LLM Skills
~/catalogue/cloud & sdk//google-adkc
Cloud & SDKsource GitHub

Google adk

/google-adkc

Applique des règles Cursor pour développer avec Google adk de façon cohérente et maintenable.

PatrickJSPatrickJS
40.7k
27 mai 2026
CC0-1.0
// contenu du skill

description: Google Agent Development Kit rules for agents, tools, sessions, memory, artifacts, evaluation, and deployment

globs: ["*/.py", "*/.ts", "*/.tsx", "*/.go", "*/.java", "pyproject.toml", "package.json"]

alwaysApply: false


Google ADK Rules

Agent Design

  • Keep each agent focused on a clear goal, persona, and tool set.
  • Use LLM agents for flexible reasoning and workflow agents for deterministic orchestration.
  • Write instructions that define task boundaries, tool-use rules, and escalation behavior.
  • Split multi-agent systems by responsibility rather than by implementation convenience.
  • Keep model choices configurable.

Tools

  • Give tools narrow, typed inputs and outputs.
  • Validate tool arguments before performing side effects.
  • Keep secrets, credentials, and privileged APIs out of agent prompts.
  • Handle tool errors explicitly and return actionable failure messages.
  • Be aware of ADK tool limitations; some built-in tools cannot be combined with other tools on the same agent.

Sessions, State, and Memory

  • Use session state for current-conversation data.
  • Use memory for cross-session recall and retrieval.
  • Keep state small and serializable.
  • Do not store large files or binary payloads in session state.
  • Make state keys stable and documented.

Artifacts

  • Use artifacts for generated files, uploaded files, reports, images, audio, and other binary data.
  • Configure an artifact service in the runner before relying on artifact operations.
  • Version artifact filenames intentionally and avoid overwriting semantically different outputs.
  • Store only references or summaries in state when full content belongs in artifacts.

Evaluation and Deployment

  • Add tests for tool behavior, agent routing, prompt regressions, and unsafe tool calls.
  • Use trace or event logs to debug agent decisions.
  • Keep local development, staging, and production configuration separate.
  • Add observability for latency, tool failures, token use, and handoff failures.

Common Mistakes

  • Do not make one agent responsible for every workflow.
  • Do not let tools accept arbitrary shell, SQL, or HTTP input without validation.
  • Do not rely on prompt text for access control.
  • Do not hide important side effects behind generic tool names.
// source originale publique
PatrickJS/awesome-cursorrules
/rules/google-adk.mdc
Licence : CC0-1.0. Consultez le dépôt avant toute réutilisation.
Projet indépendant, non affilié à Anthropic. Ce skill reste la propriété de son auteur original.
// installer ce skill
Collez cette commande dans votre terminal à la racine de votre projet :
mkdir -p .claude/commands && curl -o ".claude/commands/google-adk.mdc" "https://raw.githubusercontent.com/PatrickJS/awesome-cursorrules/main/rules/google-adk.mdc"
Ensuite dans Claude Code, tapez /google-adkc pour l'activer.
open_in_newVoir la source originale
// sauvegarder
Sauvegarde disponible après connexion.
loginSe connecter pour sauvegarder
// informations
CréateurPatrickJS
Étoiles 40.7k
CatégorieCloud & SDK
LicenceCC0-1.0
Mis à jour27 mai 2026
Format.md
AccèsGratuit
// similaires

Skills Cloud & SDK

Voir toutarrow_forward