verify-code
Run a strict verification gate after implementation; provide evidence from tests/checks.
Discover Tools skills, compare source repositories and read the instructions for each workflow.
Run a strict verification gate after implementation; provide evidence from tests/checks.
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skil...
Deploy and manage Kubernetes applications with Helm charts. Covers K8s manifests, kubectl, Kustomize, RBAC, and container orchestration. Use for container deployments, microservices, and cloud-native applicatio...
Patrones TypeScript estrictos para este portfolio (Vue 3 + Nuxt 4). Trigger: Al definir tipos, interfaces, composables tipados o props de componentes Vue.
Intelligent bridge for Frontend-Backend data interoperability. Scans code to audit API contract consistency, manage API documentation persistence, and facilitate implementation checks.
Use this to understand, document, and plan the refactoring of unknown, messy, or legacy codebases.
Comprehensive technical debt scanner. Finds duplicated code, dead code, inconsistent patterns, and cleanup opportunities.
Plugin Recommendations for Claude Code: official plugins, LSP integrations, and community extensions. Trigger: plugin, install plugin, plugin recommendations, LSP, language server
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, cal...
Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.
Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScrip...
Use when CLAUDE.md is bloated or ineffective. Use when Claude ignores instructions, file exceeds 150 lines, response formatting rules aren't working, or user asks to optimize/restructure their Claude Code confi...
Interprets CodeScene behavioral code analysis warnings and produces concrete code fixes. Use when the user provides a CodeScene warning, hotspot alert, complexity increase, delivery risk, or code health finding...
Use when reasoning about Avalonia-based UI, XAML-like layouts, MVVM patterns, and Avalonia-specific APIs or constraints.
Using TeX/LaTeX in Observable Framework for mathematical typesetting.
Use any time you are writing TypeScript code.
Interact with Storj Gerrit team code collaboration service, which we just called it gerrit, when the user ask to do it
Process inline HTML review comments () in a Markdown file — applies editorial changes via Obsidian (if available) or directly via Edit tool
Map Pencil MCP design tokens and reusable components to enforced SwiftUI coding rules. Use when generating or refactoring SwiftUI from .pen-based designs and you must enforce naming conventions, spacing tokens,...
When explicitly switching modes or when mode detection shows low confidence. Provides guidance on optimal approach for each detected mode (debugging, performance, feature, refactor, exploration, infrastructure)...
Extract reusable patterns from the current session and save them as instincts
Create new Agent Skills for VS Code using the open standard format. Covers skill structure, YAML frontmatter, content organization, examples, and resources. Enables building reusable capabilities that work acro...
Step-by-step guidance for creating custom Copilot agents in VS Code, including YAML frontmatter, file structure, handoffs, and best practices. Use when you want to define a new persona, workflow, or specialized...
Generate unit and UI tests for specified code with edge cases and mocks
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.