Agent Orchestration Improve Agent

---
version: 4.1.0-fractal
name: agent-orchestration-improve-agent
description: "Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration."
---

# Agent Performance Optimization Workflow

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

[Extended thinking: Agent optimization requires a data-driven approach combining performance metrics, user feedback analysis, and advanced prompt engineering techniques. Success depends on systematic evaluation, targeted improvements, and rigorous testing with rollback capabilities for production safety.]

## Use this skill when

- Improving an existing agent's performance or reliability
- Analyzing failure modes, prompt quality, or tool usage
- Running structured A/B tests or evaluation suites
- Designing iterative optimization workflows for agents

## Do not use this skill when

- You are building a brand-new agent from scratch
- There are no metrics, feedback, or test cases available
- The task is unrelated to agent performance or prompt quality

## Instructions

1. Establish baseline metrics and collect representative examples.
2. Identify failure modes and prioritize high-impact fixes.
3. Apply prompt and workflow improvements with measurable goals.
4. Validate with tests and roll out changes in controlled stages.

## Safety

- Avoid deploying prompt changes without regression testing.
- Roll back quickly if quality or safety metrics regress.

## Phase 1: Performance Analysis and Baseline Metrics

Comprehensive analysis of agent performance using context-manager for historical data collection.

## 🧠 Knowledge Modules (Fractal Skills)

### 1. [1.1 Gather Performance Data](./sub-skills/11-gather-performance-data.md)
### 2. [1.2 User Feedback Pattern Analysis](./sub-skills/12-user-feedback-pattern-analysis.md)
### 3. [1.3 Failure Mode Classification](./sub-skills/13-failure-mode-classification.md)
### 4. [1.4 Baseline Performance Report](./sub-skills/14-baseline-performance-report.md)
### 5. [2.1 Chain-of-Thought Enhancement](./sub-skills/21-chain-of-thought-enhancement.md)
### 6. [2.2 Few-Shot Example Optimization](./sub-skills/22-few-shot-example-optimization.md)
### 7. [2.3 Role Definition Refinement](./sub-skills/23-role-definition-refinement.md)
### 8. [2.4 Constitutional AI Integration](./sub-skills/24-constitutional-ai-integration.md)
### 9. [2.5 Output Format Tuning](./sub-skills/25-output-format-tuning.md)
### 10. [3.1 Test Suite Development](./sub-skills/31-test-suite-development.md)
### 11. [3.2 A/B Testing Framework](./sub-skills/32-ab-testing-framework.md)
### 12. [3.3 Evaluation Metrics](./sub-skills/33-evaluation-metrics.md)
### 13. [3.4 Human Evaluation Protocol](./sub-skills/34-human-evaluation-protocol.md)
### 14. [4.1 Version Management](./sub-skills/41-version-management.md)
### 15. [4.2 Staged Rollout](./sub-skills/42-staged-rollout.md)
### 16. [4.3 Rollback Procedures](./sub-skills/43-rollback-procedures.md)
### 17. [4.4 Continuous Monitoring](./sub-skills/44-continuous-monitoring.md)