Agent Swap Mechanism Skill

## Purpose

14 stars

Best use case

Agent Swap Mechanism Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

## Purpose

Teams using Agent Swap Mechanism Skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/cfn-agent-swap/SKILL.md --create-dirs "https://raw.githubusercontent.com/masharratt/claude-flow-novice/main/.claude/cfn-extras/skills/advanced-features/cfn-agent-swap/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/cfn-agent-swap/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How Agent Swap Mechanism Skill Compares

Feature / Agent	Agent Swap Mechanism Skill	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

## Purpose

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Agent Swap Mechanism Skill

## Purpose
Recommend agent replacement strategies when performance issues are detected in CFN Loops.

## Replacement Rules
1. Identify lowest-performing agent
2. Match replacement based on feedback themes
   - Security feedback → security-specialist
   - Performance feedback → performance-engineer
   - Testing feedback → tester
   - Architecture feedback → architect

## Replacement Strategies
- Complete agent replacement
- Adding specialist alongside existing agents
- Prioritize maintaining existing team composition

## Usage
```bash
./recommend-swap.sh \
  --loop3-agents "backend-dev,coder" \
  --loop3-confidences "0.82,0.70" \
  --feedback-themes "security,error-handling"
```

## Output Details
- Agent to remove
- Reasoning for removal
- Recommended replacement agent
- Updated agent configuration

## Implementation Considerations
- Stateless design
- Minimal side effects
- Clear, reproducible recommendations

Related Skills

We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.