{ "schemaVersion": "1.0", "item": { "slug": "create-agent-skills", "name": "Create Agent Skills", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/bowen31337/create-agent-skills", "canonicalUrl": "https://clawhub.ai/bowen31337/create-agent-skills", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/create-agent-skills", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=create-agent-skills", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "LICENSE.txt", "README.md", "SKILL.md", "references/output-patterns.md", "references/workflows.md", "scripts/init_skill.py" ], "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": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-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/create-agent-skills" }, "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/create-agent-skills", "agentPageUrl": "https://openagent3.xyz/skills/create-agent-skills/agent", "manifestUrl": "https://openagent3.xyz/skills/create-agent-skills/agent.json", "briefUrl": "https://openagent3.xyz/skills/create-agent-skills/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": "Skill Creator", "body": "This skill provides guidance for creating effective skills." }, { "title": "About Skills", "body": "Skills are modular, self-contained packages that extend Claude's capabilities by providing\nspecialized knowledge, workflows, and tools. Think of them as \"onboarding guides\" for specific\ndomains or tasks—they transform Claude from a general-purpose agent into a specialized agent\nequipped with procedural knowledge that no model can fully possess." }, { "title": "What Skills Provide", "body": "Specialized workflows - Multi-step procedures for specific domains\nTool integrations - Instructions for working with specific file formats or APIs\nDomain expertise - Company-specific knowledge, schemas, business logic\nBundled resources - Scripts, references, and assets for complex and repetitive tasks" }, { "title": "Concise is Key", "body": "The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.\n\nDefault assumption: Claude is already very smart. Only add context Claude doesn't already have. Challenge each piece of information: \"Does Claude really need this explanation?\" and \"Does this paragraph justify its token cost?\"\n\nPrefer concise examples over verbose explanations." }, { "title": "Set Appropriate Degrees of Freedom", "body": "Match the level of specificity to the task's fragility and variability:\n\nHigh freedom (text-based instructions): Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.\n\nMedium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.\n\nLow freedom (specific scripts, few parameters): Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.\n\nThink of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom)." }, { "title": "Anatomy of a Skill", "body": "Every skill consists of a required SKILL.md file and optional bundled resources:\n\nskill-name/\n├── SKILL.md (required)\n│ ├── YAML frontmatter metadata (required)\n│ │ ├── name: (required)\n│ │ └── description: (required)\n│ └── Markdown instructions (required)\n└── Bundled Resources (optional)\n ├── scripts/ - Executable code (Python/Bash/etc.)\n ├── references/ - Documentation intended to be loaded into context as needed\n └── assets/ - Files used in output (templates, icons, fonts, etc.)\n\nSKILL.md (required)\n\nEvery SKILL.md consists of:\n\nFrontmatter (YAML): Contains name and description fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.\nBody (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).\n\nBundled Resources (optional)\n\nScripts (scripts/)\n\nExecutable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.\n\nWhen to include: When the same code is being rewritten repeatedly or deterministic reliability is needed\nExample: scripts/rotate_pdf.py for PDF rotation tasks\nBenefits: Token efficient, deterministic, may be executed without loading into context\nNote: Scripts may still need to be read by Claude for patching or environment-specific adjustments\n\nReferences (references/)\n\nDocumentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.\n\nWhen to include: For documentation that Claude should reference while working\nExamples: references/finance.md for financial schemas, references/mnda.md for company NDA template, references/policies.md for company policies, references/api_docs.md for API specifications\nUse cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides\nBenefits: Keeps SKILL.md lean, loaded only when Claude determines it's needed\nBest practice: If files are large (>10k words), include grep search patterns in SKILL.md\nAvoid duplication: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.\n\nAssets (assets/)\n\nFiles not intended to be loaded into context, but rather used within the output Claude produces.\n\nWhen to include: When the skill needs files that will be used in the final output\nExamples: assets/logo.png for brand assets, assets/slides.pptx for PowerPoint templates, assets/frontend-template/ for HTML/React boilerplate, assets/font.ttf for typography\nUse cases: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified\nBenefits: Separates output resources from documentation, enables Claude to use files without loading them into context\n\nWhat to Not Include in a Skill\n\nA skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:\n\nREADME.md\nINSTALLATION_GUIDE.md\nQUICK_REFERENCE.md\nCHANGELOG.md\netc.