菜单
When multiple tests fail, assign each failing test file to a separate subagent that fixes it independently in parallel.
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。
基于 SOC 职业分类
Generate or edit images using the OpenAI Image API (gpt-image-2). Use when the user asks to generate, create, draw, render, illustrate, mock up, or edit an image, icon, logo, mockup, illustration, OG image, blog hero, marketing asset, or similar visual. Also use when the user supplies a reference image and asks to modify, restyle, or remix it. Triggers on: "generate an image", "create an image", "make a picture of", "edit this image", "restyle this", "make a mockup of", "draw a", "render a", "illustration of".
When the same multi-step workflow repeats in Cursor (user corrections or agent redos), capture it as a new SKILL.md under .cursor/skills/ so future sessions load it automatically.
After navigating and interacting in Cursor's built-in browser, use browser_network_requests to audit every fetch/XHR for failures, slowness, duplicate calls, and suspicious payloads. Use for API-heavy pages and after backend or client networking changes.
When GitHub Actions fails, fetch failing job logs and assign each failing job to a separate subagent that fixes its slice of the problem in parallel. Use for multi-job CI failures where jobs are independent.
Run four parallel read-only subagents that each review the same diff from a different lens — security, performance, correctness, and readability — then merge findings into one report. Use before merging large or risky PRs.
Execute a user flow step-by-step in Cursor's built-in browser while documenting each action, then emit a Playwright test that replays the same flow using stable selectors derived from the accessibility tree.
| name | parallel-test-fixing |
| description | When multiple tests fail, assign each failing test file to a separate subagent that fixes it independently in parallel. |
| user-invocable | true |
Speed up fixing a broken test suite by distributing failing tests across parallel subagents.
npm test -- --no-coverage 2>&1 || true
Capture the output and extract all failing test files.
Parse the test output for failing files:
FAIL src/components/Button.test.tsxFAIL src/utils/format.test.tsFAILED tests/test_api.py::test_create_userGroup by file — each file becomes one task.
For each failing test file, launch a generalPurpose subagent:
Task: Fix the failing tests in <file>
The test file is: <path>
The test command is: <command to run just this file>
The error output was:
<paste the relevant failure output>
Steps:
1. Read the test file and the source file it tests
2. Understand why each test is failing
3. Fix the source code (preferred) or update the test if the test is wrong
4. Run the single test file to confirm it passes
5. Report what you changed and why
Launch all subagents simultaneously — they work in parallel since each touches different files.
As each subagent completes, collect:
Run the full test suite one more time to confirm everything passes:
npm test
If there are new failures (from conflicting fixes), resolve them sequentially.
best-of-n-runner subagents if you want isolated worktrees for each fix attempt