benchmark-suite-creator

Benchmark Suite Creator - Auto-activating skill for Performance Testing. Triggers on: benchmark suite creator, benchmark suite creator Part of the Performance Testing skill category.

1.02x

Quality

Does it follow best practices?

Impact

84%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/10-performance-testing/benchmark-suite-creator/SKILL.md

Evaluation results

100%

Load Testing Suite for Checkout API

k6 load test suite generation

Criteria

Without context

With context

Uses k6

100%

Ramp-up stages

100%

Stress scenario

100%

Performance thresholds

100%

All three endpoints covered

100%

Production-ready structure

100%

Checks on responses

100%

README with run instructions

100%

Metrics or trending

50%

100%

No stub/placeholder logic

100%

Without context: $0.4448 · 2m 25s · 17 turns · 62 in / 9,242 out tokens

With context: $0.5413 · 2m 28s · 28 turns · 29 in / 8,031 out tokens

54%

Performance Benchmark for Customer Portal Web Application

JMeter benchmark suite creation

Criteria

Without context

With context

Uses JMeter

Valid JMX structure

Multiple thread groups

100%

Dashboard flow covered

100%

Document download covered

100%

Assertions present

80%

100%

Listener or results config

75%

README with CLI instructions

30%

No stub/placeholder logic

100%

Without context: $0.4931 · 2m 38s · 21 turns · 21 in / 9,316 out tokens

With context: $0.5601 · 2m 22s · 28 turns · 289 in / 8,483 out tokens

100%

Full Performance Testing Strategy for New Microservice

Comprehensive multi-type performance suite

Criteria

Without context

With context

Uses k6 or JMeter

100%

Baseline load scenario

100%

Spike scenario

100%

Endurance/soak scenario

100%

All four endpoints covered

100%

Response validation

100%

Production-ready scripts

100%

Setup guide present

100%

Step-by-step install instructions

100%

Run instructions per scenario

100%

Performance monitoring note

100%

Without context: $0.5515 · 2m 37s · 23 turns · 24 in / 10,215 out tokens

With context: $0.5478 · 2m 16s · 27 turns · 60 in / 8,190 out tokens

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 0c08951

Evaluated: 17 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Load Testing Suite for Checkout API Performance Benchmark for Customer Portal Web Application Full Performance Testing Strategy for New Microservice

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.