\n\nThe skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion." }, { "title": "Progressive Disclosure Design Principle", "body": "Skills use a three-level loading system to manage context efficiently:\n\nMetadata (name + description) - Always in context (~100 words)\nSKILL.md body - When skill triggers (<5k words)\nBundled resources - As needed by Claude (Unlimited because scripts can be executed without reading into context window)\n\nProgressive Disclosure Patterns\n\nKeep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.\n\nKey principle: When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.\n\nPattern 1: High-level guide with references\n\n# PDF Processing\n\n## Quick start\n\nExtract text with pdfplumber:\n[code example]\n\n## Advanced features\n\n- **Form filling**: See [FORMS.md](FORMS.md) for complete guide\n- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods\n- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns\n\nClaude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.\n\nPattern 2: Domain-specific organization\n\nFor Skills with multiple domains, organize content by domain to avoid loading irrelevant context:\n\nbigquery-skill/\n├── SKILL.md (overview and navigation)\n└── reference/\n ├── finance.md (revenue, billing metrics)\n ├── sales.md (opportunities, pipeline)\n ├── product.md (API usage, features)\n └── marketing.md (campaigns, attribution)\n\nWhen a user asks about sales metrics, Claude only reads sales.md.\n\nSimilarly, for skills supporting multiple frameworks or variants, organize by variant:\n\ncloud-deploy/\n├── SKILL.md (workflow + provider selection)\n└── references/\n ├── aws.md (AWS deployment patterns)\n ├── gcp.md (GCP deployment patterns)\n └── azure.md (Azure deployment patterns)\n\nWhen the user chooses AWS, Claude only reads aws.md.\n\nPattern 3: Conditional details\n\nShow basic content, link to advanced content:\n\n# DOCX Processing\n\n## Creating documents\n\nUse docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).\n\n## Editing documents\n\nFor simple edits, modify the XML directly.\n\n**For tracked changes**: See [REDLINING.md](REDLINING.md)\n**For OOXML details**: See [OOXML.md](OOXML.md)\n\nClaude reads REDLINING.md or OOXML.md only when the user needs those features.\n\nImportant guidelines:\n\nAvoid deeply nested references - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.\nStructure longer reference files - For files longer than 100 lines, include a table of contents at the top so Claude can see the full scope when previewing." }, { "title": "Skill Creation Process", "body": "Skill creation involves these steps:\n\nUnderstand the skill with concrete examples\nPlan reusable skill contents (scripts, references, assets)\nInitialize the skill (run init_skill.py)\nEdit the skill (implement resources and write SKILL.md)\nPackage the skill (run package_skill.py)\nIterate based on real usage\n\nFollow these steps in order, skipping only if there is a clear reason why they are not applicable." }, { "title": "Step 1: Understanding the Skill with Concrete Examples", "body": "Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.\n\nTo create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.\n\nFor example, when building an image-editor skill, relevant questions include:\n\n\"What functionality should the image-editor skill support? Editing, rotating, anything else?\"\n\"Can you give some examples of how this skill would be used?\"\n\"I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?\"\n\"What would a user say that should trigger this skill?\"\n\nTo avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.\n\nConclude this step when there is a clear sense of the functionality the skill should support." }, { "title": "Step 2: Planning the Reusable Skill Contents", "body": "To turn concrete examples into an effective skill, analyze each example by:\n\nConsidering how to execute on the example from scratch\nIdentifying what scripts, references, and assets would be helpful when executing these workflows repeatedly\n\nExample: When building a pdf-editor skill to handle queries like \"Help me rotate this PDF,\" the analysis shows:\n\nRotating a PDF requires re-writing the same code each time\nA scripts/rotate_pdf.py script would be helpful to store in the skill\n\nExample: When designing a frontend-webapp-builder skill for queries like \"Build me a todo app\" or \"Build me a dashboard to track my steps,\" the analysis shows:\n\nWriting a frontend webapp requires the same boilerplate HTML/React each time\nAn assets/hello-world/ template containing the boilerplate HTML/React project files would be helpful to store in the skill\n\nExample: When building a big-query skill to handle queries like \"How many users have logged in today?\" the analysis shows:\n\nQuerying BigQuery requires re-discovering the table schemas and relationships each time\nA references/schema.md file documenting the table schemas would be helpful to store in the skill\n\nTo establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets." }, { "title": "Step 3: Initializing the Skill", "body": "At this point, it is time to actually create the skill.\n\nSkip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.\n\nWhen creating a new skill from scratch, always run the init_skill.py script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.