login
aktsmm

agentic-workflow-guide

by @aktsmm in Tools
4
0
# Install this skill:
npx skills add aktsmm/Agent-Skills --skill "agentic-workflow-guide"

Install specific skill from multi-skill repository

# Description

Create, review, and update Prompt and agents and workflows. Covers 5 workflow patterns, runSubagent delegation, Handoffs, Context Engineering. Use for any .agent.md file work or multi-agent system design.

# SKILL.md

name: agentic-workflow-guide
description: "Create, review, and update Prompt and agents and workflows. Covers 5 workflow patterns, runSubagent delegation, Handoffs, Context Engineering. Use for any .agent.md file work or multi-agent system design."
license: Complete terms in LICENSE.txt
metadata:
author: yamapan (https://github.com/aktsmm)

Agentic Workflow Guide

Design, review, and improve agent workflows based on proven principles.

When to Use

Action Triggers
Create New .agent.md, workflow architecture, scaffolding
Review Orchestrator not delegating, design principle check, context overflow
Update Adding Handoffs, improving delegation, tool configuration

Core Principles

β†’ references/design-principles.md

Tier Principles
Essential SSOT, SRP, Simplicity First, Fail Fast, Feedback Loop
Quality Transparency, Gate/Checkpoint, DRY, Observability
Scale Human-in-the-Loop, Loose Coupling, Graceful Degradation

"Start with simple prompts, optimize them with comprehensive evaluation, and add multi-step agentic systems only when simpler solutions fall short." β€” Anthropic

Workflow Patterns

β†’ references/workflow-patterns.md

Pattern When to Use
Prompt Chaining Sequential tasks with validation
Routing Processing varies by input type
Parallelization Independent tasks run together
Orchestrator-Workers Dynamic task decomposition
Evaluator-Optimizer Repeat until quality criteria met

Stop Conditions (MANDATORY): Define success/failure criteria and exit conditions for every loop.

Design Workflow

  1. Requirements - Goal, subtasks, dependencies, quality criteria
  2. Pattern Selection - [!] Ask user to confirm pattern before proceeding
  3. Design Diagram - Visualize with Mermaid
  4. Principle Check - Validate against review checklist
  5. Implement & Iterate - Build small β†’ verify β†’ improve

When to Escalate

β†’ references/splitting-criteria.md

Level Configuration Escalation Triggers
L0 Single Prompt Retry 3+, unstable output
L1 Prompt + Instructions Steps > 5, "missed/overlooked" errors
L2 Single Agent Multiple responsibilities, context > 70%
L3 Multi-Agent Independent subtasks needed

Quick Check: Prompt > 50 lines? Steps > 5? SRP violation? Context > 70%? β†’ Consider splitting.

Review Checklist

β†’ references/review-checklist.md

  • [ ] Single responsibility per agent? (SRP)
  • [ ] Errors detected immediately? (Fail Fast)
  • [ ] Small iterative steps? (Iterative)
  • [ ] Results verifiable at each step? (Feedback Loop)

Key References

Topic Reference
Prompt Template references/prompt-template.md
runSubagent references/runSubagent-guide.md
Agent Template references/agent-template.md
Context Management references/context-engineering.md
Scaffold Tool references/scaffold-usage.md

runSubagent Quick Fix

Problem: Orchestrator says "I'll delegate" but does work directly.

Solution: Use MUST/MANDATORY language. See runSubagent-guide.md.

## MANDATORY: Sub-agent Delegation
You MUST use runSubagent for each file. Do NOT read files directly.

Tools Reference

β†’ references/agent-template.md

Purpose VS Code Copilot Claude Code
Shell runInTerminal Bash
Read readFile Read
Edit editFiles Write
Subagent runSubagent Task

External References

Official Documentation

Design Principles

Instructions & Context

Community Resources

Prompt Engineering

  • https://platform.openai.com/docs/guides/prompt-engineering
  • https://code.claude.com/docs/en/best-practices
  • https://www.promptingguide.ai/
  • https://www.ibm.com/think/prompt-engineering

# Related Skills

obra
executing-plans @obra

Use when you have a written implementation plan to execute in a separate session with review checkpoints

β˜… 32,766
obra
using-superpowers @obra

Use when starting any conversation - establishes how to find and use skills, requiring Skill...

β˜… 32,766

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

⚑ Amp πŸš€ Antigravity πŸ€– Claude Code πŸ¦€ Clawdbot πŸ“ Codex ▢️ Cursor πŸ€– Droid πŸ’Ž Gemini CLI πŸ™ GitHub Copilot πŸͺΏ Goose πŸ“Š Kilo Code πŸ”§ Kiro CLI πŸ’» OpenCode 🦘 Roo Code 🌲 Trae πŸ„ Windsurf

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.