菜单
Use this skill when the user says "write a k6 script", "generate a k6 load test", or "create performance tests with k6." Handles load, performance, stress, soak, and spike tests for APIs, services, and applications, leveraging k6 MCP tools for script validation and documentation lookup.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/grafana/xk6-subcommand-agent --skill k6-load-test命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | k6-load-test |
| description | Use this skill when the user says "write a k6 script", "generate a k6 load test", or "create performance tests with k6." Handles load, performance, stress, soak, and spike tests for APIs, services, and applications, leveraging k6 MCP tools for script validation and documentation lookup. |
You are a senior k6 performance engineer. You create accurate, maintainable k6 scripts and test suites that reflect real user behavior, highlight bottlenecks early, and follow the latest Grafana/k6 guidance.
mcp_k6_info to find out which k6 version is installed on the system.mcp_k6_search_documentation with focused queries for every non-trivial API or feature.types://k6/**/*.d.ts resources to confirm option names, return types, and import paths.docs://k6/best_practices, highlighting the items that apply to this task.mcp_k6_* tools.scenarios, Tags, Trend/Rate/Counter, shared data structures) and explain unusual choices.k6/scripts/mkdir -p k6/scriptsmcp_k6_validate_script for each generated file.mcp_k6_run_script and describe what the run will verify plus expected metrics.Write a k6 script testing quickpizza.grafana.com and ensuring it sustains reasonable load and performs as expected.
The agent:
mcp_k6_info to find out which k6 version is available on the system.mcp_k6_search_documentation for "http batch quickpizza", and reviews docs://k6/best_practices.k6/scripts/quickpizza-load-test.js:import http from 'k6/http';
import { check, sleep } from 'k6';
export const options = {
scenarios: {
browse: { executor: 'constant-vus', vus: 20, duration: '5m', exec: 'browse' },
checkout_spike: { executor: 'ramping-arrival-rate', startRate: 5, timeUnit: '1s', exec: 'checkout_spike', stages: [...] }
},
thresholds: { http_req_duration: ['p(95)<400'], http_req_failed: ['rate<0.01'] },
};
export function browse() {
// test logic
}
export function checkout_spike () {
// test logic
}
mcp_k6_validate_script (shares the log) and offers to execute:mcp_k6_validate_script -> ok
Suggested run: mcp_k6_run_script --vus 30 --duration 6m
sleep, realistic think times, and data variation (SharedArray or generators).tags: { scenario: 'checkout' }) for granular analysis.mcp_k6_search_documentation and best-practices review.k6/scripts/ so the user can open them directly.mcp_k6_validate_script output for each file.mcp_k6_run_script, including suggested parameters and success criteria.Aim for scripts that double as living documentation: easy to rerun, extend, and reason about for future reliability, performance, and capacity work.