agent-orchestration-multi-agent-optimize

Name: agent-orchestration-multi-agent-optimize
Author: SamarthaKV29

64stars12forks

How to install agent-orchestration-multi-agent-optimize?

samarthakv29/antigravity-god-mode/agent-orchestration-multi-agent-optimize

$npx -y skills add SamarthaKV29/antigravity-god-mode --skill agent-orchestration-multi-agent-optimize

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# Multi-Agent Optimization Toolkit
2
3	## Use this skill when
4
5	- Improving multi-agent coordination, throughput, or latency
6	- Profiling agent workflows to identify bottlenecks
7	- Designing orchestration strategies for complex workflows
8	- Optimizing cost, context usage, or tool efficiency
9
10	## Do not use this skill when
11
12	- You only need to tune a single agent prompt
13	- There are no measurable metrics or evaluation data
14	- The task is unrelated to multi-agent orchestration
15
16	## Instructions
17
18	1. Establish baseline metrics and target performance goals.
19	2. Profile agent workloads and identify coordination bottlenecks.
20	3. Apply orchestration changes and cost controls incrementally.
21	4. Validate improvements with repeatable tests and rollbacks.
22
23	## Safety
24
25	- Avoid deploying orchestration changes without regression testing.
26	- Roll out changes gradually to prevent system-wide regressions.
27
28	## Role: AI-Powered Multi-Agent Performance Engineering Specialist
29
30	### Context
31
32	The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated agent-based optimization. Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach to performance engineering across multiple domains.
33
34	### Core Capabilities
35
36	- Intelligent multi-agent coordination
37	- Performance profiling and bottleneck identification
38	- Adaptive optimization strategies
39	- Cross-domain performance optimization
40	- Cost and efficiency tracking
41
42	## Arguments Handling
43
44	The tool processes optimization arguments with flexible input parameters:
45
46	- `$TARGET`: Primary system/application to optimize
47	- `$PERFORMANCE_GOALS`: Specific performance metrics and objectives
48	- `$OPTIMIZATION_SCOPE`: Depth of optimization (quick-win, comprehensive)
49	- `$BUDGET_CONSTRAINTS`: Cost and resource limitations
50	- `$QUALITY_METRICS`: Performance quality thresholds
51
52	## 1. Multi-Agent Performance Profiling
53
54	### Profiling Strategy
55
56	- Distributed performance monitoring across system layers
57	- Real-time metrics collection and analysis
58	- Continuous performance signature tracking
59
60	#### Profiling Agents
61
62	1. Database Performance Agent
63	- Query execution time analysis
64	- Index utilization tracking
65	- Resource consumption monitoring
66
67	2. Application Performance Agent
68	- CPU and memory profiling
69	- Algorithmic complexity assessment
70	- Concurrency and async operation analysis
71
72	3. Frontend Performance Agent
73	- Rendering performance metrics
74	- Network request optimization
75	- Core Web Vitals monitoring
76
77	### Profiling Code Example
78
79	```python
80	def multi_agent_profiler(target_system):
81	agents = [
82	DatabasePerformanceAgent(target_system),
83	ApplicationPerformanceAgent(target_system),
84	FrontendPerformanceAgent(target_system)
85	]
86
87	performance_profile = {}
88	for agent in agents:
89	performance_profile[agent.__class__.__name__] = agent.profile()
90
91	return aggregate_performance_metrics(performance_profile)
92	```
93
94	## 2. Context Window Optimization
95
96	### Optimization Techniques
97
98	- Intelligent context compression
99	- Semantic relevance filtering
100	- Dynamic context window resizing
101	- Token budget management
102
103	### Context Compression Algorithm
104
105	```python
106	def compress_context(context, max_tokens=4000):
107	# Semantic compression using embedding-based truncation
108	compressed_context = semantic_truncate(
109	context,
110	max_tokens=max_tokens,
111	importance_threshold=0.7
112	)
113	return compressed_context
114	```
115
116	## 3. Agent Coordination Efficiency
117
118	### Coordination Principles
119
120	- Parallel execution design
121	- Minimal inter-agent communication overhead
122	- Dynamic workload distribution
123	- Fault-tolerant agent interactions
124
125	### Orchestration Framework
126
127	```python
128	class MultiAgentOrchestrator:
129	def __init__(self, agents):
130	self.agents = agents
131	self.execution_queue = PriorityQueue()
132	self.performance_tracker = PerformanceTracker()
133
134	def optimize(self, target_system):
135	# Parallel agent execution with coordinated optimization
136	with concurrent.futures.ThreadPoolExecutor() as executor:
137	futures = {
138	executor.submit(agent.optimize, target_system): agent
139	for agent in self.agents
140	}
141
142	for future in concurrent.futures.as_completed(futures):
143	agent = futures[future]
144	result = future.result()
145	self.performance_tracker.log(agent, result)
146	```
147
148	## 4. Parallel Execution Optimization
149
150	### Key Strategies
151
152	- Asynchronous agent processing
153	- Workload partitioning
154	- Dynamic resource allocation
155	- Minimal blocking operations
156
157	## 5. Cost Optimization Strategies
158
159	### LLM Cost Management
160
161	- To

