[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-anthropics-claude-api-zh-CN":3,"guides-for-anthropics-claude-api":826,"similar-k174mtgq6gce83khprgqhpxf3986m3ed-zh-CN":827},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":241,"isFallback":246,"parentExtension":247,"providers":304,"relations":308,"repo":309,"tags":824,"workflow":825},1778675443171.0552,"k174mtgq6gce83khprgqhpxf3986m3ed",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.",{"claudeCode":12},"anthropics/skills","claude-api","https://github.com/anthropics/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":239},1778675562818.358,"kn7fay889yv2vh7pzsf6w5v4td86m7vk","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":217,"tier":218,"useCases":219},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,133,137,140,143,146,149,153,156,159,162,165,168,171,175,179,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The description clearly states the extension's purpose (building, debugging, optimizing Claude API/Anthropic SDK apps) and provides specific triggers for use and explicit boundaries for skipping, making its scope immediately clear.",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The frontmatter is concise, self-contained, and effectively summarizes the core capabilities and trigger phrases within the character limit.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The SKILL.md body is concise and delegates deeper material to separate files or sections as appropriate.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The SKILL.md outlines procedures and links to relevant external files or detailed sections for more in-depth information.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","This skill is not designed for deep exploration or multi-file inspection that would require forked context.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","The skill provides sufficient end-to-end examples that plausibly demonstrate its advertised capabilities.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","The skill handles edge cases and lists failure modes with symptoms and recovery steps, as documented in the SKILL.md.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","This skill does not appear to rely on external tools like MCP servers that would require a fallback mechanism.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The documentation instructs the skill to abort and report on unexpected pre-states, ensuring safety.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","The skill is self-contained and any cross-skill coordination is handled explicitly and is optional.",{"category":42,"check":61,"severity":24,"summary":62},"Problem relevance","The description clearly names a concrete user problem (building/debugging/optimizing Claude API apps, migrating versions) and specifies the target audience and context.",{"category":42,"check":64,"severity":24,"summary":65},"Unique selling proposition","The skill offers significant value beyond a simple API wrapper by providing specific guidance on model versions, thinking parameters, and prompt caching strategies for Claude SDKs.",{"category":42,"check":67,"severity":24,"summary":68},"Production readiness","The skill appears to be production-ready, covering the full lifecycle of developing and maintaining Claude API applications, including migration and optimization.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","The extension focuses on a single domain: building, debugging, and optimizing Claude API/Anthropic SDK applications, including specific features like prompt caching and model version migration.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","The description is accurate, concise, and effectively reflects the skill's behavior, including its scope and triggers.",{"category":22,"check":77,"severity":39,"summary":78},"Scoped tools","This skill does not expose explicit tools in the traditional sense; its functionality is driven by prompt-based instructions and code generation.",{"category":30,"check":80,"severity":24,"summary":81},"Configuration & parameter reference","The documentation clearly references and explains parameters like model versions, thinking types, and prompt caching mechanisms, including defaults.",{"category":70,"check":83,"severity":39,"summary":84},"Tool naming","This skill does not expose user-facing tools with distinct names; its interaction is via natural language prompts and generated code.",{"category":70,"check":86,"severity":39,"summary":87},"Minimal I/O surface","The skill operates via natural language and code generation, not through explicit tool parameter schemas or structured responses.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The license is clearly stated as Apache 2.0, with a LICENSE.txt file provided, making it a permissive OSS license.