running-load-tests
This skill enables Claude to create and execute load tests for performance validation. It is designed to generate load test scripts using tools like k6, JMeter, and Artillery, based on specified test scenarios. Use this skill when the user requests to create a "load test", conduct "performance testing", validate "application performance", or needs a "stress test" to identify breaking points in the application. The skill helps define performance thresholds and provides execution instructions.
78
50%
Does it follow best practices?
Impact
99%
1.00xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-batch-20251204-000554/plugins/performance/load-test-runner/skills/load-test-runner/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates its purpose, lists specific tools and actions, and includes explicit trigger guidance. The only minor weakness is the use of 'It is designed to' which is slightly verbose, and the phrase 'This skill enables Claude to' uses a slightly indirect voice, but overall the description is strong and functional.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: create and execute load tests, generate load test scripts using specific tools (k6, JMeter, Artillery), define performance thresholds, and provide execution instructions. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate load test scripts using k6/JMeter/Artillery, define performance thresholds, provide execution instructions) and 'when' (explicit 'Use this skill when...' clause with specific trigger scenarios like load test, performance testing, stress test). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'load test', 'performance testing', 'application performance', 'stress test', 'breaking points', plus tool names like 'k6', 'JMeter', 'Artillery'. Good coverage of natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around load/performance/stress testing with specific tool names (k6, JMeter, Artillery). Unlikely to conflict with general coding skills or other testing skills due to the specific domain focus on performance validation. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is essentially a marketing description of what load testing is, rather than an actionable skill that teaches Claude how to generate and execute load tests. It contains no executable code examples, no script templates for k6/JMeter/Artillery, no specific commands, and no validation steps. The content explains concepts Claude already knows while omitting the concrete technical details that would make it useful.
Suggestions
Replace the abstract 'How It Works' section with concrete, executable script templates for at least one tool (e.g., a complete k6 script with realistic scenarios, thresholds, and stages).
Add actual code examples in the Examples section—show the generated k6/JMeter/Artillery script output rather than describing what the skill 'will do'.
Include specific execution commands (e.g., `k6 run --vus 1000 --duration 5m script.js`) and validation steps (e.g., how to interpret results, what metrics to check, when to flag failures).
Remove the 'Overview', 'When to Use This Skill', 'Best Practices', and 'Integration' sections—they add no actionable information and waste tokens on things Claude already knows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and padded with unnecessary context. Sections like 'Overview', 'How It Works', 'When to Use This Skill', and 'Integration' explain things Claude already knows or repeat the frontmatter description. Phrases like 'This skill empowers Claude to automate' and 'It streamlines the process' are filler that add no actionable value. | 1 / 3 |
Actionability | There is no executable code, no concrete script examples, no specific commands, and no copy-paste ready content. The examples describe what the skill 'will do' in abstract terms rather than providing actual k6, JMeter, or Artillery script templates. The guidance is entirely descriptive rather than instructive. | 1 / 3 |
Workflow Clarity | The 'How It Works' section lists abstract steps (analyze, identify, generate, define) without any concrete sequencing, validation checkpoints, or error recovery. There are no commands to run, no verification steps to confirm scripts work, and no feedback loops for iterating on test results. | 1 / 3 |
Progressive Disclosure | The content is a monolithic block with no references to external files, no bundle files to support it, and no structured navigation. All content is inline but paradoxically lacks the depth that would justify being inline—it's simultaneously too long (verbose framing) and too shallow (no actual technical content). | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
9be4627
- Reviewed
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.