running-load-tests

Create and execute load tests for performance validation using k6, JMeter, and Artillery. Use when validating application performance under load conditions or identifying bottlenecks. Trigger with phrases like "run load test", "create stress test", or "validate performance under load".

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/performance/load-test-runner/skills/running-load-tests/SKILL.md

Quality

Content

20%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-sectioned but padded with generic prose and lacks any executable code or commands, making it more descriptive than instructional. It also fails to reference the bundled scripts and templates that contain the actual tooling.

Suggestions

Replace the Overview/How It Works marketing prose with a concise quick-start showing a real k6, JMeter, or Artillery script, and remove explanations of what load testing is.

Add at least one complete, executable example per tool (e.g., a k6 script with options/thresholds) so the skill instructs rather than describes.

Insert an explicit validation checkpoint in the workflow (e.g., verify thresholds pass before reporting) and link to the bundled scripts/templates in scripts/ and assets/ instead of restating their purpose inline.

Dimension	Reasoning	Score
Conciseness	The Overview ("This skill empowers Claude to automate the creation and execution of load tests, ensuring applications can handle expected traffic…") and How It Works sections explain load-testing concepts Claude already knows, and Examples repeat the same ideas. This matches the verbose/padded anchor, and is not a 2 because the padding is pervasive rather than incidental.	1 / 3
Actionability	The body contains no executable code or commands; Examples only describe outcomes ("Generate a k6 script that simulates 1000 concurrent users") and Instructions are abstract steps. This matches "describes rather than instructs," and is not a 2 because there is no code or pseudocode at all, not merely incomplete code.	1 / 3
Workflow Clarity	Instructions give a clear six-step sequence (analyze, define scenarios, generate, configure, execute, analyze), but there are no validation checkpoints or feedback loops for batch load-test execution, which the rubric caps at 2. It is not a 1 because the sequence is present, and not a 3 because validation steps are missing.	2 / 3
Progressive Disclosure	The body is organized into clear sections, but the bundled scripts (k6_script_generator.py, load_test_executor.py, etc.) and asset templates exist and are never referenced or signaled from the body. It is not a 1 because it is not a monolithic wall, and not a 3 because the bundle files are not navigated.	2 / 3
	Total	6 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description: it states concrete actions and named tools, gives an explicit Use-when clause, and lists natural trigger phrases in third-person voice. It cleanly satisfies all four dimensions.

Dimension	Reasoning	Score
Specificity	"Create and execute load tests for performance validation using k6, JMeter, and Artillery" names concrete actions (create, execute) and three specific tools, matching the anchor that lists multiple specific concrete actions. It is comprehensive rather than partial, so it is not a 2.	3 / 3
Completeness	It states what the skill does (create and execute load tests with named tools) and when to use it ("Use when validating application performance under load conditions or identifying bottlenecks" plus trigger phrases). It is not a 2 because the "when" is explicit rather than merely implied.	3 / 3
Trigger Term Quality	Explicit trigger phrases "run load test", "create stress test", and "validate performance under load" are natural terms a user would say, giving good coverage. It is not a 2 because it supplies common variations rather than only a few relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Load testing with k6/JMeter/Artillery is a clear niche with distinct triggers unlikely to fire for unrelated skills. It is not a 2 because it does not meaningfully overlap with adjacent skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/performance/load-test-runner/skills/running-load-tests/SKILL.md
Commit: be8dd2e

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.