All skills
aktsmm avatar

/agentic-workflow-guide

@fb34748
by yamapanaktsmm/agent-skills26 stars
4

Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.

Use this Skill: https://skilld.dev/gh/aktsmm/agent-skills/agentic-workflow-guide

This session only. Nothing lands on disk.

referencesworkflow-patternscombining-patterns.md

≈825 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Combining Patterns

In real workflows, multiple patterns are often combined.

Back to overview.md

Example: Code Generation Workflow

graph TD
    A[Requirements] --> B{Routing}
    B -->|New Feature| C[Design Agent]
    B -->|Bug Fix| D[Analysis Agent]
    C --> E[Orchestrator]
    D --> E
    E --> F[Implementation Worker 1]
    E --> G[Implementation Worker 2]
    F --> H[Evaluator]
    G --> H
    H -->|NG| I[Feedback]
    I --> F
    I --> G
    H -->|OK| J[Complete]

Patterns Used

Pattern Role in Workflow
Routing Branch processing by requirement type
Orchestrator-Workers Implement changes per file
Evaluator-Optimizer Review → fix loop until quality is met

Combination Guidelines

1. Sequential Combination

Chain patterns where output of one becomes input for next:

Routing → Prompt Chaining → Evaluator-Optimizer

2. Nested Combination

Embed one pattern inside another:

Orchestrator
├─ Worker 1 (uses Prompt Chaining internally)
├─ Worker 2 (uses Evaluator-Optimizer internally)
└─ Worker 3 (uses Routing internally)

3. Parallel Combination

Run different patterns simultaneously on different inputs:

Input
├─ Path A: Routing → Handler A
└─ Path B: Parallelization → Aggregator
    ↓
    Merge results

Common Combinations

Combination Use Case
Routing + Orchestrator-Workers Multi-type tasks with dynamic subtasks
Prompt Chaining + Evaluator-Optimizer Sequential with quality gates
Parallelization + Evaluator-Optimizer Parallel execution with voting
Connected Agents + IR Architecture Shared context with structured output

Anti-Patterns

❌ Over-engineering: Don't combine patterns unnecessarily

Simple translation task:
  ❌ Routing → Orchestrator → Workers → Evaluator
  ✅ Prompt Chaining (sufficient for linear task)

❌ Pattern mismatch: Don't force incompatible patterns

Independent tasks:
  ❌ Prompt Chaining (forces serial execution)
  ✅ Parallelization (allows concurrent execution)

Decision Framework

Question Yes → Pattern No → Alternative
Tasks must be sequential? Prompt Chaining Parallelization
Input needs classification? Routing Direct processing
Task count unknown until runtime? Orchestrator-Workers Static worker assignment
Quality requires iteration? Evaluator-Optimizer Single-pass processing
Agents need shared context? Connected Agents Independent agents
Deterministic output required? IR Architecture Direct generation

Source: SKILL.md on GitHub

2 warnings4mo4 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    This skill is a professional development toolkit for designing, reviewing, and managing AI agent workflows. It provides structured templates, architectural guidance, and utility scripts to help users build efficient multi-agent systems following best practices like Single Responsibility and Single Source of Truth.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: MEDIUM · 1 issue

  • Runlayer7mo

    15/58 files flagged

Signed by skilld at fb34748. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 17 hours ago.

Activeupdated last week
user-invocable
true
metadata
{
  "author": "yamapan (https://github.com/aktsmm)"
}
Other metadata
argument-hint
作りたい .agent.md / .instructions.md / .prompt.md / AGENTS.md、設計したい workflow、または困っている症状

README badge

README badge for aktsmm/agent-skills/agentic-workflow-guide