artillery-config-generator

Artillery Config Generator - Auto-activating skill for Performance Testing. Triggers on: artillery config generator, artillery config generator Part of the Performance Testing skill category.

0.98x

Quality

11%

Does it follow best practices?

Impact

98%

0.98x

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/artillery-config-generator/SKILL.md

Evaluation results

100%

Black Friday Load Test Preparation

Production-ready load test config

Criteria

Without context

With context

Valid YAML config

100%

Target defined

100%

Multi-phase load

100%

Ramp-up phase present

100%

Sustained peak phase

100%

Scenario with HTTP flow

100%

Multiple endpoints covered

100%

POST body included

100%

Run command documented

100%

Dependency install documented

100%

Results interpretation

100%

Without context: $0.2874 · 1m 16s · 19 turns · 19 in / 4,052 out tokens

With context: $0.3864 · 1m 28s · 24 turns · 24 in / 4,520 out tokens

100%

Finding the Breaking Point of the Notifications Service

Stress test phase escalation

Criteria

Without context

With context

Valid Artillery YAML

100%

Target URL set

100%

Three or more phases

100%

Progressive load increase

100%

Duration per phase

100%

Total duration under 10 min

100%

POST endpoint flow

100%

Breaking point explanation

100%

Metrics to watch documented

100%

Testing approach described

100%

Production-ready config

100%

Without context: $0.2964 · 1m 23s · 19 turns · 61 in / 4,396 out tokens

With context: $0.3920 · 1m 37s · 24 turns · 24 in / 5,646 out tokens

96%

-4%

API Performance Benchmark: Before and After Query Optimization

Benchmark comparison config

Criteria

Without context

With context

Both config files present

100%

Different targets

100%

Constant arrivalRate

100%

66%

Sufficient benchmark duration

100%

Search endpoint in flow

100%

Report output flags

100%

Sequential execution

100%

Constant-rate rationale

100%

Metrics comparison documented

100%

Configs are identical except target

100%

Without context: $0.2304 · 1m 17s · 15 turns · 16 in / 3,301 out tokens

With context: $0.4358 · 1m 43s · 27 turns · 318 in / 5,421 out tokens

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

Evaluated: 18 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Black Friday Load Test Preparation Finding the Breaking Point of the Notifications Service API Performance Benchmark: Before and After Query Optimization

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.