$ show anthropics/skills
This repository is a collection of Claude/Anthropic skills and platform documentation rather than a standalone application. It contains skill definitions (SKILL.md files), MCP server evaluation guidance, managed-agents documentation, and supporting tooling such as schema definitions and build scripts. The dominant character is developer-facing content and reusable patterns for building LLM agents, with some executable scripts for validation and report generation. It provides structured output schemas for evaluation pipelines (grading, benchmark, comparison, analysis), a validator hierarchy for XML/XSD-based skill files, and a security-conscious file I/O example in build-report-lite.mjs. It also documents managed agents, platform availability, and MCP best practices. The repository is not a data research project; there are no notebooks, data pipelines, or model training scripts. Maintenance is active, but technical drift is medium due to version-sensitive SDK references, manually maintained platform availability tables, and multiple language-specific examples that must be kept in sync. The code and schemas are generally well-structured and reusable, though some paths are hardcoded and some documentation is tightly coupled to generator scripts.
The LLM identified 4 files worth highlighting for reuse:
Defines explicit JSON schemas for grading, benchmark, comparison, and analysis outputs. Reusable as a contract for any LLM evaluation pipeline; fields like pass_rate and structured criteria make results machine-checkable.
Demonstrates a secure file-output pattern using O_NOFOLLOW, fstat-after-open, hard-link detection, and path containment. Extractable as a template for any tool that writes files based on untrusted or model-influenced input.
Well-structured validator hierarchy with BaseSchemaValidator providing common logic (XML parsing, namespace checks, unique IDs, file references, content types, XSD validation) and subclasses adding format-specific checks. Isolated enough to extract into a reusable validation library.
Centralizes feature availability across Claude platforms. Although manually maintained, it is a reusable pattern for keeping multi-platform API docs consistent and is referenced by language-specific managed-agent guides.