{
  "schemaVersion": "1.0",
  "item": {
    "slug": "clawhub-skill-creator",
    "name": "Clawhub Skill Creator",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/erview/clawhub-skill-creator",
    "canonicalUrl": "https://clawhub.ai/erview/clawhub-skill-creator",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/clawhub-skill-creator",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawhub-skill-creator",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "LICENSE.txt",
      "SKILL.md",
      "_meta.json",
      "references/agent-first-design.md",
      "references/skill-structure.md",
      "references/token-optimization.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": "2026-04-23T16:43:11.935Z",
      "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/clawhub-skill-creator"
    },
    "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/clawhub-skill-creator",
    "agentPageUrl": "https://openagent3.xyz/skills/clawhub-skill-creator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawhub-skill-creator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawhub-skill-creator/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": "Clawhub Skill Creator",
        "body": "Complete guide for creating skills compatible with clawhub registry and optimized for AI agent usage."
      },
      {
        "title": "Language Rule",
        "body": "Skill description must be in English, unless context requires otherwise (examples, comments, etc. may use other languages when appropriate).\n\ndescription in frontmatter: English only\nSKILL.md body: English preferred\nExamples, code comments: Any language as needed\nReferences: Any language as appropriate for domain"
      },
      {
        "title": "Create New Skill",
        "body": "# Run initializer\n./scripts/init-skill.sh my-skill\n\n# Or manually create structure\nmkdir -p my-skill/{references,scripts,assets}\ntouch my-skill/SKILL.md my-skill/_meta.json my-skill/LICENSE.txt"
      },
      {
        "title": "Phase 1: Understand Requirements",
        "body": "Before writing any code, clarify:\n\nWhat problem does this skill solve?\n\nConcrete use cases (2-3 examples)\nTarget queries that should trigger skill\n\n\n\nWho will use this skill?\n\nAI agents (primary audience for clawhub)\nExpected context (tools available, environment)\n\n\n\nWhat resources are needed?\n\nReferences for detailed docs?\nAssets for templates?\nScripts for automation?\n\nOutput: Clear understanding of skill scope and triggers."
      },
      {
        "title": "Phase 2: Plan Structure",
        "body": "Choose pattern based on complexity:\n\nComplexityStructureWhen to UseSimpleSKILL.md only<100 lines, single purposeMedium+ references/100-300 lines, some detailsComplex+ references/ + assets/>300 lines, multi-domain\n\nDecide on resources:\n\nWhich references needed? (docs, examples, patterns)\nWhich assets needed? (templates, configs)\nWhich scripts needed? (validation, packaging)\n\nOutput: Directory structure and resource list."
      },
      {
        "title": "Phase 3: Initialize Structure",
        "body": "# Create directory\nmkdir -p my-skill/{references,scripts,assets}\n\n# Create required files\ntouch my-skill/SKILL.md\ntouch my-skill/_meta.json\ntouch my-skill/LICENSE.txt\n\nRequired files for clawhub:\n\nmy-skill/\n├── SKILL.md              # Instructions and metadata (required)\n├── _meta.json            # Registry metadata (required)\n├── LICENSE.txt           # License file (required)\n├── references/           # Optional: detailed documentation\n├── scripts/              # Optional: automation scripts\n└── assets/               # Optional: templates, resources"
