{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"npm-skilld","slug":"skilld","name":"skilld","type":"skill","url":"https://github.com/skilld-dev/skilld#readme","page_url":"https://unfragile.ai/skilld","categories":["automation"],"tags":["ai","agent","skills","npm","documentation","claude","llm","cursor","codex"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"npm-skilld__cap_0","uri":"capability://code.generation.editing.npm.package.documentation.to.agent.skill.conversion","name":"npm-package-documentation-to-agent-skill-conversion","description":"Automatically extracts API signatures, function definitions, and usage patterns from npm package README and documentation files, then generates structured skill definitions compatible with AI agent frameworks. Uses LLM-powered parsing to understand package semantics and convert unstructured documentation into machine-readable skill schemas with parameter types, return values, and usage examples.","intents":["I want to quickly enable my AI agent to use an npm package without manually writing skill definitions","I need to generate tool-use schemas from existing package documentation to avoid manual API mapping","I want to batch-convert multiple npm packages into agent-compatible skill definitions"],"best_for":["AI agent developers building multi-tool systems with npm ecosystem packages","Teams automating agent capability expansion without manual schema writing","LLM application builders using Claude or similar models with tool-calling support"],"limitations":["Accuracy depends on documentation quality and clarity — poorly documented packages may generate incomplete or incorrect skill definitions","Requires LLM API calls (Claude) for each package, adding latency and cost per conversion","No built-in validation that generated skills actually work with the target package version","Limited to npm packages with accessible documentation; private or undocumented packages will fail"],"requires":["Node.js 14+ (npm package ecosystem access)","Claude API key or compatible LLM endpoint","npm package with accessible README or documentation file","Agent framework supporting skill/tool schema format (e.g., Claude's tool_use format)"],"input_types":["npm package name (string)","package documentation (markdown/text)","package.json metadata"],"output_types":["structured skill definition (JSON schema)","function signatures with typed parameters","usage examples and descriptions"],"categories":["code-generation-editing","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-skilld__cap_1","uri":"capability://code.generation.editing.claude.api.skill.generation.with.structured.output","name":"claude-api-skill-generation-with-structured-output","description":"Leverages Claude's API with structured output mode to generate deterministic, schema-compliant skill definitions from package documentation. Sends documentation context to Claude with a predefined JSON schema, ensuring generated skills conform to agent framework requirements without post-processing or validation overhead.","intents":["I want to generate skills that are guaranteed to match my agent's expected schema format","I need reproducible skill generation without manual fixing or schema validation","I want to batch-process multiple packages with consistent output structure"],"best_for":["Teams using Claude as their primary LLM and needing deterministic skill generation","Production systems requiring schema-compliant output without fallback handling","Developers building skill generation pipelines that feed directly into agent systems"],"limitations":["Locked to Claude API — no support for other LLM providers (GPT-4, Gemini, local models)","Requires Claude API credits/billing for each package processed","Structured output mode may limit Claude's ability to handle edge cases or unusual documentation patterns","No fallback mechanism if Claude API is unavailable or rate-limited"],"requires":["Claude API key with access to models supporting structured output (Claude 3.5+)","Network connectivity to Anthropic API","Predefined JSON schema matching agent framework requirements"],"input_types":["npm package documentation (markdown/text)","target skill schema (JSON schema definition)"],"output_types":["structured skill definition (JSON, schema-compliant)","typed function parameters and return values"],"categories":["code-generation-editing","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-skilld__cap_2","uri":"capability://automation.workflow.batch.npm.package.skill.discovery.and.generation","name":"batch-npm-package-skill-discovery-and-generation","description":"Processes multiple npm packages in sequence or parallel, automatically fetching package metadata, documentation, and generating skills for each. Handles package resolution, documentation discovery, and skill generation with error handling and progress tracking across a package list.","intents":["I want to generate skills for my entire project's npm dependencies at once","I need to create a skill library covering multiple related packages (e.g., all lodash utilities)","I want to automate skill generation as part of my agent setup or CI/CD pipeline"],"best_for":["Teams managing agents with large tool ecosystems","CI/CD pipelines that need to auto-generate skills from dependency trees","Developers building skill libraries for reuse across multiple agents"],"limitations":["Batch processing multiplies API costs and latency — processing 100 packages requires 100 Claude API calls","No intelligent deduplication — if multiple packages expose similar functions, skills may be redundant","Error in one package doesn't prevent others from processing, but error reporting and recovery is manual","No built-in caching — re-running batch generation re-processes all packages without incremental updates"],"requires":["Node.js 14+","Claude API key with sufficient quota for batch processing","npm registry access or local package.json with dependencies","Sufficient