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The repository has recent commits, indicating active maintenance, with the latest commit within the last week.",{"category":93,"check":97,"severity":39,"summary":98},"Dependency Management","No third-party dependencies are explicitly managed or declared for this skill's core functionality, as it relies on the Claude environment and Anthropic SDKs.",{"category":100,"check":101,"severity":39,"summary":102},"Security","Secret Management","The skill itself does not handle secrets; it generates code that might interact with secrets, but the responsibility for secret management lies with the user's application.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","The skill's documentation emphasizes treating external code and prompts as data, and does not indicate runtime download of external instructions.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","The skill operates within its defined bundle and relies on documented SDKs, not on runtime fetching of executable content.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","The skill operates within the Claude environment and generates code; it does not attempt to modify files outside of the user's project or specified scope.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","There are no indications of detached processes or deny-retry loops in the skill's logic.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","The skill focuses on code generation and API interaction patterns; it does not instruct the agent to exfiltrate confidential data to third parties.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","The bundled content and documentation appear free of hidden steering tricks or malicious Unicode characters.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","The skill's code and instructions are presented in a clear, readable format, without obfuscation or runtime code fetching.",{"category":57,"check":126,"severity":24,"summary":127},"Structural Assumption","The skill makes general assumptions about project structure for language detection but does not rely on specific, brittle user file paths.",{"category":129,"check":130,"severity":131,"summary":132},"Trust","Issues Attention","warning","There are 135 open issues and 11 closed issues in the last 90 days, indicating a very low closure rate and potentially slow maintainer response.",{"category":134,"check":135,"severity":24,"summary":136},"Versioning","Release Management","The repository has a `pushedAt` date indicating recent activity, and the license file indicates it's part of the anthropics/skills repo which likely has versioning practices.",{"category":49,"check":138,"severity":39,"summary":139},"Validation","This skill generates code and documentation; it does not directly execute user input through validation schemas.",{"category":100,"check":141,"severity":24,"summary":142},"Unguarded Destructive Operations","The skill focuses on code generation and API interaction, not destructive operations like file deletion or infrastructure changes, thus requiring no guardrails for such actions.",{"category":49,"check":144,"severity":24,"summary":145},"Error Handling","The documentation thoroughly covers error handling, including API errors, model migration pitfalls, and general troubleshooting steps.",{"category":49,"check":147,"severity":39,"summary":148},"Logging","The skill itself does not perform actions that require local audit logging; logging would be handled by the user's application interacting with the Claude API.",{"category":150,"check":151,"severity":24,"summary":152},"Compliance","GDPR","The skill's purpose is code generation and API interaction, not processing personal data directly; it does not appear to submit personal data to third parties without sanitization.",{"category":150,"check":154,"severity":24,"summary":155},"Target market","The extension is designed for Claude API and Anthropic SDK users globally, with no discernible regional or jurisdictional limitations.",{"category":57,"check":157,"severity":24,"summary":158},"Runtime stability","The skill relies on the Claude environment and standard SDKs, making it portable across different user environments without specific OS or shell assumptions.",{"category":30,"check":160,"severity":24,"summary":161},"README","The README file exists and clearly explains the purpose of the repository and its skills.",{"category":70,"check":163,"severity":39,"summary":164},"Tool surface size","This skill does not expose a distinct set of tools; it operates via natural language prompts and code generation.",{"category":22,"check":166,"severity":39,"summary":167},"Overlapping near-synonym tools","The skill does not expose distinct tools, so there are no overlapping near-synonym tools.",{"category":30,"check":169,"severity":24,"summary":170},"Phantom features","All features advertised in the description and SKILL.md, such as prompt caching and model migration, have corresponding implementations and documentation.",{"category":172,"check":173,"severity":24,"summary":174},"Install","Installation instruction","The README provides clear instructions for installing and using the skills in Claude Code, Claude.ai, and via the API, including example invocations.",{"category":176,"check":177,"severity":24,"summary":178},"Errors","Actionable error messages","The documentation provides