Agent Orchestration Improve Agent

dokhacgiakhoa/agent-orchestration-improve-agent

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

3k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

505

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI --skill agent-orchestration-improve-agent

What comes with it

8 398 bytes besides the instruction

sub-skills/11-gather-performance-data.md

sub-skills/12-user-feedback-pattern-analysis.md

sub-skills/13-failure-mode-classification.md

sub-skills/14-baseline-performance-report.md

sub-skills/21-chain-of-thought-enhancement.md

sub-skills/22-few-shot-example-optimization.md

sub-skills/23-role-definition-refinement.md

sub-skills/24-constitutional-ai-integration.md

sub-skills/25-output-format-tuning.md

sub-skills/31-test-suite-development.md

sub-skills/32-ab-testing-framework.md

sub-skills/33-evaluation-metrics.md

sub-skills/34-human-evaluation-protocol.md

sub-skills/41-version-management.md

sub-skills/42-staged-rollout.md

sub-skills/43-rollback-procedures.md

sub-skills/44-continuous-monitoring.md

The instruction itself

24 sections, as written by the author

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

Establish baseline metrics and collect representative examples.
Identify failure modes and prioritize high-impact fixes.
Apply prompt and workflow improvements with measurable goals.
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

2. 1.2 User Feedback Pattern Analysis

3. 1.3 Failure Mode Classification

4. 1.4 Baseline Performance Report

5. 2.1 Chain-of-Thought Enhancement

6. 2.2 Few-Shot Example Optimization

8. 2.4 Constitutional AI Integration

9. 2.5 Output Format Tuning

10. 3.1 Test Suite Development

11. 3.2 A/B Testing Framework

12. 3.3 Evaluation Metrics

13. 3.4 Human Evaluation Protocol

14. 4.1 Version Management

15. 4.2 Staged Rollout

16. 4.3 Rollback Procedures

17. 4.4 Continuous Monitoring

How to use it

Copy the folder

Take dokhacgiakhoa/agent-orchestration-improve-agent from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.