API rate limit for concurrent/sequential package processing"],"input_types":["array of npm package names (strings)","package.json file with dependencies","npm registry metadata"],"output_types":["array of skill definitions (JSON)","skill manifest or registry (structured data)","error report for failed packages"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-skilld__cap_3","uri":"capability://data.processing.analysis.documentation.parsing.and.api.extraction","name":"documentation-parsing-and-api-extraction","description":"Extracts API signatures, function definitions, parameter types, return values, and usage examples from unstructured package documentation (README, docs files). Uses LLM-powered semantic analysis to identify callable functions, their constraints, and contextual usage patterns without requiring structured metadata or AST parsing.","intents":["I want to understand what functions a package exposes without reading the full documentation","I need to extract parameter types and constraints from documentation examples","I want to identify which functions are safe/appropriate for agent tool-calling"],"best_for":["Developers integrating packages into agent systems without manual API review","Teams building automated documentation-to-schema pipelines","LLM-powered tools that need to understand package capabilities programmatically"],"limitations":["Accuracy depends on documentation quality — incomplete or ambiguous docs produce incomplete skill definitions","No type inference from source code — relies entirely on documentation, missing implicit types or constraints","Cannot detect breaking changes between package versions from documentation alone","Struggles with packages using non-standard documentation formats or heavy code examples without explanation"],"requires":["Package documentation in accessible format (markdown, HTML, or plain text)","Claude API key for semantic analysis","Documentation that includes function signatures or usage examples"],"input_types":["markdown documentation (string)","README files","API documentation pages"],"output_types":["extracted function signatures (JSON)","parameter definitions with types","usage examples and constraints"],"categories":["data-processing-analysis","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-skilld__cap_4","uri":"capability://code.generation.editing.agent.framework.skill.schema.generation","name":"agent-framework-skill-schema-generation","description":"Generates skill definitions in formats compatible with specific AI agent frameworks (Claude tools, LangChain tools, etc.). Maps extracted API information to framework-specific schema requirements, including parameter validation, return type definitions, and tool metadata (descriptions, categories, tags).","intents":["I want to generate skills that work directly with my agent framework without manual schema mapping","I need to ensure generated skills follow my framework's tool-calling conventions","I want to generate skills with proper descriptions and metadata for agent decision-making"],"best_for":["Developers using Claude, LangChain, or other agent frameworks with tool-calling support","Teams standardizing skill definitions across multiple agent implementations","Builders creating agent skill libraries for specific frameworks"],"limitations":["Currently supports Claude tool format primarily — limited support for other frameworks","No automatic conversion between framework formats — skills generated for one framework may not port to another","Framework-specific constraints (e.g., parameter count limits, description length) may cause generation failures","Requires knowledge of target framework's schema requirements to configure generation correctly"],"requires":["Target agent framework specified (e.g., 'claude', 'langchain')","Framework schema definition or documentation","Claude API key for generation"],"input_types":["extracted API definitions (JSON)","framework identifier (string)","framework schema constraints"],"output_types":["framework-specific skill definition (JSON)","tool schema with metadata","parameter validation rules"],"categories":["code-generation-editing","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-skilld__cap_5","uri":"capability://data.processing.analysis.skill.parameter.type.inference.and.validation","name":"skill-parameter-type-inference-and-validation","description":"Infers parameter types, constraints, and validation rules from documentation examples, function signatures, and usage patterns. Generates parameter definitions with type information (string, number, boolean, object, array) and constraints (required/optional, min/max values, enum values, regex patterns) suitable for agent tool-calling validation.","intents":["I want to ensure agent tools validate parameters before calling functions","I need to infer parameter types from documentation without manual specification","I want to generate parameter constraints that prevent invalid function calls"],"best_for":["Teams building robust agent systems that need parameter validation","Developers automating skill generation with type safety","Builders creating agent tools that need to guide LLM parameter selection"],"limitations":["Type inference from documentation is heuristic-based — complex types or union types may be inferred incorrectly","Cannot detect runtime constraints not mentioned in documentation (e.g., API rate limits, authentication requirements)","No validation that inferred types match actual function implementation","Struggles with polymorphic functions that accept multiple parameter types"],"requires":["Documentation with function signatures or usage examples","Claude API for semantic type inference","Target framework's type system definition"],"input_types":["function documentation (markdown/text)","usage examples","function signatures"],"output_types":["parameter definitions with types (JSON schema)","validation rules and constraints","required/optional