      },
      {
        "title": "Phase 4: Write SKILL.md",
        "body": "Frontmatter (YAML)\n\n---\nname: skill-name\ndescription: What it does. Use when: (1) trigger-1, (2) trigger-2, (3) trigger-3.\n---\n\nCritical rules:\n\nname must match directory name\ndescription is ONLY trigger mechanism — include all \"when to use\" here\ndescription must be in English\nOnly name and description are required in frontmatter\n\nBody Structure\n\n# Skill Title\n\nBrief purpose (1-2 sentences).\n\n## Quick Start\n\n**Linux/Mac:**\n```bash\ncommand --option\n\nWindows CMD:\n\ncommand --option\n\nPowerShell:\n\ncommand --option"
      },
      {
        "title": "When to Use",
        "body": "Situation 1: What to do\nSituation 2: What to do\nSituation 3: What to do"
      },
      {
        "title": "Workflow",
        "body": "Step one: Description\nStep two: Description\nStep three: Description"
      },
      {
        "title": "Resources",
        "body": "references/advanced.md - For complex cases\nreferences/examples.md - Usage examples\nassets/template.txt - Starting template\n\n**Writing guidelines:**\n- Imperative voice (\"Open file\", not \"You should open file\")\n- Concrete examples over abstract explanations\n- Platform-aware commands\n- Navigation to references\n- English preferred for body text\n\n### Phase 5: Create _meta.json\n\n```json\n{\n  \"name\": \"skill-name\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Short description for registry listing\",\n  \"requires\": {\n    \"env\": [\"ENV_VAR_1\", \"ENV_VAR_2\"],\n    \"credentials\": [\"credential_name\"]\n  },\n  \"tags\": [\"tag1\", \"tag2\", \"latest\"]\n}\n\nFields explained:\n\nname: Must match directory and SKILL.md frontmatter\nversion: Semver (X.Y.Z), check registry before setting\ndescription: For registry listing, must be in English\nrequires.env: Environment variables needed\nrequires.credentials: Credentials needed\ntags: Include \"latest\" for discoverability"
      },
      {
        "title": "Phase 6: Add LICENSE.txt",
        "body": "Choose license (MIT recommended):\n\nMIT License\n\nCopyright (c) 2025 [Author]\n\nPermission is hereby granted..."
      },
      {
        "title": "Phase 7: Write References (if needed)",
        "body": "Create files in references/:\n\n# Reference Title\n\nDetailed documentation here.\n\n## Section\n\nContent...\n\nGuidelines:\n\nOne topic per file\n<5K words per file\nLink from SKILL.md with clear context\nNo deeply nested references\nLanguage: English preferred, domain-specific allowed"
      },
      {
        "title": "Phase 8: Validate Locally",
        "body": "# Check structure\n./scripts/validate.sh my-skill\n\n# Or manual checks:\n# - SKILL.md exists and has frontmatter\n# - _meta.json is valid JSON\n# - LICENSE.txt exists\n# - No README.md, CHANGELOG.md\n# - Line count < 300\n# - References linked correctly\n\nValidation checklist:\n\nDirectory name matches name in frontmatter and _meta.json\n description in English, includes \"Use when:\" triggers\n SKILL.md < 300 lines\n _meta.json valid JSON\n No extraneous files (README, CHANGELOG)\n References exist and linked\n Token estimate < 10K"
      },
      {
        "title": "Phase 9: Test with Agent",
        "body": "Trigger test:\n\nDoes skill activate for intended queries?\nDoes description correctly trigger skill?\n\nWorkflow test:\n\nCan agent follow steps without clarification?\nAre commands clear and executable?\n\nResource test:\n\nAre references loaded at appropriate time?\nIs navigation clear?\n\nEdge case test:\n\nHow does skill handle errors?\nAre platform differences handled?"
