setup-artillery-cli-for-load-testing
Set up Artillery load testing for any project. Detects package manager and project type, creates a TypeScript test script (HTTP or Playwright browser), configures Artillery Cloud, and provides the run command. Use when the user wants to add load testing, performance testing, or browser-based load testing to their project.
93
88%
Does it follow best practices?
Impact
96%
1.84xAverage score across 6 eval scenarios
Risky
Do not use without reviewing
Quality
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 an excellent skill description that clearly articulates specific capabilities (package manager detection, TypeScript test script creation, Artillery Cloud configuration) and provides explicit trigger guidance. It uses third person voice correctly and includes natural keywords that users would actually say when needing load testing functionality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Detects package manager and project type, creates a TypeScript test script (HTTP or Playwright browser), configures Artillery Cloud, and provides the run command.' | 3 / 3 |
Completeness | Clearly answers both what (set up Artillery, detect package manager, create test scripts, configure cloud, provide run command) AND when ('Use when the user wants to add load testing, performance testing, or browser-based load testing'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'load testing', 'performance testing', 'browser-based load testing', 'Artillery'. These are terms users would naturally use when seeking this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche with distinct triggers: Artillery-specific, load/performance testing focus, mentions specific technologies (Playwright, TypeScript). Unlikely to conflict with general testing or other performance tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill with clear workflow steps and executable code templates. The main weakness is some verbosity—the reference section duplicates template information, and basic explanations could be trimmed. The decision points and safety boundary (not auto-running tests) are excellent patterns.
Suggestions
Remove the reference section at the end—the information is already demonstrated in the code templates above it
Condense the package manager table to a single line pattern like 'Install with your package manager: `{npm|pnpm|yarn|bun} {install|add} -D artillery`'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundant explanations (e.g., explaining what Artillery is, listing all package manager commands in a table when Claude could infer this). The reference section at the end duplicates information already shown in the templates. | 2 / 3 |
Actionability | Provides fully executable TypeScript code templates with proper imports and types. Commands are copy-paste ready, and the templates include clear placeholders (TARGET_URL, ENDPOINT) with instructions on how to adapt them. | 3 / 3 |
Workflow Clarity | Clear 6-step sequence with explicit decision points marked as 'DECISION'. The workflow includes appropriate checkpoints (asking user questions before proceeding) and explicitly instructs Claude NOT to run the test, leaving that to the user—a good safety boundary. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, but everything is in a single file. The reference section at the end could be a separate file. For a skill of this length (~150 lines), some content like the full TypeScript reference could be split out. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- artilleryio/agent-skills
- Commit
78a9dbe
- 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.