detailed guidance on error handling, including common pitfalls and how to interpret API errors.",{"category":180,"check":181,"severity":39,"summary":182},"Execution","Pinned dependencies","The skill relies on the Claude environment and Anthropic SDKs, which are managed by the platform, rather than user-managed dependencies.",{"category":70,"check":184,"severity":39,"summary":185},"Dry-run preview","This skill generates code and instructions, it does not perform state-changing operations that would require a dry-run preview.",{"category":187,"check":188,"severity":39,"summary":189},"Protocol","Idempotent retry & timeouts","The skill itself does not make direct API calls that require explicit retry logic or timeouts; these are handled by the underlying SDK and Claude platform.",{"category":150,"check":191,"severity":24,"summary":192},"Telemetry opt-in","The skill's documentation does not mention telemetry collection, and it operates by generating code, implying no telemetry is emitted by the skill itself.",1778675562717,"This skill assists developers in building, debugging, and optimizing applications using the Claude API and Anthropic SDK. It provides support for prompt caching, migrating code between Claude model versions, and guidance on using various API features. The skill operates by generating code and instructions based on user prompts and project context.",[196,197,198,199,200],"Build and optimize Claude API/Anthropic SDK applications","Implement prompt caching strategies","Migrate Claude API code between model versions","Guidance on Claude features (caching, thinking, tool use, etc.)","Default to Opus 4.7 model with adaptive thinking and streaming",[202,203,204],"Developing applications with OpenAI or other third-party SDKs.","Writing provider-neutral code.","General programming or machine learning tasks outside of Claude API integration.","3.0.0","4.4.0","To empower developers to efficiently build, optimize, and maintain applications leveraging the Claude API and Anthropic SDK, ensuring best practices and smooth transitions between model versions.","The primary finding impacting the score is the 'Issues Attention' check, which shows a high number of open issues with a very low closure rate, indicating potential maintenance lags. Despite this, the skill is otherwise well-documented, feature-complete, and adheres to good practices.",79,"A comprehensive skill for developing and optimizing Claude API applications, with detailed guidance and robust documentation.",[13,212,213,214,215,216],"anthropic-sdk","llm-development","code-generation","api-optimization","model-migration","global","community",[220,221,222,223],"Use when building new applications with the Anthropic SDK.","Use when debugging or optimizing existing Claude API integrations.","Use when migrating Claude API code to newer model versions (e.g., 4.5 to 4.7).","Use when implementing prompt caching or tuning its hit rate in an Anthropic SDK project.",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"security":237,"testCoverage":238},{"hasLockfile":226},false,1778675544086,{"descriptionLength":229,"readmeSize":230},744,5552,{"closedIssues90d":232,"forks":233,"hasChangelog":226,"openIssues90d":234,"pushedAt":235,"stars":236},11,15729,135,1778286877000,133400,{"hasNpmPackage":226,"smitheryVerified":226},{"hasCi":226,"hasTests":226},{"updatedAt":240},1778675562818,{"basePath":242,"githubOwner":243,"githubRepo":244,"locale":18,"slug":13,"type":245},"skills/claude-api","anthropics","skills","skill",true,{"_creationTime":248,"_id":249,"community":250,"display":251,"identity":255,"parentExtension":258,"providers":287,"relations":300,"tags":301,"workflow":302},1778675443171.0537,"k170qz33xe7jskt6553a2dh72586mgxe",{"reviewCount":8},{"description":252,"installMethods":253,"name":254,"sourceUrl":14},"Collection of document processing suite including Excel, Word, PowerPoint, and PDF capabilities",{"claudeCode":244},"Claude API and SDK Guide",{"basePath":256,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":257},"","plugin",{"_creationTime":259,"_id":260,"community":261,"display":262,"identity":266,"providers":268,"relations":281,"tags":283,"workflow":284},1778675443171.0535,"k179jez5bqzvcf34s52bze7t7n86nhn3",{"reviewCount":8},{"description":263,"installMethods":264,"name":265,"sourceUrl":14},"Anthropic example skills",{"claudeCode":12},"anthropic-agent-skills",{"basePath":256,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":267},"marketplace",{"evaluate":269,"extract":275},{"promptVersionExtension":270,"promptVersionScoring":206,"score":209,"tags":271,"targetMarket":217,"tier":218},"3.1.0",[272,244,267,273,274],"ai","documentation","examples",{"commitSha":276,"marketplace":277,"plugin":279},"HEAD",{"name":265,"pluginCount":278},1,{"mcpCount":8,"provider":280,"skillCount":8},"classify",{"repoId":282},"kd70961715zznj5333pbvetk3986mf7x",[272,273,274,267,244],{"evaluatedAt":285,"extractAt":286,"updatedAt":285},1778675460927,1778675443171,{"evaluate":288,"extract":296},{"promptVersionExtension":205,"promptVersionScoring":206,"score":289,"tags":290,"targetMarket":217,"tier