      },
      {
        "title": "Phase 10: Iterate (if needed)",
        "body": "If tests reveal issues:\n\nIdentify problem\n\nTrigger not working? → Fix description\nWorkflow unclear? → Rewrite steps\nMissing info? → Add reference\n\n\n\nUpdate files\n\nSKILL.md, _meta.json, or references\n\n\n\nRe-validate and re-test\n\nGo back to Phase 8\n\n\n\nRepeat until satisfied\n\nIterate cycle: Phase 8 → Phase 9 → Phase 10 (loop) → Phase 11"
      },
      {
        "title": "Phase 11: Check Version",
        "body": "Before publishing, verify current registry version:\n\n# Check current registry version\nclawhub inspect skill-name --json | grep version\n\n# Ensure new version follows semver:\n# 1.0.0 → 1.0.1 (patch: bug fixes)\n# 1.0.0 → 1.1.0 (minor: new features)\n# 1.0.0 → 2.0.0 (major: breaking changes)\n\n# Never downgrade! (1.1.0 → 1.0.2 is wrong)\n\nUpdate _meta.json with correct version:\n\n{\n  \"version\": \"1.0.1\"\n}"
      },
      {
        "title": "Phase 12: Package",
        "body": "# Create .skill package for distribution\n./scripts/package-skill.sh my-skill ./dist\n\n# Output: dist/my-skill.skill\n# Validates structure before packaging\n\nPackage contains:\n\nAll skill files\nValidated structure\nReady for distribution"
      },
      {
        "title": "Phase 13: Publish",
        "body": "cd my-skill\n\n# Publish to clawhub\nclawhub publish . --version 1.0.1 --changelog \"Description of changes\"\n\n# Verify publication\nclawhub inspect skill-name\n\nAfter publish:\n\nSkill available in registry\nOthers can install via clawhub install skill-name"
      },
      {
        "title": "SKILL.md",
        "body": "Instructions and metadata:\n\nYAML frontmatter (name, description in English)\nMarkdown body (workflow, examples)\nNavigation to references"
      },
      {
        "title": "_meta.json",
        "body": "Registry metadata:\n\n{\n  \"name\": \"skill-name\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Registry listing description in English\",\n  \"requires\": {\n    \"env\": [],\n    \"credentials\": []\n  },\n  \"tags\": [\"latest\"]\n}"
      },
      {
        "title": "LICENSE.txt",
        "body": "License file (MIT, Apache-2.0, etc.)"
      },
      {
        "title": "Resources",
        "body": "references/skill-structure.md - Directory structure patterns\nreferences/agent-first-design.md - Designing for AI vs humans\nreferences/token-optimization.md - Minimizing context usage\nreferences/cross-platform.md - Platform-aware scripts\nreferences/validation-checklist.md - Pre-publish checks\nreferences/versioning.md - Semver best practices"
      },
      {
        "title": "1. Agent-First Design",
        "body": "Skills used by AI agents, not humans:\n\n❌ No interactive prompts\n❌ No platform-specific scripts (use knowledge instead)\n✅ Command templates for all platforms\n✅ Clear navigation to references"
      },
      {
        "title": "2. Progressive Disclosure",
        "body": "Level 1: Metadata (name + description)     → Always loaded\nLevel 2: SKILL.md body                      → On trigger\nLevel 3: Resources (references/, assets/)   → On demand"
      },
      {
        "title": "3. Token Budget",
        "body": "ComponentTargetMaxMetadata50 words100 wordsSKILL.md200 lines300 linesReferences3K words5K wordsTotal5K tokens10K tokens"
      },
      {
        "title": "4. Cross-Platform Awareness",
