Explorar skills

Container-based development for isolated, reproducible environments. Use when running npm commands, installing packages, executing code, or managing project dependencies. Trigger phrases include "npm install", "run the build", "start the server", "install package", or any code execution request.

Apply idiomatic Python patterns: list comprehensions, generators, context managers, decorators, dataclasses, walrus operator, and unpacking. Use when the user writes Python code, asks for Pythonic idioms, refactors Python, or mentions any of these patterns. Trigger proactively when you see non-idiomatic Python.

Master TypeScript generics for reusable, type-safe abstractions. Use when the user works with generic constraints, conditional types, mapped types, the infer keyword, utility types, recursive types, or needs help building type-safe libraries, APIs, or data structures.

Prevent OWASP Top 10 vulnerabilities in web applications. Activate whenever the user writes API endpoints, form handlers, database queries, authentication logic, file uploads, HTML rendering, or any code that handles user input or external data. Also activate when the user asks about security, hardening, or vulnerability prevention.

Guide for Docker multi-stage builds with builder patterns, distroless and alpine base images, cache mounts, and build args. Use when the user needs to optimize Docker image size, separate build from runtime dependencies, or improve build performance. Trigger when the user mentions multi-stage, distroless, slim images, or Docker build optimization.

Guide git branching strategies, branch naming, and merge/rebase decisions. Use when the user creates branches, asks about Git Flow vs trunk-based development, discusses merge vs rebase, or is setting up a new repository's branching model.

Docker and OCI image hardening — base-image selection, USER/caps/read-only FS discipline, distroless migration, build-time scanning with trivy/grype, image signing via sigstore, and runtime guardrails (seccomp, AppArmor).

Guide for Anthropic Python/TypeScript SDK usage including messages API, streaming, prompt caching, batches, token counting, and error handling. Use when the user is building with the Anthropic API, setting up Claude SDK, calling messages endpoints, implementing streaming, or troubleshooting API errors.

Guide for creating MCP (Model Context Protocol) servers in TypeScript and Python, including scaffolding, transports, lifecycle hooks, and testing. Use when the user wants to build an MCP server, add tools/resources/prompts to an MCP server, configure stdio or SSE transport, or test MCP server functionality.

Validate data with Pydantic v2: BaseModel, Field validators, model validators, computed fields, discriminated unions, and custom types. Use when the user defines API schemas, validates input data, works with Pydantic models, or asks about data validation in Python. Trigger when you see dict-based data handling that should use Pydantic models.

This skill should be used when the user asks about 'knowledge gaps', 'package coverage', 'which packages need notes', 'undocumented dependencies', 'dependency audit', 'missing documentation', 'tool coverage', 'undocumented tools', 'brew/action/docker/vscode coverage', 'standard coverage', 'protocol coverage', 'domain standards', 'concept gaps', 'missing hub notes', 'undocumented concepts', 'topics

This skill should be used when the user asks to 'research a homebrew formula', 'brew intel', 'what does [brew-tool] do', 'research a cask', 'cask intel', 'what does [cask] do', 'research a GitHub Action', 'action intel', 'what does [action] do', 'research a docker image', 'docker intel', 'what does [docker image] do', 'research a VSCode extension', 'vscode intel', 'what does [extension] do', 'rese