":218},89,[13,291,292,293,294,295,273],"llm","sdk","typescript","python","developer-tools",{"commitSha":276,"license":297,"plugin":298},"Proprietary",{"mcpCount":8,"provider":280,"skillCount":299},17,{"parentExtensionId":260,"repoId":282},[13,295,273,291,294,292,293],{"evaluatedAt":303,"extractAt":286,"updatedAt":303},1778675491504,{"evaluate":305,"extract":307},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":306,"targetMarket":217,"tier":218},[13,212,213,214,215,216],{"commitSha":276},{"parentExtensionId":249,"repoId":282},{"_creationTime":310,"_id":282,"identity":311,"providers":312,"workflow":820},1778675438038.062,{"githubOwner":243,"githubRepo":244,"sourceUrl":14},{"classify":313,"discover":813,"github":816},{"commitSha":276,"extensions":314},[315,325,331,337,342,359,368,377,383,391,518,527,544,561,591,662,692,701,710,725,742,804],{"basePath":256,"description":263,"displayName":265,"installMethods":316,"rationale":317,"selectedPaths":318,"source":324,"sourceLanguage":18,"type":267},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[319,322],{"path":320,"priority":321},".claude-plugin/marketplace.json","mandatory",{"path":323,"priority":321},"README.md","rule",{"basePath":256,"description":252,"displayName":326,"installMethods":327,"rationale":328,"selectedPaths":329,"source":324,"sourceLanguage":18,"type":257},"document-skills",{"claudeCode":244},"inline plugin source from marketplace.json at /",[330],{"path":323,"priority":321},{"basePath":256,"description":332,"displayName":333,"installMethods":334,"rationale":328,"selectedPaths":335,"source":324,"sourceLanguage":18,"type":257},"Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling","example-skills",{"claudeCode":244},[336],{"path":323,"priority":321},{"basePath":256,"description":338,"displayName":13,"installMethods":339,"rationale":328,"selectedPaths":340,"source":324,"sourceLanguage":18,"type":257},"Claude API and SDK documentation skill for building LLM-powered applications",{"claudeCode":244},[341],{"path":323,"priority":321},{"basePath":343,"description":344,"displayName":345,"installMethods":346,"rationale":347,"selectedPaths":348,"source":324,"sourceLanguage":18,"type":245},"skills/algorithmic-art","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.","algorithmic-art",{"claudeCode":12},"SKILL.md frontmatter at skills/algorithmic-art/SKILL.md",[349,351,354,357],{"path":350,"priority":321},"SKILL.md",{"path":352,"priority":353},"LICENSE.txt","high",{"path":355,"priority":356},"templates/generator_template.js","low",{"path":358,"priority":356},"templates/viewer.html",{"basePath":360,"description":361,"displayName":362,"installMethods":363,"rationale":364,"selectedPaths":365,"source":324,"sourceLanguage":18,"type":245},"skills/brand-guidelines","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.","brand-guidelines",{"claudeCode":12},"SKILL.md frontmatter at skills/brand-guidelines/SKILL.md",[366,367],{"path":350,"priority":321},{"path":352,"priority":353},{"basePath":369,"description":370,"displayName":371,"installMethods":372,"rationale":373,"selectedPaths":374,"source":324,"sourceLanguage":18,"type":245},"skills/canvas-design","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.","canvas-design",{"claudeCode":12},"SKILL.md frontmatter at skills/canvas-design/SKILL.md",[375,376],{"path":350,"priority":321},{"path":352,"priority":353},{"basePath":242,"description":10,"displayName":13,"installMethods":378,"rationale":379,"selectedPaths":380,"source":324,"sourceLanguage":18,"type":245},{"claudeCode":12},"SKILL.md frontmatter at skills/claude-api/SKILL.md",[381,382],{"path":350,"priority":321},{"path":352,"priority":353},{"basePath":384,"description":385,"displayName":386,"installMethods":387,"rationale":388,"selectedPaths":389,"source":324,"sourceLanguage":18,"type":245},"skills/doc-coauthoring","Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.","doc-coauthoring",{"claudeCode":12},"SKILL.md frontmatter at skills/doc-coauthoring/SKILL.md",[390],{"path":350,"priority":321},{"basePath":392,"description":393,"displayName":394,"installMethods":395,"rationale":396,"selectedPaths":397,"source":324,"sourceLanguage":18,"type":245},"skills/docx","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.","docx",{"claudeCode":12},"SKILL.md frontmatter at skills/docx/SKILL.md",[398,399,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516],{"path":350,"priority":321},{"path":352,"priority":353},{"path":401,"priority":356},"scripts/__init__.py",{"path":403,"priority":356},"scripts/accept_changes.py",{"path":405,"priority":356},"scripts/comment.py",{"path":407,"priority":356},"scripts/office/helpers/__init__.py",{"path":409,"priority":356},"scripts/office/helpers/merge_runs.py",{"path":411,"priority":356},"scripts/office/helpers/simplify_redlines.py",{"path":413,"priority":356},"scripts/office/pack.py",{"path":415,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd",{"path":417,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd",{"path":419,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd",{"path":421,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd",{"path":423,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd",{"path":425,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd",{"path":427,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd",{"path":429,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd",{"path":431,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd",{"path":433,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd",{"path":435,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd",{"path":437,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd",{"path":439,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd",{"path":441,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd",{"path":443,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd",{"path":445,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd",{"path":447,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd",{"path":449,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd",{"path":451,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd",{"path":453,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd",{"path":455,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd",{"path":457,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd",{"path":459,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd",{"path":461,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd",{"path":463,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd",{"path":465,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd",{"path":467,"priority":356},"scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd",{"path":469,"priority":356},"scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd",{"path":471,"priority":356},"scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd",{"path":473,"priority":356},"scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd",{"path":475,"priority":356},"scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd",{"path":477,"priority":356},"scripts/office/schemas/mce/mc.xsd",{"path":479,"priority":356},"scripts/office/schemas/microsoft/wml-2010.xsd",{"path":481,"priority":356},"scripts/office/schemas/microsoft/wml-2012.xsd",{"path":483,"priority":356},"scripts/office/schemas/microsoft/wml-2018.xsd",{"path":485,"priority":356},"scripts/office/schemas/microsoft/wml-cex-2018.xsd",{"path":487,"priority":356},"scripts/office/schemas/microsoft/wml-cid-2016.xsd",{"path":489,"priority":356},"scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd",{"path":491,"priority":356},"scripts/office/schemas/microsoft/wml-symex-2015.xsd",{"path":493,"priority":356},"scripts/office/soffice.py",{"path":495,"priority":356},"scripts/office/unpack.py",{"path":497,"priority":356},"scripts/office/validate.py",{"path":499,"priority":356},"scripts/office/validators/__init__.py",{"path":501,"priority":356},"scripts/office/validators/base.py",{"path":503,"priority":356},"scripts/office/validators/docx.py",{"path":505,"priority":356},"scripts/office/validators/pptx.py",{"path":507,"priority":356},"scripts/office/validators/redlining.py",{"path":509,"priority":356},"scripts/templates/comments.xml",{"path":511,"priority":356},"scripts/templates/commentsExtended.xml",{"path":513,"priority":356},"scripts/templates/commentsExtensible.xml",{"path":515,"priority":356},"scripts/templates/commentsIds.xml",{"path":517,"priority":356},"scripts/templates/people.xml",{"basePath":519,"description":520,"displayName":521,"installMethods":522,"rationale":523,"selectedPaths":524,"source":324,"sourceLanguage":18,"type":245},"skills/frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","frontend-design",{"claudeCode":12},"SKILL.md frontmatter at skills/frontend-design/SKILL.md",[525,526],{"path":350,"priority":321},{"path":352,"priority":353},{"basePath":528,"description":529,"displayName":530,"installMethods":531,"rationale":532,"selectedPaths":533,"source":324,"sourceLanguage":18,"type":245},"skills/internal-comms","A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).","internal-comms",{"claudeCode":12},"SKILL.md frontmatter at skills/internal-comms/SKILL.md",[534,535,536,538,540,542],{"path":350,"priority":321},{"path":352,"priority":353},{"path":537,"priority":356},"examples/3p-updates.md",{"path":539,"priority":356},"examples/company-newsletter.md",{"path":541,"priority":356},"examples/faq-answers.md",{"path":543,"priority":356},"examples/general-comms.md",{"basePath":545,"description":546,"displayName":547,"installMethods":548,"rationale":549,"selectedPaths":550,"source":324,"sourceLanguage":18,"type":245},"skills/mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).","mcp-builder",{"claudeCode":12},"SKILL.md frontmatter at skills/mcp-builder/SKILL.md",[551,552,553,555,557,559],{"path":350,"priority":321},{"path":352,"priority":353},{"path":554,"priority":356},"scripts/connections.py",{"path":556,"priority":356},"scripts/evaluation.py",{"path":558,"priority":356},"scripts/example_evaluation.xml",{"path":560,"priority":356},"scripts/requirements.txt",{"basePath":562,"description":563,"displayName":564,"installMethods":565,"rationale":566,"selectedPaths":567,"source":324,"sourceLanguage":18,"type":245},"skills/pdf","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.","pdf",{"claudeCode":12},"SKILL.md