\n\nUsage:\n\nscripts/init_skill.py --path \n\nThe script:\n\nCreates the skill directory at the specified path\nGenerates a SKILL.md template with proper frontmatter and TODO placeholders\nCreates example resource directories: scripts/, references/, and assets/\nAdds example files in each directory that can be customized or deleted\n\nAfter initialization, customize or remove the generated SKILL.md and example files as needed." }, { "title": "Step 4: Edit the Skill", "body": "When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.\n\nLearn Proven Design Patterns\n\nConsult these helpful guides based on your skill's needs:\n\nMulti-step processes: See references/workflows.md for sequential workflows and conditional logic\nSpecific output formats or quality standards: See references/output-patterns.md for template and example patterns\n\nThese files contain established best practices for effective skill design.\n\nStart with Reusable Skill Contents\n\nTo begin implementation, start with the reusable resources identified above: scripts/, references/, and assets/ files. Note that this step may require user input. For example, when implementing a brand-guidelines skill, the user may need to provide brand assets or templates to store in assets/, or documentation to store in references/.\n\nAdded scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.\n\nAny example files and directories not needed for the skill should be deleted. The initialization script creates example files in scripts/, references/, and assets/ to demonstrate structure, but most skills won't need all of them.\n\nUpdate SKILL.md\n\nWriting Guidelines: Always use imperative/infinitive form.\n\nFrontmatter\n\nWrite the YAML frontmatter with name and description:\n\nname: The skill name\ndescription: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill.\n\nInclude both what the Skill does and specific triggers/contexts for when to use it.\nInclude all \"when to use\" information here - Not in the body. The body is only loaded after triggering, so \"When to Use This Skill\" sections in the body are not helpful to Claude.\nExample description for a docx skill: \"Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks\"\n\nDo not include any other fields in YAML frontmatter.\n\nBody\n\nWrite instructions for using the skill and its bundled resources." }, { "title": "Step 5: Packaging a Skill", "body": "Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:\n\nscripts/package_skill.py \n\nOptional output directory specification:\n\nscripts/package_skill.py ./dist\n\nThe packaging script will:\n\nValidate the skill automatically, checking:\n\nYAML frontmatter format and required fields\nSkill naming conventions and directory structure\nDescription completeness and quality\nFile organization and resource references\n\n\n\nPackage the skill if validation passes, creating a .skill file named after the skill (e.g., my-skill.skill) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.\n\nIf validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again." }, { "title": "Step 6: Iterate", "body": "After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.\n\nIteration workflow:\n\nUse the skill on real tasks\nNotice struggles or inefficiencies\nIdentify how SKILL.md or bundled resources should be updated\nImplement changes and test again" } ], "body": "Skill Creator\n\nThis skill provides guidance for creating effective skills.\n\nAbout Skills\n\nSkills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as \"onboarding guides\" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.\n\nWhat Skills Provide\nSpecialized workflows - Multi-step procedures for specific domains\nTool integrations - Instructions for working with specific file formats or APIs\nDomain expertise - Company-specific knowledge, schemas, business logic\nBundled resources - Scripts, references, and assets for complex and repetitive tasks\nCore Principles\nConcise is Key\n\nThe context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.\n\nDefault assumption: Claude is already very smart. Only add context Claude doesn't already have. Challenge each piece of information: \"Does Claude really need this explanation?\" and \"Does this paragraph justify its token cost?\"\n\nPrefer concise examples over verbose explanations.\n\nSet Appropriate Degrees of Freedom\n\nMatch the level of specificity to the task's fragility and variability:\n\nHigh freedom (text-based instructions): Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.\n\nMedium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.\n\nLow freedom (specific scripts, few parameters): Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.\n\nThink of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).\n\nAnatomy of a Skill\n\nEvery skill consists of a required SKILL.md file and optional bundled resources:\n\nskill-name/\n├── SKILL.md (required)\n│ ├── YAML frontmatter metadata (required)\n│ │ ├── name: (required)\n│ │ └── description: (required)\n│ └── Markdown instructions (required)\n└── Bundled Resources (optional)\n ├── scripts/ - Executable code (Python/Bash/etc.)\n ├── references/ - Documentation intended to be loaded into context as needed\n └── assets/ - Files used in output (templates, icons, fonts, etc.)\n\nSKILL.md (required)\n\nEvery SKILL.md consists of:\n\nFrontmatter (YAML): Contains name and description fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.\nBody (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).\nBundled Resources (optional)\nScripts (scripts/)\n\nExecutable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.