CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-performance-analyzer

Agent skill for performance-analyzer - invoke with $agent-performance-analyzer

35

1.00x
Quality

0%

Does it follow best practices?

Impact

99%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-performance-analyzer/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

2%

Data Pipeline Performance Investigation

Performance report structure and KPI tracking

Criteria
Without context
With context

Executive Summary section

100%

100%

Detailed Findings section

100%

100%

Trend Analysis section

100%

100%

P95 and P99 reported

100%

100%

All five KPI categories present

100%

100%

Bottleneck Impact field

75%

100%

Bottleneck Root Cause field

100%

100%

Expected Improvement percentage

100%

100%

Bottleneck Recommendation field

100%

100%

Enrichment service identified

100%

100%

Increasing trend noted

100%

100%

kpi_summary.json produced

100%

100%

98%

-1%

Agent Coordination System Diagnosis

Bottleneck pattern classification and optimization strategies

Criteria
Without context
With context

Single Agent Overload identified

100%

100%

Sequential Task Chain identified

100%

100%

Communication Overhead identified

100%

100%

Topology change recommended

90%

80%

Parallelization recommended

100%

100%

Stream processing recommended

100%

100%

Expected improvement percentages

100%

100%

Root cause per bottleneck

100%

100%

Impact/severity per bottleneck

100%

100%

remediation_plan.json produced

100%

100%

Batching recommended for messages

100%

100%

Specialist agents underutilized

100%

100%

100%

CI/CD Pipeline Performance Planning

Three-phase analysis workflow and proactive optimization planning

Criteria
Without context
With context

Data collection phase documented

100%

100%

Analysis phase documented

100%

100%

Recommendation phase documented

100%

100%

Baseline comparison made

100%

100%

Cache hit rate degradation identified

100%

100%

Sequential test execution identified

100%

100%

Action plan with success metrics

100%

100%

Expected improvement percentages

100%

100%

Baseline metrics for monitoring

100%

100%

Regression alerting recommended

100%

100%

Gradual/staged implementation

100%

100%

Resource contention trend noted

100%

100%

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.