frontmatter at skills/pdf/SKILL.md",[568,569,570,573,575,577,579,581,583,585,587,589],{"path":350,"priority":321},{"path":352,"priority":353},{"path":571,"priority":572},"forms.md","medium",{"path":574,"priority":572},"reference.md",{"path":576,"priority":356},"scripts/check_bounding_boxes.py",{"path":578,"priority":356},"scripts/check_fillable_fields.py",{"path":580,"priority":356},"scripts/convert_pdf_to_images.py",{"path":582,"priority":356},"scripts/create_validation_image.py",{"path":584,"priority":356},"scripts/extract_form_field_info.py",{"path":586,"priority":356},"scripts/extract_form_structure.py",{"path":588,"priority":356},"scripts/fill_fillable_fields.py",{"path":590,"priority":356},"scripts/fill_pdf_form_with_annotations.py",{"basePath":592,"description":593,"displayName":594,"installMethods":595,"rationale":596,"selectedPaths":597,"source":324,"sourceLanguage":18,"type":245},"skills/pptx","Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.","pptx",{"claudeCode":12},"SKILL.md frontmatter at skills/pptx/SKILL.md",[598,599,600,602,604,605,607,609,610,611,612,613,614,615,616,617,618,619,620,621,622,623,624,625,626,627,628,629,630,631,632,633,634,635,636,637,638,639,640,641,642,643,644,645,646,647,648,649,650,651,652,653,654,655,656,657,658,659,660],{"path":350,"priority":321},{"path":352,"priority":353},{"path":601,"priority":572},"editing.md",{"path":603,"priority":572},"pptxgenjs.md",{"path":401,"priority":356},{"path":606,"priority":356},"scripts/add_slide.py",{"path":608,"priority":356},"scripts/clean.py",{"path":407,"priority":356},{"path":409,"priority":356},{"path":411,"priority":356},{"path":413,"priority":356},{"path":415,"priority":356},{"path":417,"priority":356},{"path":419,"priority":356},{"path":421,"priority":356},{"path":423,"priority":356},{"path":425,"priority":356},{"path":427,"priority":356},{"path":429,"priority":356},{"path":431,"priority":356},{"path":433,"priority":356},{"path":435,"priority":356},{"path":437,"priority":356},{"path":439,"priority":356},{"path":441,"priority":356},{"path":443,"priority":356},{"path":445,"priority":356},{"path":447,"priority":356},{"path":449,"priority":356},{"path":451,"priority":356},{"path":453,"priority":356},{"path":455,"priority":356},{"path":457,"priority":356},{"path":459,"priority":356},{"path":461,"priority":356},{"path":463,"priority":356},{"path":465,"priority":356},{"path":467,"priority":356},{"path":469,"priority":356},{"path":471,"priority":356},{"path":473,"priority":356},{"path":475,"priority":356},{"path":477,"priority":356},{"path":479,"priority":356},{"path":481,"priority":356},{"path":483,"priority":356},{"path":485,"priority":356},{"path":487,"priority":356},{"path":489,"priority":356},{"path":491,"priority":356},{"path":493,"priority":356},{"path":495,"priority":356},{"path":497,"priority":356},{"path":499,"priority":356},{"path":501,"priority":356},{"path":503,"priority":356},{"path":505,"priority":356},{"path":507,"priority":356},{"path":661,"priority":356},"scripts/thumbnail.py",{"basePath":663,"description":664,"displayName":665,"installMethods":666,"rationale":667,"selectedPaths":668,"source":324,"sourceLanguage":18,"type":245},"skills/skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","skill-creator",{"claudeCode":12},"SKILL.md frontmatter at skills/skill-creator/SKILL.md",[669,670,671,673,675,676,678,680,682,684,686,688,690],{"path":350,"priority":321},{"path":352,"priority":353},{"path":672,"priority":356},"assets/eval_review.html",{"path":674,"priority":572},"references/schemas.md",{"path":401,"priority":356},{"path":677,"priority":356},"scripts/aggregate_benchmark.py",{"path":679,"priority":356},"scripts/generate_report.py",{"path":681,"priority":356},"scripts/improve_description.py",{"path":683,"priority":356},"scripts/package_skill.py",{"path":685,"priority":356},"scripts/quick_validate.py",{"path":687,"priority":356},"scripts/run_eval.py",{"path":689,"priority":356},"scripts/run_loop.py",{"path":691,"priority":356},"scripts/utils.py",{"basePath":693,"description":694,"displayName":695,"installMethods":696,"rationale":697,"selectedPaths":698,"source":324,"sourceLanguage":18,"type":245},"skills/slack-gif-creator","Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like \"make me a GIF of X doing Y for Slack.