agent-orchestration-multi-agent-optimize

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.

Install with Tessl CLI

npx tessl i github:duclm1x1/Dive-Ai --skill agent-orchestration-multi-agent-optimize

What are skills?

Review — 47%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

27%

Coordinated Agent Optimization System

Multi-agent orchestrator implementation

Criteria

Without context

With context

ThreadPoolExecutor usage

100%

Futures-based dispatch

100%

PriorityQueue scheduling

100%

PerformanceTracker component

100%

Minimal inter-agent overhead

100%

Incremental deployment plan

100%

Regression testing requirement

100%

Rollback support

100%

Gradual rollout strategy

100%

Before/after measurement

50%

100%

Without context: $0.4064 · 1m 59s · 19 turns · 26 in / 6,421 out tokens

With context: $0.4565 · 2m 6s · 22 turns · 322 in / 6,389 out tokens

98%

LLM Cost Reduction for a Multi-Agent Customer Support Platform

Cost-aware adaptive model selection

Criteria

Without context

With context

Monthly token budget

40%

100%

Token usage tracking

100%

Per-model cost map

100%

Includes haiku-class model

100%

Complexity-based model selection

100%

Budget enforcement

80%

100%

Result caching

100%

Incremental cost controls

100%

Before/after cost measurement

100%

Regression test for output quality

70%

80%

Without context: $0.4402 · 2m 22s · 17 turns · 22 in / 8,887 out tokens

With context: $0.7038 · 3m 7s · 25 turns · 30 in / 11,343 out tokens

93%

Diagnosing and Improving a Slow E-Commerce Agent Pipeline

Baseline profiling and incremental optimization workflow

Criteria

Without context

With context

Baseline metrics first

100%

Database profiling agent

100%

Application profiling agent

100%

Frontend profiling agent

100%

Context compression

100%

Semantic truncation pattern

37%

100%

Incremental change plan

100%

After-optimization measurement

100%

Rollback mechanism

100%

Fault tolerance

50%

12%

Performance target defined

100%

Without context: $0.4932 · 2m 53s · 19 turns · 26 in / 9,442 out tokens

With context: $0.5208 · 2m 19s · 23 turns · 184 in / 7,683 out tokens

Evaluated: about 2 hours ago
Agent: Claude Code

Table of Contents

Coordinated Agent Optimization System LLM Cost Reduction for a Multi-Agent Customer Support Platform Diagnosing and Improving a Slow E-Commerce Agent Pipeline

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.