flags"],"categories":["data-processing-analysis","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-skilld__cap_6","uri":"capability://text.generation.language.skill.description.and.metadata.generation","name":"skill-description-and-metadata-generation","description":"Generates human-readable descriptions, usage guidelines, and metadata for skills based on package documentation. Creates descriptions suitable for agent decision-making (helping LLMs understand when to use a skill) and includes examples, warnings, and contextual information extracted from documentation.","intents":["I want my agent to understand when and how to use each skill","I need to generate skill descriptions that help LLMs make better tool-calling decisions","I want to include usage examples and warnings in skill metadata"],"best_for":["Teams building agents that need rich skill metadata for better decision-making","Developers creating skill libraries with comprehensive documentation","Builders optimizing agent performance through better skill descriptions"],"limitations":["Description quality depends on source documentation — poor docs produce poor descriptions","No automatic detection of dangerous or side-effect-heavy functions — requires manual review","Descriptions may be too verbose or too terse depending on documentation style","Cannot infer when a skill should NOT be used without explicit warnings in documentation"],"requires":["Package documentation with clear explanations and examples","Claude API for description generation","Target framework's metadata requirements"],"input_types":["package documentation (markdown/text)","function descriptions and examples","usage patterns and warnings"],"output_types":["skill description (string)","usage guidelines (string)","examples and warnings (structured data)","metadata tags and categories"],"categories":["text-generation-language","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-skilld__cap_7","uri":"capability://tool.use.integration.cursor.ide.integration.for.skill.generation","name":"cursor-ide-integration-for-skill-generation","description":"Integrates with Cursor IDE to enable in-editor skill generation from npm packages. Allows developers to generate skills directly from Cursor's AI assistant interface, with context from the current project and dependencies. Leverages Cursor's LLM integration to streamline the skill generation workflow within the development environment.","intents":["I want to generate skills without leaving my IDE","I need to quickly add skills for packages I'm currently working with","I want to use Cursor's AI assistant to help generate and review skills"],"best_for":["Cursor IDE users building AI agents","Teams using Cursor as their primary development environment","Developers who want to integrate skill generation into their coding workflow"],"limitations":["Requires Cursor IDE — not available in VS Code or other editors","Depends on Cursor's LLM integration and API availability","Limited to packages accessible from the current project context","No built-in skill validation or testing within the IDE"],"requires":["Cursor IDE installed and configured","Cursor API access and LLM integration enabled","npm packages in current project or accessible via npm registry"],"input_types":["npm package name (from IDE context or user input)","current project dependencies"],"output_types":["skill definition (JSON, displayed in IDE)","generated code snippets for skill integration"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":31,"verified":false,"data_access_risk":"low","permissions":["Node.js 14+ (npm package ecosystem access)","Claude API key or compatible LLM endpoint","npm package with accessible README or documentation file","Agent framework supporting skill/tool schema format (e.g., Claude's tool_use format)","Claude API key with access to models supporting structured output (Claude 3.5+)","Network connectivity to Anthropic API","Predefined JSON schema matching agent framework requirements","Node.js 14+","Claude API key with sufficient quota for batch processing","npm registry access or local package.json with dependencies"],"failure_modes":["Accuracy depends on documentation quality and clarity — poorly documented packages may generate incomplete or incorrect skill definitions","Requires LLM API calls (Claude) for each package, adding latency and cost per conversion","No built-in validation that generated skills actually work with the target package version","Limited to npm packages with accessible documentation; private or undocumented packages will fail","Locked to Claude API — no support for other LLM providers (GPT-4, Gemini, local models)","Requires Claude API credits/billing for each package processed","Structured output mode may limit Claude's ability to handle edge cases or unusual documentation patterns","No fallback mechanism if Claude API is unavailable or rate-limited","Batch processing multiplies API costs and latency — processing 100 packages requires 100 Claude API calls","No intelligent deduplication — if multiple packages expose similar functions, skills may be redundant","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.2633617504106044,"quality":0.26,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.6,"weights":{"adoption":0.15,"quality":0.25,"ecosystem":0.1,"match_graph":0.45,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:23.902Z","last_scraped_at":"2026-04-22T08:08:13.651Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":1037,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=skilld","compare_url":"https://unfragile.ai/compare?artifact=skilld"}},"signature":"1tmi97ZnqxmUef/GzZ4vpuHPmZ4FgpYlrtFx8BxbLpYhdnZ27dy7KHPYBm2V+kcDTr4Npd9qm3j4hTeom1RfDg==","signedAt":"2026-06-22T01:01:08.197Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/skilld","artifact":"https://unfragile.ai/skilld","verify":"https://unfragile.ai/api/v1/verify?slug=skilld","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}