\"","slack-gif-creator",{"claudeCode":12},"SKILL.md frontmatter at skills/slack-gif-creator/SKILL.md",[699,700],{"path":350,"priority":321},{"path":352,"priority":353},{"basePath":702,"description":703,"displayName":704,"installMethods":705,"rationale":706,"selectedPaths":707,"source":324,"sourceLanguage":18,"type":245},"skills/theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","theme-factory",{"claudeCode":12},"SKILL.md frontmatter at skills/theme-factory/SKILL.md",[708,709],{"path":350,"priority":321},{"path":352,"priority":353},{"basePath":711,"description":712,"displayName":713,"installMethods":714,"rationale":715,"selectedPaths":716,"source":324,"sourceLanguage":18,"type":245},"skills/web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.","web-artifacts-builder",{"claudeCode":12},"SKILL.md frontmatter at skills/web-artifacts-builder/SKILL.md",[717,718,719,721,723],{"path":350,"priority":321},{"path":352,"priority":353},{"path":720,"priority":356},"scripts/bundle-artifact.sh",{"path":722,"priority":356},"scripts/init-artifact.sh",{"path":724,"priority":356},"scripts/shadcn-components.tar.gz",{"basePath":726,"description":727,"displayName":728,"installMethods":729,"rationale":730,"selectedPaths":731,"source":324,"sourceLanguage":18,"type":245},"skills/webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","webapp-testing",{"claudeCode":12},"SKILL.md frontmatter at skills/webapp-testing/SKILL.md",[732,733,734,736,738,740],{"path":350,"priority":321},{"path":352,"priority":353},{"path":735,"priority":356},"examples/console_logging.py",{"path":737,"priority":356},"examples/element_discovery.py",{"path":739,"priority":356},"examples/static_html_automation.py",{"path":741,"priority":356},"scripts/with_server.py",{"basePath":743,"description":744,"displayName":745,"installMethods":746,"rationale":747,"selectedPaths":748,"source":324,"sourceLanguage":18,"type":245},"skills/xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","xlsx",{"claudeCode":12},"SKILL.md frontmatter at skills/xlsx/SKILL.md",[749,750,751,752,753,754,755,756,757,758,759,760,761,762,763,764,765,766,767,768,769,770,771,772,773,774,775,776,777,778,779,780,781,782,783,784,785,786,787,788,789,790,791,792,793,794,795,796,797,798,799,800,801,802],{"path":350,"priority":321},{"path":352,"priority":353},{"path":407,"priority":356},{"path":409,"priority":356},{"path":411,"priority":356},{"path":413,"priority":356},{"path":415,"priority":356},{"path":417,"priority":356},{"path":419,"priority":356},{"path":421,"priority":356},{"path":423,"priority":356},{"path":425,"priority":356},{"path":427,"priority":356},{"path":429,"priority":356},{"path":431,"priority":356},{"path":433,"priority":356},{"path":435,"priority":356},{"path":437,"priority":356},{"path":439,"priority":356},{"path":441,"priority":356},{"path":443,"priority":356},{"path":445,"priority":356},{"path":447,"priority":356},{"path":449,"priority":356},{"path":451,"priority":356},{"path":453,"priority":356},{"path":455,"priority":356},{"path":457,"priority":356},{"path":459,"priority":356},{"path":461,"priority":356},{"path":463,"priority":356},{"path":465,"priority":356},{"path":467,"priority":356},{"path":469,"priority":356},{"path":471,"priority":356},{"path":473,"priority":356},{"path":475,"priority":356},{"path":477,"priority":356},{"path":479,"priority":356},{"path":481,"priority":356},{"path":483,"priority":356},{"path":485,"priority":356},{"path":487,"priority":356},{"path":489,"priority":356},{"path":491,"priority":356},{"path":493,"priority":356},{"path":495,"priority":356},{"path":497,"priority":356},{"path":499,"priority":356},{"path":501,"priority":356},{"path":503,"priority":356},{"path":505,"priority":356},{"path":507,"priority":356},{"path":803,"priority":356},"scripts/recalc.py",{"basePath":805,"description":806,"displayName":807,"installMethods":808,"rationale":809,"selectedPaths":810,"source":324,"sourceLanguage":812,"type":245},"template","Replace with description of the skill and when Claude should use it.","template-skill",{"claudeCode":12},"SKILL.md frontmatter at template/SKILL.md",[811],{"path":350,"priority":321},"fr",{"sources":814},[815],"manual",{"closedIssues90d":232,"description":817,"forks":233,"openIssues90d":234,"pushedAt":235,"readmeSize":230,"stars":236,"topics":818},"Public repository for Agent Skills",[819],"agent-skills",{"classifiedAt":821,"discoverAt":822,"extractAt":823,"githubAt":823,"updatedAt":821},1778675442937,1778675438038,1778675441020,[212,215,13,214,213,216],{"evaluatedAt":240,"extractAt":286,"updatedAt":240},[],[828,856,890,919,947,978],{"_creationTime":829,"_id":830,"community":831,"display":832,"identity":838,"providers":841,"relations":850,"tags":852,"workflow":853},1778695021936.555,"k1715rn9402s29yge55y9nt0x986n2tf",{"reviewCount":8},{"description":833,"installMethods":834,"name":836,"sourceUrl":837},"Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.",{"claudeCode":835},"openai/skills","cli-creator","https://github.com/openai/skills",{"basePath":839,"githubOwner":840,"githubRepo":244,"locale":18,"slug":836,"type":245},"skills/.curated/cli-creator","openai",{"evaluate":842,"extract":849},{"promptVersionExtension":205,"promptVersionScoring":206,"score":843,"tags":844,"targetMarket":217,"tier":848},100,[845,214,295,846,847],"cli","codex","automation","verified",{"commitSha":276},{"repoId":851},"kd75n2zj3yh472p25zffgycved86mnpx",[847,845,214,846,295],{"evaluatedAt":854,"extractAt":855,"updatedAt":854},1778695068759,1778695021936,{"_creationTime":857,"_id":858,"community":859,"display":860,"identity":866,"providers":871,"relations":882,"tags":885,"workflow":886},1778693768760.7378,"k175yn0rkw0qm6g8ctn8fm789586mft8",{"reviewCount":8},{"description":861,"installMethods":862,"name":864,"sourceUrl":865},"使用并行子代理军队管理 context-mode GitHub 问题、PR、发布和营销。