Guide for creating optimized Claude Code agents. Use to design a new specialized agent, a swarm sub-agent, or a multi-agent workflow. Follows the Skill → Agent (preloaded skills) → Skill orchestration pattern.
中文简介正在准备中。当前显示原文说明。
Guide for Playwright end-to-end tests. Use to create a new e2e test, debug a flaky test, or test API endpoints. Covers patterns, workarounds, and project conventions.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Read .claude/roles/code-reviewer.md — adopt this profile and follow all its rules.
This skill activates for:
src/tests/e2e/
├── fixtures/
│ └── test-data.ts # Test data (webhooks, payloads, etc.)
├── specs/
│ ├── setup.ts # Server setup (run once)
│ └── <context>/
│ └── <feature>.spec.ts # Tests per feature
└── utils/
└── test-helpers.ts # Helpers (API calls, server setup)
| Command | Usage |
|---|---|
yarn e2e | Run all tests |
yarn e2e:debug | Debug mode with inspector |
yarn test:e2e:report | View HTML report |
specs/
├── setup.ts # Setup (do not touch)
├── webhook/ # Webhook endpoint tests
├── review/ # Review workflow tests
└── health/ # Health check tests
// specs/webhook/github-webhook.spec.ts
import { test, expect } from "@playwright/test";
test.describe("GitHub Webhook", () => {
test("should accept a valid pull request event", async ({ request }) => {
const response = await request.post("/webhooks/github", {
headers: {
"content-type": "application/json",
"x-github-event": "pull_request",
"x-hub-signature-256": "sha256=valid-signature",
},
data: {
action: "opened",
pull_request: {
number: 42,
title: "feat: add new feature",
head: { ref: "feat/new-feature" },
base: { ref: "main" },
},
repository: { full_name: "org/repo" },
sender: { login: "developer" },
},
});
expect(response.status()).toBe(200);
});
test("should reject an invalid payload", async ({ request }) => {
const response = await request.post("/webhooks/github", {
data: {},
});
expect(response.status()).toBe(400);
});
});
# Debug mode
yarn e2e:debug
# Run a single file
yarn e2e specs/webhook/github-webhook.spec.ts
| Priority | Type | Example |
|---|---|---|
| 1 | data-testid | [data-testid="submit-btn"] |
| 2 | Role (accessibility) | getByRole("button", { name: "Submit" }) |
| 3 | Text | getByText("Submit") |
| 4 | CSS (last resort) | table tbody tr |
test.describe("Authenticated API", () => {
test("should return review status with valid token", async ({ request }) => {
const response = await request.get("/api/reviews/123", {
headers: {
Authorization: `Bearer ${process.env.TEST_API_TOKEN}`,
},
});
expect(response.status()).toBe(200);
const body = await response.json();
expect(body).toHaveProperty("status");
});
});
import { TEST_WEBHOOKS, TEST_PAYLOADS } from "../fixtures/test-data";
test("should process a GitLab merge request event", async ({ request }) => {
const response = await request.post("/webhooks/gitlab", {
data: TEST_PAYLOADS.gitlabMergeRequest,
});
expect(response.status()).toBe(200);
});
// fixtures/test-data.ts
export const TEST_PAYLOADS = {
gitlabMergeRequest: {
object_kind: "merge_request",
object_attributes: {
iid: 1,
title: "feat: add review automation",
action: "open",
},
},
githubPullRequest: {
action: "opened",
pull_request: {
number: 42,
title: "fix: resolve webhook validation",
},
},
};
yarn e2e:debug specs/webhook/my-test.spec.ts
Traces are enabled on the first retry. After a failure:
yarn test:e2e:report
// Add checkpoints
console.log("Step: Sending webhook payload");
// Flaky: not waiting for server readiness
await request.post("/webhooks/github", { data: payload });
// Stable: verify server is ready first
const health = await request.get("/health");
expect(health.status()).toBe(200);
await request.post("/webhooks/github", { data: payload });
expect() from Playwright| Avoid | Prefer |
|---|---|
| Hardcoded test data | Fixtures from test-data.ts |
| Tests dependent on each other | Isolated tests |
| Missing error case coverage | Test both success and failure paths |
| Ignoring response body | Validate status AND body structure |
Arbitrary waitForTimeout | Proper readiness checks |
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Guide for creating optimized Claude Code agents. Use to design a new specialized agent, a swarm sub-agent, or a multi-agent workflow. Follows the Skill → Agent (preloaded skills) → Skill orchestration pattern.
中文简介正在准备中。当前显示原文说明。
Anti-overengineering guide based on YAGNI. Use before adding an architectural pattern, during code review, or to challenge an overly complex implementation.
中文简介正在准备中。当前显示原文说明。
Clean Architecture (Uncle Bob) guide for this project. Use when creating modules, entities, use cases, presenters, controllers, gateways, guards, services. Contains tactical patterns and structure conventions.
中文简介正在准备中。当前显示原文说明。
Audit documentation for duplication, staleness, language issues, and verbosity. Read-only — produces an actionable report.
中文简介正在准备中。当前显示原文说明。
Local auto-review of modified code (no GitLab/GitHub). Runs 5 sequential audits and generates a local report. Ideal for validating code before creating a MR/PR.
中文简介正在准备中。当前显示原文说明。
Clean Code (Robert C. Martin) guide to produce and challenge code that is readable, durable, simple, and consistent. Covers naming, functions, comments, smells, and refactor heuristics. Complements `/solid` (SOLID principles) and `/anti-overengineering` (YAGNI/KISS). Activate during the REFACTOR phase of the TDD cycle and during implementation self-review.
中文简介正在准备中。当前显示原文说明。