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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

35%

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 and has a coherent workflow, but it lacks any executable code or commands, leans on generic/marketing prose, and omits validation checkpoints. Progressive disclosure is undercut by stub-only bundle files that are never referenced from the body.

Suggestions

Add concrete, copy-paste-ready examples — a complete k6 script with thresholds, and sample JMeter/Artillery launch commands — instead of describing outcomes like "Generate a k6 script that simulates 1000 concurrent users."

Trim the Overview marketing language ("empowers Claude", "streamlines", "comprehensive") and remove the generic Best Practices, Integration, and Resources pointers that restate what Claude already knows.

Insert explicit validation checkpoints into the workflow, e.g. run a small-scale smoke test first and confirm thresholds pass before scaling to full load, with a validate → fix → re-run feedback loop for failures.

Dimension	Reasoning	Score
Conciseness	The body is mostly organized but padded with marketing fluff ("empowers Claude", "streamlines the process", "comprehensive performance validation") and generic Best Practices/Integration prose Claude already knows; it could be tightened without losing meaning.	2 / 3
Actionability	No executable code or concrete commands appear anywhere; Instructions and Examples describe outcomes ("Generate a k6 script that simulates 1000 concurrent users") rather than instruct, and the bundled generator scripts are referenced only in a README and do not exist as files.	1 / 3
Workflow Clarity	A sequence exists (analyze → identify scenarios → generate scripts → define thresholds → execute → analyze), but there are no explicit validation checkpoints or a validate-fix-retry feedback loop; for a batch operation like load testing, missing feedback loops cap this at 2.	2 / 3
Progressive Disclosure	The SKILL.md has clear section structure but is essentially monolithic at ~90 lines with no well-signaled one-level-deep references to real detail files; the bundle contains only stub READMEs and the body never links to the listed scripts or templates.	2 / 3
	Total	7 / 12 Passed

Description

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.

A strong, concise description that states concrete actions and tools, gives explicit "Use when" trigger guidance with natural phrases, and carves out a distinct niche. It avoids first/second-person voice and over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Create and execute load tests") and names the specific tools ("k6, JMeter, and Artillery") rather than vague language; it is not merely naming a domain like the score-2 anchor.	3 / 3
Completeness	Explicitly answers what ("Create and execute load tests for performance validation using k6, JMeter, and Artillery") and when ("Use when validating application performance under load conditions or identifying bottlenecks") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Provides natural phrases a user would say — "run load test", "create stress test", "validate performance under load" — plus "identifying bottlenecks", giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (load/performance testing with named tools) with distinct triggers unlikely to fire for unrelated skills; the "Use when..." clause narrows the scope to load validation.	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
Commit: 6e3a65f

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.