\n\nWhen to include: When the same code is being rewritten repeatedly or deterministic reliability is needed\nExample: scripts/rotate_pdf.py for PDF rotation tasks\nBenefits: Token efficient, deterministic, may be executed without loading into context\nNote: Scripts may still need to be read by Claude for patching or environment-specific adjustments\nReferences (references/)\n\nDocumentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.\n\nWhen to include: For documentation that Claude should reference while working\nExamples: references/finance.md for financial schemas, references/mnda.md for company NDA template, references/policies.md for company policies, references/api_docs.md for API specifications\nUse cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides\nBenefits: Keeps SKILL.md lean, loaded only when Claude determines it's needed\nBest practice: If files are large (>10k words), include grep search patterns in SKILL.md\nAvoid duplication: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.\nAssets (assets/)\n\nFiles not intended to be loaded into context, but rather used within the output Claude produces.\n\nWhen to include: When the skill needs files that will be used in the final output\nExamples: assets/logo.png for brand assets, assets/slides.pptx for PowerPoint templates, assets/frontend-template/ for HTML/React boilerplate, assets/font.ttf for typography\nUse cases: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified\nBenefits: Separates output resources from documentation, enables Claude to use files without loading them into context\nWhat to Not Include in a Skill\n\nA skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:\n\nREADME.md\nINSTALLATION_GUIDE.md\nQUICK_REFERENCE.md\nCHANGELOG.md\netc.\n\nThe skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.\n\nProgressive Disclosure Design Principle\n\nSkills use a three-level loading system to manage context efficiently:\n\nMetadata (name + description) - Always in context (~100 words)\nSKILL.md body - When skill triggers (<5k words)\nBundled resources - As needed by Claude (Unlimited because scripts can be executed without reading into context window)\nProgressive Disclosure Patterns\n\nKeep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.\n\nKey principle: When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.\n\nPattern 1: High-level guide with references\n\n# PDF Processing\n\n## Quick start\n\nExtract text with pdfplumber:\n[code example]\n\n## Advanced features\n\n- **Form filling**: See [FORMS.md](FORMS.md) for complete guide\n- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods\n- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns\n\n\nClaude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.\n\nPattern 2: Domain-specific organization\n\nFor Skills with multiple domains, organize content by domain to avoid loading irrelevant context:\n\nbigquery-skill/\n├── SKILL.md (overview and navigation)\n└── reference/\n ├── finance.md (revenue, billing metrics)\n ├── sales.md (opportunities, pipeline)\n ├── product.md (API usage, features)\n └── marketing.md (campaigns, attribution)\n\n\nWhen a user asks about sales metrics, Claude only reads sales.md.\n\nSimilarly, for skills supporting multiple frameworks or variants, organize by variant:\n\ncloud-deploy/\n├── SKILL.md (workflow + provider selection)\n└── references/\n ├── aws.md (AWS deployment patterns)\n ├── gcp.md (GCP deployment patterns)\n └── azure.md (Azure deployment patterns)\n\n\nWhen the user chooses AWS, Claude only reads aws.md.\n\nPattern 3: Conditional details\n\nShow basic content, link to advanced content:\n\n# DOCX Processing\n\n## Creating documents\n\nUse docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).\n\n## Editing documents\n\nFor simple edits, modify the XML directly.\n\n**For tracked changes**: See [REDLINING.md](REDLINING.md)\n**For OOXML details**: See [OOXML.md](OOXML.md)\n\n\nClaude reads REDLINING.md or OOXML.md only when the user needs those features.\n\nImportant guidelines:\n\nAvoid deeply nested references - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.\nStructure longer reference files - For files longer than 100 lines, include a table of contents at the top so Claude can see the full scope when previewing.\nSkill Creation Process\n\nSkill creation involves these steps:\n\nUnderstand the skill with concrete examples\nPlan reusable skill contents (scripts, references, assets)\nInitialize the skill (run init_skill.py)\nEdit the skill (implement resources and write SKILL.md)\nPackage the skill (run package_skill.py)\nIterate based on real usage\n\nFollow these steps in order, skipping only if there is a clear reason why they are not applicable.\n\nStep 1: Understanding the Skill with Concrete Examples\n\nSkip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.\n\nTo create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.\n\nFor example, when building an image-editor skill, relevant questions include:\n\n\"What functionality should the image-editor skill support? Editing, rotating, anything else?\"\n\"Can you give some examples of how this skill would be used?\"\n\"I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?\"\n\"What would a user say that should trigger this skill?\"\n\nTo avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.\n\nConclude this step when there is a clear sense of the functionality the skill should support.