agentic-patterns
Use simple, composable patterns to decide when to keep a deterministic workflow versus letting an LLM drive its own control flow with tools, retrieval, and memory. Prefer minimal patterns and add agentic loops only when they unlock necessary flexibility.
npx skills add majiayu000/claude-skill-registry --skill agentic-patterns --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
--- name: agentic-patterns description: Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or multi-step task delegation; triggers: agentic, multi-agent, orchestration, ReAct, evaluator-optimizer, tool-use, handoff. --- # Agentic Patterns ## Overview Use simple, composable patterns to decide when to keep a deterministic workflow versus letting an LLM drive its own control flow with tools, retrieval, and memory. Prefer minimal patterns and add agentic loops only when they unlock necessary flexibility. ## When to Use - Use this skill when the request matches the frontmatter description and triggers; otherwise start with a deterministic workflow or a single prompt. ## Decision Tree 1. Determine whether the task can be mapped to a fixed sequence. - Yes: implement a workflow chain. - No: continue. 2. Determine whether the output can be evaluated with explicit criteria. - Yes: use an evaluator-optimizer loop. - No: continue. 3. Determine whether the task decomposes into independent subtasks. - Yes: use orchestrator-workers. - No: add a
- Overview
- When to Use
- Decision Tree
- Workflows
- 1. Evaluator-Optimizer Loop
- 2. Orchestrator-Worker Task Delegation
- 3. Tool Poka-Yoke Audit
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the agentic-patterns skill do?
Use simple, composable patterns to decide when to keep a deterministic workflow versus letting an LLM drive its own control flow with tools, retrieval, and memory. Prefer minimal patterns and add agentic loops only when they unlock necessary flexibility.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill agentic-patterns --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.