By testacode
Toolkit de productividad para Claude Code: skills, agents, commands y configuraciones para desarrollo con LLMs
Plan implementation before coding - creates spec in /docs/wip/ and interviews for requirements
Fix the most recent error - analyzes console output and proposes solution
Run project validations - lint, typecheck, tests, and build
Interview to flesh out a plan/spec
Create a working proof-of-concept to validate ideas or demonstrate functionality
Deep codebase analysis specialist. <example> user: "cómo funciona el sistema de auth?" assistant: Uses codebase-analyst to trace auth flow <commentary>Understanding existing code requires systematic analysis</commentary> </example> <example> user: "qué impacto tiene cambiar esta función?" assistant: Uses codebase-analyst for impact analysis <commentary>Dependency tracing requires codebase exploration</commentary> </example> Use for: code structure, dependency tracing, patterns, impact analysis, legacy code, debugging.
Analiza frames extraidos de screen recordings para detectar glitches visuales, layout shifts, y problemas de animacion en UIs web. Se usa como fallback cuando no hay modelo de vision local (mlx-vlm o LM Studio). <example> Context: La skill video-debugger extrajo frames pero no hay modelo de vision local disponible user: "te paso este video para que veas el bug" assistant: "Extraje los frames y el diff report. No hay modelo de vision local, lanzo el agente frame-analyzer para analizar visualmente." <commentary> Sin modelo local, el agente Sonnet analiza frames con su vision multimodal nativa. </commentary> </example> <example> Context: El usuario quiere analisis visual de frames ya extraidos user: "analiza los frames que estan en debug-frames/" assistant: "Lanzo el agente frame-analyzer para analizar esos frames." <commentary> Analisis visual directo de frames existentes sin necesidad de modelo local. </commentary> </example>
Expert in GitHub Actions for CI/CD automation. <example> user: "agregar CI al proyecto" assistant: Uses github-actions-expert to create workflow <commentary>User wants CI pipeline - this agent specializes in GH Actions</commentary> </example> <example> user: "el workflow está fallando" assistant: Uses github-actions-expert to debug <commentary>Workflow debugging requires GH Actions expertise</commentary> </example>
Grafana dashboard and alerting specialist. <example> user: "crear dashboard de métricas" assistant: Uses grafana-expert to design dashboard <commentary>Dashboard creation requires Grafana visualization expertise</commentary> </example> <example> user: "configurar alertas en Grafana" assistant: Uses grafana-expert to set up alerting <commentary>Alerting systems are core Grafana functionality</commentary> </example>
Java development specialist for enterprise applications. <example> user: "implementar patrón Factory en Java" assistant: Uses java-expert to implement design pattern <commentary>Design patterns in Java require language-specific expertise</commentary> </example> <example> user: "optimizar concurrencia Java" assistant: Uses java-expert to review threading code <commentary>Java concurrency requires deep JVM knowledge</commentary> </example>
This skill should be used when the user asks to model a house or building in Blender, create 3D architecture from floor plans, build walls/roofs/openings in Blender via MCP, or work on architectural visualization. Trigger phrases include: "model a house in Blender", "create 3D architecture", "build floor plan in Blender", "modelar casa", "crear modelo arquitectonico", "render a building in Blender", "Blender MCP architecture".
This skill should be used when the user wants to create, build, modify, test, or publish a browser extension. Trigger phrases include: "crear extension", "browser extension", "extension Chrome", "extension Firefox", "content script", "popup extension", "addon", "extension de navegador", "chrome extension", "firefox addon", "extension para el browser", "quiero hacer un plugin para Chrome", "modificar headers del navegador", "inyectar script en pagina", "publicar extension", "publish to Chrome Web Store", "publish to Firefox AMO", "automate extension release", "extension sin WXT", "Rspack extension", "Webpack extension", "AMO source package", "test my extension", or any project involving a web extension. Defaults to WXT for new projects; also covers existing non-WXT (Rspack/Webpack/Vite, hand-rolled MV3) extensions and CI store publishing.
Escribe y mejora archivos CLAUDE.md siguiendo best practices de Anthropic. Este skill se activa cuando el usuario dice "crear CLAUDE.md", "mejorar CLAUDE.md", "actualizar CLAUDE.md", "revisar CLAUDE.md", "escribir instrucciones del proyecto", "create CLAUDE.md", "improve CLAUDE.md", "review CLAUDE.md", "write project instructions", "optimize docs for Claude", "auditar CLAUDE.md", "audit CLAUDE.md", "limpiar CLAUDE.md", "dead weight", o configura un nuevo repositorio.
Ejemplos detallados y anti-patrones para escribir codigo de calidad con LLMs (simplicidad, cambios quirurgicos, objetivos verificables). Use this skill at the start of any coding task where the user asks to implement a feature, add functionality, fix a bug, refactor code, or modify an existing file, especially when the request is vague ("agrega X" / "add X", "arregla Y" / "fix Y", "mejora Z" / "improve Z", "refactoriza esto" / "refactor this") and assumptions about libraries, patterns, or scope need to be surfaced before writing code. Also use when the user asks for code review focused on over-engineering, scope creep, or unnecessary changes.