        "body": "Instead of script:\n\n## Commands\n\n**Linux/Mac:**\n```bash\ncommand --option\n\nWindows CMD:\n\ncommand --option\n\nPowerShell:\n\ncommand --option\n\n**Agent chooses** appropriate variant based on detected platform.\n\n### 5. English Language for Descriptions\n\n**Required in English:**\n- `description` in SKILL.md frontmatter\n- `description` in _meta.json\n- Main workflow instructions\n\n**May use other languages:**\n- Code examples\n- Comments\n- Domain-specific references\n- User-facing examples\n\n## Scripts\n\n- `scripts/init-skill.sh` - Initialize new skill structure\n- `scripts/package-skill.sh` - Package skill for distribution\n- `scripts/validate.sh` - Validate skill structure\n\n## Anti-Patterns\n\n❌ **Don't:**\n- Put \"When to use\" only in body (must be in description)\n- Use non-English description in frontmatter\n- Duplicate info between SKILL.md and references\n- Create README.md, CHANGELOG.md (clutter)\n- Use platform-specific scripts (sh/bat)\n- Write passive voice (\"You should\")\n- Include generic background theory\n- Skip validation before publish\n- Forget to bump version\n- Publish without testing\n\n✅ **Do:**\n- Write description in English\n- Start with concrete examples\n- Move details to references/\n- Use imperative voice (\"Do X\")\n- Challenge every sentence's value\n- Test with real agent queries\n- Validate before publish\n- Follow semver strictly\n- Iterate based on test results"
      }
    ],
    "body": "Clawhub Skill Creator\n\nComplete guide for creating skills compatible with clawhub registry and optimized for AI agent usage.\n\nLanguage Rule\n\nSkill description must be in English, unless context requires otherwise (examples, comments, etc. may use other languages when appropriate).\n\ndescription in frontmatter: English only\nSKILL.md body: English preferred\nExamples, code comments: Any language as needed\nReferences: Any language as appropriate for domain\nQuick Start\nCreate New Skill\n# Run initializer\n./scripts/init-skill.sh my-skill\n\n# Or manually create structure\nmkdir -p my-skill/{references,scripts,assets}\ntouch my-skill/SKILL.md my-skill/_meta.json my-skill/LICENSE.txt\n\nSkill Creation Workflow\nPhase 1: Understand Requirements\n\nBefore writing any code, clarify:\n\nWhat problem does this skill solve?\n\nConcrete use cases (2-3 examples)\nTarget queries that should trigger skill\n\nWho will use this skill?\n\nAI agents (primary audience for clawhub)\nExpected context (tools available, environment)\n\nWhat resources are needed?\n\nReferences for detailed docs?\nAssets for templates?\nScripts for automation?\n\nOutput: Clear understanding of skill scope and triggers.\n\nPhase 2: Plan Structure\n\nChoose pattern based on complexity:\n\nComplexity\tStructure\tWhen to Use\nSimple\tSKILL.md only\t<100 lines, single purpose\nMedium\t+ references/\t100-300 lines, some details\nComplex\t+ references/ + assets/\t>300 lines, multi-domain\n\nDecide on resources:\n\nWhich references needed? (docs, examples, patterns)\nWhich assets needed? (templates, configs)\nWhich scripts needed? (validation, packaging)\n\nOutput: Directory structure and resource list.\n\nPhase 3: Initialize Structure\n# Create directory\nmkdir -p my-skill/{references,scripts,assets}\n\n# Create required files\ntouch my-skill/SKILL.md\ntouch my-skill/_meta.json\ntouch my-skill/LICENSE.txt\n\n\nRequired files for clawhub:\n\nmy-skill/\n├── SKILL.md              # Instructions and metadata (required)\n├── _meta.json            # Registry metadata (required)\n├── LICENSE.txt           # License file (required)\n├── references/           # Optional: detailed documentation\n├── scripts/              # Optional: automation scripts\n└── assets/               # Optional: templates, resources\n\nPhase 4: Write SKILL.md\nFrontmatter (YAML)\n---\nname: skill-name\ndescription: What it does. Use when: (1) trigger-1, (2) trigger-2, (3) trigger-3.\n---\n\n\nCritical rules:\n\nname must match directory name\ndescription is ONLY trigger mechanism — include all \"when to use\" here\ndescription must be in English\nOnly name and description are required in frontmatter\nBody Structure\n# Skill Title\n\nBrief purpose (1-2 sentences).