentskills/agentskills#subdirectory=skills-ref\n# Or use uvx for one-shot validation\nuvx --from git+https://github.com/agentskills/agentskills#subdirectory=skills-ref skills-ref validate ./skill\n\nCommand\tDescription\nskills-ref validate <path>\tCheck structure, frontmatter, token budgets\nskills-ref read-properties <path>\tExtract metadata\nskills-ref to-prompt <path>\tGenerate prompt format\nWriting Rules\nImperative language: \"Check: command\" not \"You might want to...\"\nConcrete examples with expected output; handle common errors with solutions\nProgressive disclosure: core in SKILL.md (<5000 tokens), details in references/\nCommon Errors\nError\tFix\nInvalid name\tLowercase alphanumeric-hyphens only\nMissing description\tAdd description: field with \"Use when...\"\nDescription too long\t<1024 chars, move details to body\nInvalid YAML\tCheck indentation, quote special chars\nMissing SKILL.md\tFilename must be exactly SKILL.md\nDir name mismatch\tDirectory name must match name: field\nQuick Workflow\nCreate: mkdir skill-name && touch skill-name/SKILL.md\nAdd frontmatter (name, description with \"Use when...\")\nWrite instructions (bullets, not prose); validate: skills-ref validate ./skill-name\nTest with AI agent, iterate; add LICENSE, push to repository\nPlugin Structure (Claude Code)\nplugin-name/\n├── .claude-plugin/plugin.json\n├── README.md, LICENSE, CHANGELOG.md  # CHANGELOG.md tracks versions\n├── skills/skill-name/SKILL.md\n├── agents/     # Optional: subagents (.md files)\n└── examples/   # Optional: full demo projects\n\n\nDistinctions: Plugin examples/ = runnable projects. Skill assets/ = static resources only.\n\nBatch Validation & Versioning\nbash scripts/validate-skills-repo.sh     # Validate all skills in repo\nbash scripts/bump-changed-plugins.sh     # Auto-bump only changed plugins (semver)\n\nMinimal Example\n---\nname: example-skill\ndescription: Brief description. Use when doing X.\n---\n# Example Skill\n## Prerequisites\n- Required tools\n## Instructions\n1. First step: `command`\n2. Second step with example\n## Troubleshooting\n**Error**: Message → **Fix**: Solution\n\nSymlink Sharing\n\nShare skills across Claude Code, Cursor, VS Code: ln -s /path/to/skills ~/.cursor/skills\n\nReferences\nspecification.md - Full YAML schema, token budgets\nexamples.md - Complete examples across platforms\nvalidation.md - Error troubleshooting\nbest-practices.md - Advanced patterns, symlink setup"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/killerapp/agentskills-io",
    "publisherUrl": "https://clawhub.ai/killerapp/agentskills-io",
    "owner": "killerapp",
    "version": "2.5.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agentskills-io",
    "downloadUrl": "https://openagent3.xyz/downloads/agentskills-io",
    "agentUrl": "https://openagent3.xyz/skills/agentskills-io/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agentskills-io/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agentskills-io/agent.md"
  }
}