Guía de evaluación de ADK: métricas, esquema de evalset, LLM como juez, puntuación de trayectorias de herramientas y causas de fallos comunes. Léelo antes de ejecutar cualquier evaluación de ADK.
Esta skill proporciona una guía completa sobre la metodología de evaluación del Agent Development Kit (ADK) de Google. Es fundamental leerla antes de ejecutar cualquier evaluación de ADK, ya que cubre métricas de evaluación, el esquema del conjunto de evaluación (evalset), el uso de un LLM como juez (LLM-as-judge), la puntuación de trayectorias de herramientas (tool trajectory scoring) y las causas comunes de fallos. Útil para evaluar la calidad de un agente, ejecutar `adk eval` o depurar resultados de evaluación. No debe utilizarse para patrones de código de API (usar adk-cheatsheet), despliegue (usar adk-deploy-guide) ni para andamiaje de proyectos (usar adk-scaffold).
npx skills add https://github.com/google/adk-docs/tree/main/skills/adk-eval-guideInstalled? Explore more Productividad y colaboración skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
DEBE LEERSE antes de ejecutar cualquier evaluación de ADK. Metodología de evaluación de ADK — métricas de evaluación, esquema de evalset, LLM como juez, puntuación de trayectorias de herramientas y causas de fallos comunes. Úselo al evaluar la calidad de un agente, ejecutar adk eval o depurar resultados de evaluación. NO lo use para patrones de código de API (use adk-cheatsheet), despliegue (use adk-deploy-guide) ni andamiaje de proyectos (use adk-scaffold).
This repo contains 5 individual skills — each has its own dedicated page.
MUST READ before writing or modifying ADK agent code. ADK API quick reference for Python — agent types, tool definitions, orchestration patterns, callbacks, and state management. Includes an index of all ADK documentation pages. Do NOT use for creating new projects (use adk-scaffold).
MUST READ before deploying any ADK agent. ADK deployment guide — Agent Engine, Cloud Run, GKE, CI/CD pipelines, secrets, observability, and production workflows. Use when deploying agents to Google Cloud or troubleshooting deployments. Do NOT use for API code patterns (use adk-cheatsheet), evaluation (use adk-eval-guide), or project scaffolding (use adk-scaffold).
ALWAYS ACTIVE — read at the start of any ADK agent development session. ADK development lifecycle and mandatory coding guidelines — spec-driven workflow, code preservation rules, model selection, and troubleshooting.
MUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK observability guide — Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations, and troubleshooting. Use when configuring monitoring, tracing, or logging for agents, or when understanding how a deployed agent handles real traffic.
MUST READ before creating or enhancing any ADK agent project. Use when the user wants to build a new agent (e.g. "build me a search agent") or enhance an existing project (e.g. "add CI/CD to my project", "add RAG").
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.