Consulta de legislación argentina: Constitución Nacional (CN), Código Penal (CP) y Código Civil y Comercial (CCyC). Se activa cuando el usuario pregunta por artículos específicos, derechos constitucionales, delitos, penas, contratos, obligaciones, familia, sucesiones, derechos reales, prescripción, responsabilidad civil, o cualquier tema de derecho argentino de fondo. También cuando dice "qué dice el artículo", "código penal", "código civil", "constitución", "es constitucional", "prescripción", "daños y perjuicios", "contrato de locación", "derechos del consumidor", "amparo", "habeas corpus", "habeas data", "divorcio", "sucesión", "herencia", "propiedad horizontal", "alimentos", "responsabilidad civil", "delitos contra la propiedad", "estafa", "homicidio", "derecho argentino", "legislación argentina", "ley argentina".
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Requires secrets
Needs API keys or credentials to function
Requires secrets
Needs API keys or credentials to function
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Coleccion de herramientas, configuraciones y extensiones para trabajar con modelos de lenguaje (Claude, GPT, Qwen, Mistral, etc.).
Quick Start: Ver docs/QUICK-START.md para empezar en 5 minutos.
llm-toolkit/
├── skills/ # Skills para Claude Code
│ ├── llms-txt-generator/
│ ├── claude-md-writer/
│ ├── nextjs-project-starter/
│ └── doc-writer/
├── agents/ # Agentes especializados
├── commands/ # Slash commands organizados
│ ├── git/ # commit
│ ├── code/ # explain, simplify, translate
│ ├── docs/ # diagram, document
│ ├── dev/ # prototype, summary
│ └── security/ # scrub
├── cli/nub/ # CLI Go para ahorrar tokens
├── docs/ # Documentacion
├── .claude-plugin/ # Configuracion del plugin
│ ├── hooks.json # Hooks PreToolUse/PostToolUse
│ ├── scripts/ # Scripts de hooks
│ ├── marketplace.json
│ └── plugin.json # Declaracion de todo el contenido
├── .claude/ # Configuracion local
│ └── settings.template.json
├── rules/ # Reglas y guidelines (futuro)
├── prompts/ # Prompts reutilizables (futuro)
└── configs/ # Configuraciones por IDE (futuro)
| Skill | Descripcion | Trigger |
|---|---|---|
| llms-txt-generator | Genera documentacion optimizada para LLMs siguiendo el estandar llms.txt | "crear llms.txt", "generate LLM docs" |
| claude-md-writer | Guia para escribir, mejorar y auditar archivos CLAUDE.md siguiendo best practices | "crear CLAUDE.md", "revisar CLAUDE.md", "auditar CLAUDE.md" |
| nextjs-project-starter | Crea proyectos Next.js con stack configurable (Mantine, Supabase, Zustand) | "crear proyecto", "new nextjs project" |
| git-reconciler | Sincroniza branch con main/master detectando conflictos antes de merge | "sync con main", "reconciliar", "actualizar branch" |
| worktree-manager | Gestiona git worktrees en carpeta .worktrees/ | "crear worktree", "listar worktrees" |
| setup-project | Configura proyectos con scripts de check y detecta CLIs disponibles | "configurar proyecto", "setup", "qué CLIs tengo" |
| feature-planner | Planifica features con entrevista estructurada y genera plan de implementacion | "planificar feature", "nueva funcionalidad" |
| doc-writer | Organiza specs, planes y docs tecnicos en docs/ con categorias y naming automatico | "escribir spec", "crear plan", "documentar ADR" |
| doc-organizer | Organiza y categoriza documentos existentes en estructura correcta | "organizar docs", "categorizar archivos" |
| plan-viewer | Renderiza un plan como HTML self-contained (Mermaid, file map, codigo anotado, open questions) en docs/visual-plans/ | "ver el plan visual", "plan en HTML", "visualizar el plan" |
| investor-profiler | Entrevista estructurada para determinar perfil de inversor y recomendar asset allocation | "perfil inversor", "en qué invertir", "asset allocation" |
| github-actions | Configura GitHub Actions con deteccion proactiva de repos sin CI. Soporta Node.js, Python, Go | "agregar CI", "configurar GitHub Actions", "workflow de deploy" |
| gh-cli | Referencia completa de GitHub CLI (gh): repos, issues, PRs, Actions, releases, search, API | "gh pr", "gh issue", "github cli", "gh api" |
| logging-backend | Wide Events para observabilidad real en backend | "agregar logging", "wide events", "mejorar logs" |
| coding-guidelines | Ejemplos y anti-patrones para codigo de calidad (principios core en CLAUDE.md global) | "agrega X", "arregla Y", "refactoriza", "implementa" |
| blender-architect | Modelado arquitectonico 3D en Blender via MCP | "modelar casa", "create 3D architecture" |
| furniture-planner | Diseña muebles a medida con planos HTML, BOM, máximas de diseño ergonómico y export Excel CorteCloud | "diseñar mueble", "bajo mesada", "placard", "cortecloud" |
| nano-banana | Construye prompts optimizados para generación de imagen (familia Gemini). Entrega el prompt para pegar en Gemini Studio, Claude.ai u otro generador | "generar imagen", "render", "prompt para imagen", "armar prompt" |
npx claudepluginhub testacode/llm-toolkit --plugin llm-toolkitHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques