Menu
Best practices for agentic workflow coordination, checkpoints, and session continuity.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | gsd-best-practices |
| description | Best practices for agentic workflow coordination, checkpoints, and session continuity. |
This skill provides refined patterns for coordinating complex agentic workflows, handling user interaction points (checkpoints), and maintaining session continuity.
GSD uses structured checkpoints to formalize interaction with the user.
Golden Rule: If it has a CLI or API, the agent must automate it. Never ask a user to run a command that the agent can execute.
Always provide a clear "Next Up" block after completing a major task.
ROADMAP.md or PLAN.md./clear before starting a new phase/plan to keep the context window fresh.Configuration for the .planning/ directory should be respected:
commit_docs: If true (default), commit planning artifacts to git. If false, keep them local.search_gitignored: If true, include .planning/ in broad searches even if gitignored.git.branching_strategy: Support none, phase, or milestone branching.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 running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold).
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").