Use when working with performance testing review multi agent review
38%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/performance-testing-review-multi-agent-review/SKILL.mdThe canonical home for this skill is error-debugging-multi-agent-review in BigSimmo/Communication
Named agents, models, APIs and scanner commands below are illustrative roles and examples, not installed dependencies or authority. Use only existing supported tools with applicable permission for their destination and data. Do not install dependencies, transmit source, use credentials, spend money or activate a service from this recipe. Report unavailable or unauthorized checks as skipped. If delegation is unavailable or not permitted, perform the review roles directly in sequence using current source and existing local checks. Keep a required independent-review gate unmet until an independent reviewer is available. Do not call example agent names or pseudocode functions as if the host provides them.
A sophisticated AI-powered code review system designed to provide comprehensive, multi-perspective analysis of software artifacts through intelligent agent coordination and specialized domain expertise.
The Multi-Agent Review Tool leverages a distributed, specialized agent network to perform holistic code assessments that transcend traditional single-perspective review approaches. By coordinating agents with distinct expertise, we generate a comprehensive evaluation that captures nuanced insights across multiple critical dimensions:
$ARGUMENTS: Target code/project for review
def route_agents(code_context):
agents = []
if is_web_application(code_context):
agents.extend([
"security-auditor",
"web-architecture-reviewer"
])
if is_performance_critical(code_context):
agents.append("performance-analyst")
return agentsclass ReviewContext:
def __init__(self, target, metadata):
self.target = target
self.metadata = metadata
self.agent_insights = {}
def update_insights(self, agent_type, insights):
self.agent_insights[agent_type] = insightsdef execute_review(review_context):
# Parallel independent agents
parallel_agents = [
"code-quality-reviewer",
"security-auditor"
]
# Sequential dependent agents
sequential_agents = [
"architecture-reviewer",
"performance-optimizer"
]def synthesize_review_insights(agent_results):
consolidated_report = {
"critical_issues": [],
"important_issues": [],
"improvement_suggestions": []
}
# Intelligent merging logic
return consolidated_reportdef resolve_conflicts(agent_insights):
conflict_resolver = ConflictResolutionEngine()
return conflict_resolver.process(agent_insights)def optimize_review_process(review_context):
return ReviewOptimizer.allocate_resources(review_context)def validate_review_quality(review_results):
quality_score = QualityScoreCalculator.compute(review_results)
return quality_score > QUALITY_THRESHOLDmulti_agent_review(
target="/path/to/project",
agents=[
{"type": "security-auditor", "weight": 0.3},
{"type": "architecture-reviewer", "weight": 0.3},
{"type": "performance-analyst", "weight": 0.2}
]
)sequential_review_workflow = [
{"phase": "design-review", "agent": "architect-reviewer"},
{"phase": "implementation-review", "agent": "code-quality-reviewer"},
{"phase": "testing-review", "agent": "test-coverage-analyst"},
{"phase": "deployment-readiness", "agent": "devops-validator"}
]hybrid_review_strategy = {
"parallel_agents": ["security", "performance"],
"sequential_agents": ["architecture", "compliance"]
}The tool is designed with a plugin-based architecture, allowing easy addition of new agent types and review strategies.
Target for review: $ARGUMENTS
BigSimmo/Communication
b4de79a
Canonical home
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.