\n\n## Quick Start\n\n**Linux/Mac:**\n```bash\ncommand --option\n\n\nWindows CMD:\n\ncommand --option\n\n\nPowerShell:\n\ncommand --option\n\nWhen to Use\nSituation 1: What to do\nSituation 2: What to do\nSituation 3: What to do\nWorkflow\nStep one: Description\nStep two: Description\nStep three: Description\nResources\nreferences/advanced.md - For complex cases\nreferences/examples.md - Usage examples\nassets/template.txt - Starting template\n\n**Writing guidelines:**\n- Imperative voice (\"Open file\", not \"You should open file\")\n- Concrete examples over abstract explanations\n- Platform-aware commands\n- Navigation to references\n- English preferred for body text\n\n### Phase 5: Create _meta.json\n\n```json\n{\n  \"name\": \"skill-name\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Short description for registry listing\",\n  \"requires\": {\n    \"env\": [\"ENV_VAR_1\", \"ENV_VAR_2\"],\n    \"credentials\": [\"credential_name\"]\n  },\n  \"tags\": [\"tag1\", \"tag2\", \"latest\"]\n}\n\n\nFields explained:\n\nname: Must match directory and SKILL.md frontmatter\nversion: Semver (X.Y.Z), check registry before setting\ndescription: For registry listing, must be in English\nrequires.env: Environment variables needed\nrequires.credentials: Credentials needed\ntags: Include \"latest\" for discoverability\nPhase 6: Add LICENSE.txt\n\nChoose license (MIT recommended):\n\nMIT License\n\nCopyright (c) 2025 [Author]\n\nPermission is hereby granted...\n\nPhase 7: Write References (if needed)\n\nCreate files in references/:\n\n# Reference Title\n\nDetailed documentation here.\n\n## Section\n\nContent...\n\n\nGuidelines:\n\nOne topic per file\n<5K words per file\nLink from SKILL.md with clear context\nNo deeply nested references\nLanguage: English preferred, domain-specific allowed\nPhase 8: Validate Locally\n# Check structure\n./scripts/validate.sh my-skill\n\n# Or manual checks:\n# - SKILL.md exists and has frontmatter\n# - _meta.json is valid JSON\n# - LICENSE.txt exists\n# - No README.md, CHANGELOG.md\n# - Line count < 300\n# - References linked correctly\n\n\nValidation checklist:\n\n Directory name matches name in frontmatter and _meta.json\n description in English, includes \"Use when:\" triggers\n SKILL.md < 300 lines\n _meta.json valid JSON\n No extraneous files (README, CHANGELOG)\n References exist and linked\n Token estimate < 10K\nPhase 9: Test with Agent\n\nTrigger test:\n\nDoes skill activate for intended queries?\nDoes description correctly trigger skill?\n\nWorkflow test:\n\nCan agent follow steps without clarification?\nAre commands clear and executable?\n\nResource test:\n\nAre references loaded at appropriate time?\nIs navigation clear?\n\nEdge case test:\n\nHow does skill handle errors?\nAre platform differences handled?\nPhase 10: Iterate (if needed)\n\nIf tests reveal issues:\n\nIdentify problem\n\nTrigger not working? → Fix description\nWorkflow unclear? → Rewrite steps\nMissing info? → Add reference\n\nUpdate files\n\nSKILL.md, _meta.json, or references\n\nRe-validate and re-test\n\nGo back to Phase 8\n\nRepeat until satisfied\n\nIterate cycle: Phase 8 → Phase 9 → Phase 10 (loop) → Phase 11\n\nPhase 11: Check Version\n\nBefore publishing, verify current registry version:\n\n# Check current registry version\nclawhub inspect skill-name --json | grep version\n\n# Ensure new version follows semver:\n# 1.0.0 → 1.0.1 (patch: bug fixes)\n# 1.0.0 → 1.1.0 (minor: new features)\n# 1.0.0 → 2.0.0 (major: breaking changes)\n\n# Never downgrade! (1.1.0 → 1.0.2 is wrong)\n\n\nUpdate _meta.json with correct version:\n\n{\n  \"version\": \"1.0.1\"\n}\n\nPhase 12: Package\n# Create .skill package for distribution\n./scripts/package-skill.sh my-skill ./dist\n\n# Output: dist/my-skill.skill\n# Validates structure before packaging\n\n\nPackage contains:\n\nAll skill files\nValidated