为每个任务编排 10-20 个动态代理。在分类问题、审查 PR、发布版本、撰写 LinkedIn 帖子、宣布发布、修复错误、合并贡献、验证 ENV 变量、测试适配器或同步分支时使用。",{"claudeCode":863},"mksglu/context-mode","context-mode-ops","https://github.com/mksglu/context-mode",{"basePath":867,"githubOwner":868,"githubRepo":869,"locale":870,"slug":864,"type":245},".claude/skills/context-mode-ops","mksglu","context-mode","zh-CN",{"evaluate":872,"extract":881},{"promptVersionExtension":205,"promptVersionScoring":206,"score":843,"tags":873,"targetMarket":217,"tier":848},[874,875,876,214,877,878,879,880],"context-window","llm-optimization","session-continuity","developer-tool","productivity","security","compliance",{"commitSha":276},{"repoId":883,"translatedFrom":884},"kd764b2fctbqg4b8j8y6xvmkvs86m29m","k1758b69g51wttzw4r6epd3jrs86mtk8",[214,880,874,877,875,878,879,876],{"evaluatedAt":887,"extractAt":888,"updatedAt":889},1778693567505,1778693511416,1778693768760,{"_creationTime":891,"_id":892,"community":893,"display":894,"identity":900,"providers":904,"relations":911,"tags":914,"workflow":915},1778692997480.065,"k174jb7x7h52qzjr42hvgsxpj986mgws",{"reviewCount":8},{"description":895,"installMethods":896,"name":898,"sourceUrl":899},"使用严格的交付工作流执行编码任务：构建完整计划、分步实现、持续运行测试，并默认在每一步 (`per_step`) 后提交。当用户要求行为驱动交付或需求不明确时，支持显式提交策略覆盖 (`final_only`, `milestone`) 和可选的 BDD（给定/当/则）。",{"claudeCode":897},"majiayu000/vibeguard","fixflow","https://github.com/majiayu000/vibeguard",{"basePath":901,"githubOwner":902,"githubRepo":903,"locale":870,"slug":898,"type":245},"workflows/fixflow","majiayu000","vibeguard",{"evaluate":905,"extract":910},{"promptVersionExtension":205,"promptVersionScoring":206,"score":843,"tags":906,"targetMarket":217,"tier":848},[907,908,295,214,909,879],"code-quality","ai-safety","workflow-automation",{"commitSha":276},{"repoId":912,"translatedFrom":913},"kd7b0vh258xpbyerk68bk3e1ks86mk58","k17bwx69hk0p0w7rnpzvv2p16h86mp2k",[908,214,907,295,879,909],{"evaluatedAt":916,"extractAt":917,"updatedAt":918},1778692812461,1778692607327,1778692997480,{"_creationTime":920,"_id":921,"community":922,"display":923,"identity":929,"providers":933,"relations":941,"tags":943,"workflow":944},1778687399826.038,"k177k6yc1nvmc35w54dht6t11586np31",{"reviewCount":8},{"description":924,"installMethods":925,"name":927,"sourceUrl":928},"Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library.",{"claudeCode":926},"github/awesome-copilot","kotlin-mcp-server-generator","https://github.com/github/awesome-copilot",{"basePath":930,"githubOwner":931,"githubRepo":932,"locale":18,"slug":927,"type":245},"skills/kotlin-mcp-server-generator","github","awesome-copilot",{"evaluate":934,"extract":940},{"promptVersionExtension":205,"promptVersionScoring":206,"score":843,"tags":935,"targetMarket":217,"tier":848},[936,937,938,214,939],"kotlin","mcp","server","gradle",{"commitSha":276},{"repoId":942},"kd7dsmv976w8rtkqnjjfdtfgks86nnmw",[214,939,936,937,938],{"evaluatedAt":945,"extractAt":946,"updatedAt":945},1778690535577,1778687399826,{"_creationTime":948,"_id":949,"community":950,"display":951,"identity":957,"providers":962,"relations":971,"tags":974,"workflow":975},1778675056600.2686,"k173gm7eeaah3h512009r9g6vn86mj43",{"reviewCount":8},{"description":952,"installMethods":953,"name":955,"sourceUrl":956},"Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project specification and expects a complete, runnable repository. Stack-agnostic: Next.js, FastAPI, Rails, Go, Rust, Flutter, and more.",{"claudeCode":954},"alirezarezvani/claude-skills","Spec to Repo","https://github.com/alirezarezvani/claude-skills",{"basePath":958,"githubOwner":959,"githubRepo":960,"locale":18,"slug":961,"type":245},"product-team/skills/spec-to-repo","alirezarezvani","claude-skills","spec-to-repo",{"evaluate":963,"extract":969},{"promptVersionExtension":205,"promptVersionScoring":206,"score":843,"tags":964,"targetMarket":217,"tier":848},[214,965,966,967,968],"scaffolding","application-development","fullstack","stack-agnostic",{"commitSha":276,"license":970},"MIT",{"parentExtensionId":972,"repoId":973},"k17104ysr0smp7vvp26mnn1fzh86nynm","kd7ff9s1w43mfyy1n7hf87816186m6px",[966,214,967,965,968],{"evaluatedAt":976,"extractAt":977,"updatedAt":976},1778685725353,1778675056600,{"_creationTime":979,"_id":980,"community":981,"display":982,"identity":986,"providers":988,"relations":995,"tags":997,"workflow":998},1778675056600.2441,"k171y80q0m602mftp477895w5s86n54t",{"reviewCount":8},{"description":983,"installMethods":984,"name":985,"sourceUrl":956},"Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.",{"claudeCode":954},"extract",{"basePath":987,"githubOwner":959,"githubRepo":960,"locale":18,"slug":985,"type":245},"engineering-team/self-improving-agent/skills/extract",{"evaluate":989,"extract":994},{"promptVersionExtension":205,"promptVersionScoring":206,"score":843,"tags":990,"targetMarket":217,"tier":848},[991,992,214,993,295],"skill-extraction","agent-development","knowledge-management",{"commitSha":276},{"parentExtensionId":996,"repoId":973},"k171b5pw3erme9qy3334r4gbv586mzhf",[992,214,295,993,991],{"evaluatedAt":999,"extractAt":977,"updatedAt":999},1778682824392]