People who liked this also viewed

6 picks

Type

agent-orchestration-multi-agent-optimize

64stars12forks

View on GitHub

How to install agent-orchestration-multi-agent-optimize?

samarthakv29/antigravity-god-mode/agent-orchestration-multi-agent-optimize

$npx -y skills add SamarthaKV29/antigravity-god-mode --skill agent-orchestration-multi-agent-optimize

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# Multi-Agent Optimization Toolkit
2
3	## Use this skill when
4
5	- Improving multi-agent coordination, throughput, or latency
6	- Profiling agent workflows to identify bottlenecks
7	- Designing orchestration strategies for complex workflows
8	- Optimizing cost, context usage, or tool efficiency
9
10	## Do not use this skill when
11
12	- You only need to tune a single agent prompt
13	- There are no measurable metrics or evaluation data
14	- The task is unrelated to multi-agent orchestration
15
16	## Instructions
17
18	1. Establish baseline metrics and target performance goals.
19	2. Profile agent workloads and identify coordination bottlenecks.
20	3. Apply orchestration changes and cost controls incrementally.
21	4. Validate improvements with repeatable tests and rollbacks.
22
23	## Safety
24
25	- Avoid deploying orchestration changes without regression testing.
26	- Roll out changes gradually to prevent system-wide regressions.
27
28	## Role: AI-Powered Multi-Agent Performance Engineering Specialist
29
30	### Context
31
32	The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated agent-based optimization. Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach to performance engineering across multiple domains.
33
34	### Core Capabilities
35
36	- Intelligent multi-agent coordination
37	- Performance profiling and bottleneck identification
38	- Adaptive optimization strategies
39	- Cross-domain performance optimization
40	- Cost and efficiency tracking
41
42	## Arguments Handling
43
44	The tool processes optimization arguments with flexible input parameters:
45
46	- `$TARGET`: Primary system/application to optimize
47	- `$PERFORMANCE_GOALS`: Specific performance metrics and objectives
48	- `$OPTIMIZATION_SCOPE`: Depth of optimization (quick-win, comprehensive)
49	- `$BUDGET_CONSTRAINTS`: Cost and resource limitations
50	- `$QUALITY_METRICS`: Performance quality thresholds
51
52	## 1. Multi-Agent Performance Profiling
53
54	### Profiling Strategy
55
56	- Distributed performance monitoring across system layers
57	- Real-time metrics collection and analysis
58	- Continuous performance signature tracking
59
60	#### Profiling Agents
61
62	1. Database Performance Agent
63	- Query execution time analysis
64	- Index utilization tracking
65	- Resource consumption monitoring
66
67	2. Application Performance Agent
68	- CPU and memory profiling
69	- Algorithmic complexity assessment
70	- Concurrency and async operation analysis
71
72	3. Frontend Performance Agent
73	- Rendering performance metrics
74	- Network request optimization
75	- Core Web Vitals monitoring
76
77	### Profiling Code Example
78
79	```python
80	def multi_agent_profiler(target_system):
81	agents = [
82	DatabasePerformanceAgent(target_system),
83	ApplicationPerformanceAgent(target_system),
84	FrontendPerformanceAgent(target_system)
85	]
86
87	performance_profile = {}
88	for agent in agents:
89	performance_profile[agent.__class__.__name__] = agent.profile()
90
91	return aggregate_performance_metrics(performance_profile)
92	```
93
94	## 2. Context Window Optimization
95
96	### Optimization Techniques
97
98	- Intelligent context compression
99	- Semantic relevance filtering
100	- Dynamic context window resizing
101	- Token budget management
102
103	### Context Compression Algorithm
104
105	```python
106	def compress_context(context, max_tokens=4000):
107	# Semantic compression using embedding-based truncation
108	compressed_context = semantic_truncate(
109	context,
110	max_tokens=max_tokens,
111	importance_threshold=0.7
112	)
113	return compressed_context
114	```
115
116	## 3. Agent Coordination Efficiency
117
118	### Coordination Principles
119
120	- Parallel execution design
121	- Minimal inter-agent communication overhead
122	- Dynamic workload distribution
123	- Fault-tolerant agent interactions
124
125	### Orchestration Framework
126
127	```python
128	class MultiAgentOrchestrator:
129	def __init__(self, agents):
130	self.agents = agents
131	self.execution_queue = PriorityQueue()
132	self.performance_tracker = PerformanceTracker()
133
134	def optimize(self, target_system):
135	# Parallel agent execution with coordinated optimization
136	with concurrent.futures.ThreadPoolExecutor() as executor:
137	futures = {
138	executor.submit(agent.optimize, target_system): agent
139	for agent in self.agents
140	}
141
142	for future in concurrent.futures.as_completed(futures):
143	agent = futures[future]
144	result = future.result()
145	self.performance_tracker.log(agent, result)
146	```
147
148	## 4. Parallel Execution Optimization
149
150	### Key Strategies
151
152	- Asynchronous agent processing
153	- Workload partitioning
154	- Dynamic resource allocation
155	- Minimal blocking operations
156
157	## 5. Cost Optimization Strategies
158
159	### LLM Cost Management
160
161	- To

People who liked this also viewed

6 picks

Type