structure\nReady for distribution\nPhase 13: Publish\ncd my-skill\n\n# Publish to clawhub\nclawhub publish . --version 1.0.1 --changelog \"Description of changes\"\n\n# Verify publication\nclawhub inspect skill-name\n\n\nAfter publish:\n\nSkill available in registry\nOthers can install via clawhub install skill-name\nRequired Files for Clawhub\nSKILL.md\n\nInstructions and metadata:\n\nYAML frontmatter (name, description in English)\nMarkdown body (workflow, examples)\nNavigation to references\n_meta.json\n\nRegistry metadata:\n\n{\n  \"name\": \"skill-name\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Registry listing description in English\",\n  \"requires\": {\n    \"env\": [],\n    \"credentials\": []\n  },\n  \"tags\": [\"latest\"]\n}\n\nLICENSE.txt\n\nLicense file (MIT, Apache-2.0, etc.)\n\nResources\nreferences/skill-structure.md - Directory structure patterns\nreferences/agent-first-design.md - Designing for AI vs humans\nreferences/token-optimization.md - Minimizing context usage\nreferences/cross-platform.md - Platform-aware scripts\nreferences/validation-checklist.md - Pre-publish checks\nreferences/versioning.md - Semver best practices\nKey Principles\n1. Agent-First Design\n\nSkills used by AI agents, not humans:\n\n❌ No interactive prompts\n❌ No platform-specific scripts (use knowledge instead)\n✅ Command templates for all platforms\n✅ Clear navigation to references\n2. Progressive Disclosure\nLevel 1: Metadata (name + description)     → Always loaded\nLevel 2: SKILL.md body                      → On trigger\nLevel 3: Resources (references/, assets/)   → On demand\n\n3. Token Budget\nComponent\tTarget\tMax\nMetadata\t50 words\t100 words\nSKILL.md\t200 lines\t300 lines\nReferences\t3K words\t5K words\nTotal\t5K tokens\t10K tokens\n4. Cross-Platform Awareness\n\nInstead of script:\n\n## Commands\n\n**Linux/Mac:**\n```bash\ncommand --option\n\n\nWindows CMD:\n\ncommand --option\n\n\nPowerShell:\n\ncommand --option\n\n\n**Agent chooses** appropriate variant based on detected platform.\n\n### 5. English Language for Descriptions\n\n**Required in English:**\n- `description` in SKILL.md frontmatter\n- `description` in _meta.json\n- Main workflow instructions\n\n**May use other languages:**\n- Code examples\n- Comments\n- Domain-specific references\n- User-facing examples\n\n## Scripts\n\n- `scripts/init-skill.sh` - Initialize new skill structure\n- `scripts/package-skill.sh` - Package skill for distribution\n- `scripts/validate.sh` - Validate skill structure\n\n## Anti-Patterns\n\n❌ **Don't:**\n- Put \"When to use\" only in body (must be in description)\n- Use non-English description in frontmatter\n- Duplicate info between SKILL.md and references\n- Create README.md, CHANGELOG.md (clutter)\n- Use platform-specific scripts (sh/bat)\n- Write passive voice (\"You should\")\n- Include generic background theory\n- Skip validation before publish\n- Forget to bump version\n- Publish without testing\n\n✅ **Do:**\n- Write description in English\n- Start with concrete examples\n- Move details to references/\n- Use imperative voice (\"Do X\")\n- Challenge every sentence's value\n- Test with real agent queries\n- Validate before publish\n- Follow semver strictly\n- Iterate based on test results"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/erview/clawhub-skill-creator",
    "publisherUrl": "https://clawhub.ai/erview/clawhub-skill-creator",
    "owner": "erview",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/clawhub-skill-creator",
    "downloadUrl": "https://openagent3.xyz/downloads/clawhub-skill-creator",
    "agentUrl": "https://openagent3.xyz/skills/clawhub-skill-creator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawhub-skill-creator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawhub-skill-creator/agent.md"
  }
}