\n\nStep 2: Planning the Reusable Skill Contents\n\nTo turn concrete examples into an effective skill, analyze each example by:\n\nConsidering how to execute on the example from scratch\nIdentifying what scripts, references, and assets would be helpful when executing these workflows repeatedly\n\nExample: When building a pdf-editor skill to handle queries like \"Help me rotate this PDF,\" the analysis shows:\n\nRotating a PDF requires re-writing the same code each time\nA scripts/rotate_pdf.py script would be helpful to store in the skill\n\nExample: When designing a frontend-webapp-builder skill for queries like \"Build me a todo app\" or \"Build me a dashboard to track my steps,\" the analysis shows:\n\nWriting a frontend webapp requires the same boilerplate HTML/React each time\nAn assets/hello-world/ template containing the boilerplate HTML/React project files would be helpful to store in the skill\n\nExample: When building a big-query skill to handle queries like \"How many users have logged in today?\" the analysis shows:\n\nQuerying BigQuery requires re-discovering the table schemas and relationships each time\nA references/schema.md file documenting the table schemas would be helpful to store in the skill\n\nTo establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.\n\nStep 3: Initializing the Skill\n\nAt this point, it is time to actually create the skill.\n\nSkip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.\n\nWhen creating a new skill from scratch, always run the init_skill.py script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.\n\nUsage:\n\nscripts/init_skill.py --path \n\n\nThe script:\n\nCreates the skill directory at the specified path\nGenerates a SKILL.md template with proper frontmatter and TODO placeholders\nCreates example resource directories: scripts/, references/, and assets/\nAdds example files in each directory that can be customized or deleted\n\nAfter initialization, customize or remove the generated SKILL.md and example files as needed.\n\nStep 4: Edit the Skill\n\nWhen editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.\n\nLearn Proven Design Patterns\n\nConsult these helpful guides based on your skill's needs:\n\nMulti-step processes: See references/workflows.md for sequential workflows and conditional logic\nSpecific output formats or quality standards: See references/output-patterns.md for template and example patterns\n\nThese files contain established best practices for effective skill design.\n\nStart with Reusable Skill Contents\n\nTo begin implementation, start with the reusable resources identified above: scripts/, references/, and assets/ files. Note that this step may require user input. For example, when implementing a brand-guidelines skill, the user may need to provide brand assets or templates to store in assets/, or documentation to store in references/.\n\nAdded scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.\n\nAny example files and directories not needed for the skill should be deleted. The initialization script creates example files in scripts/, references/, and assets/ to demonstrate structure, but most skills won't need all of them.\n\nUpdate SKILL.md\n\nWriting Guidelines: Always use imperative/infinitive form.\n\nFrontmatter\n\nWrite the YAML frontmatter with name and description:\n\nname: The skill name\ndescription: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill.\nInclude both what the Skill does and specific triggers/contexts for when to use it.\nInclude all \"when to use\" information here - Not in the body. The body is only loaded after triggering, so \"When to Use This Skill\" sections in the body are not helpful to Claude.\nExample description for a docx skill: \"Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks\"\n\nDo not include any other fields in YAML frontmatter.\n\nBody\n\nWrite instructions for using the skill and its bundled resources.\n\nStep 5: Packaging a Skill\n\nOnce development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:\n\nscripts/package_skill.py \n\n\nOptional output directory specification:\n\nscripts/package_skill.py ./dist\n\n\nThe packaging script will:\n\nValidate the skill automatically, checking:\n\nYAML frontmatter format and required fields\nSkill naming conventions and directory structure\nDescription completeness and quality\nFile organization and resource references\n\nPackage the skill if validation passes, creating a .skill file named after the skill (e.g., my-skill.skill) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.\n\nIf validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.\n\nStep 6: Iterate\n\nAfter testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.\n\nIteration workflow:\n\nUse the skill on real tasks\nNotice struggles or inefficiencies\nIdentify how SKILL.md or bundled resources should be updated\nImplement changes and test again" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/bowen31337/create-agent-skills", "publisherUrl": "https://clawhub.ai/bowen31337/create-agent-skills", "owner": "bowen31337", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/create-agent-skills", "downloadUrl": "https://openagent3.xyz/downloads/create-agent-skills", "agentUrl": "https://openagent3.xyz/skills/create-agent-skills/agent", "manifestUrl": "https://openagent3.xyz/skills/create-agent-skills/agent.json", "briefUrl": "https://openagent3.xyz/skills/create-agent-skills/agent.md" } }