grinding-until-pass

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Grind Until Pass

持续迭代直至通过

Use this skill when you want the agent to keep working autonomously until a specific goal is met — all tests pass, the build succeeds, or linting is clean. Instead of stopping after one attempt, the agent loops until done.

当你希望Agent自主持续工作直至达成特定目标（所有测试通过、构建成功或代码检查无问题）时，使用此技能。Agent不会仅尝试一次就停止，而是循环执行直至完成目标。

Steps

步骤

Define the goal command — the command whose exit code determines success:

Tests:
```
npm test
```
or
```
npx vitest run
```
Build:
```
npm run build
```
Lint:
```
npm run lint
```
Type-check:
```
npx tsc --noEmit
```

All of the above:

npm run lint && npx tsc --noEmit && npm test && npm run build

Run the command — execute it and capture the output.
If it fails — analyze and fix:
- Read the error output carefully.
- Identify the root cause: failing test assertion, type error, lint violation, import error, etc.
- Make the minimal fix. Don't refactor — just fix the error.
- Go back to step 2.
If it passes — stop and report:
- Report what was fixed and how many iterations it took.
- Summarize the changes made.

定义目标命令 —— 该命令的退出码将决定是否成功：
- 测试：
```
npm test
```
  或
```
npx vitest run
```
- 构建：
```
npm run build
```
- 代码检查：
```
npm run lint
```
- 类型检查：
```
npx tsc --noEmit
```
- 以上全部：
```
npm run lint && npx tsc --noEmit && npm test && npm run build
```
运行命令 —— 执行命令并捕获输出。
若失败——分析并修复：
- 仔细读取错误输出。
- 识别根本原因：测试断言失败、类型错误、代码检查违规、导入错误等。
- 进行最小化修复。不要重构——仅修复错误即可。
- 返回至步骤2。
若成功——停止并报告：
- 报告修复内容及迭代次数。
- 总结所做的更改。

Rules for the Loop

循环规则

Maximum 10 iterations — if after 10 attempts the command still fails, stop and report what's blocking progress. Something fundamental is wrong and needs human input.
Fix one thing at a time — don't try to fix all errors at once. Fix the first error, re-run, and see if the fix resolves downstream errors too.
Don't delete tests — if a test is failing, fix the code to make it pass. Don't modify the test unless the test itself is clearly wrong (testing old behavior that was intentionally changed).
Don't suppress errors — don't add
```
@ts-ignore
```
,
```
eslint-disable
```
, or
```
any
```
types to silence errors. Fix the actual problem.
Track progress — if the number of errors is increasing instead of decreasing, stop and reassess the approach.

最多10次迭代 —— 如果经过10次尝试后命令仍失败，停止并报告阻碍进度的问题。此时存在需要人工介入的根本性问题。
一次只修复一个问题 —— 不要尝试一次性修复所有错误。先修复第一个错误，重新运行，查看该修复是否也解决了后续错误。
不要删除测试 —— 如果测试失败，修复代码使其通过。除非测试本身明显有误（测试的是已被有意更改的旧行为），否则不要修改测试。
不要抑制错误 —— 不要添加
```
@ts-ignore
```
、
```
eslint-disable
```
或
```
any
```
类型来掩盖错误。修复实际问题。
跟踪进度 —— 如果错误数量不减反增，停止并重新评估方法。

When to Use This

使用场景

After a large refactor that broke multiple tests
After upgrading a dependency that introduced type errors
After merging a branch with conflicts that need resolution
When you want to "just make it green" and trust the agent to grind through it

大型重构导致多个测试失败后
升级依赖引入类型错误后
合并存在冲突的分支后
当你希望“直接让结果达标”并信任Agent自主解决问题时

Advanced: Cursor Hooks Integration

进阶：Cursor Hooks集成

You can automate this with a Cursor hook in

.cursor/hooks.json

that triggers after the agent's turn ends, checks if tests pass, and sends a follow-up message if they don't:

json

{
  "hooks": [
    {
      "event": "stop",
      "command": "bash .cursor/scripts/check-tests.sh",
      "description": "Re-run tests after agent stops and send follow-up if failing"
    }
  ]
}

The script checks the exit code and returns a

followup_message

if tests are still failing.

你可以通过

.cursor/hooks.json

中的Cursor Hook实现自动化，在Agent任务结束后触发，检查测试是否通过，若未通过则发送后续消息：

json

{
  "hooks": [
    {
      "event": "stop",
      "command": "bash .cursor/scripts/check-tests.sh",
      "description": "Re-run tests after agent stops and send follow-up if failing"
    }
  ]
}

该脚本会检查退出码，若测试仍失败则返回

followup_message

。

Notes

注意事项

This works best with fast test suites. If your tests take 5+ minutes, the loop will be slow.
Use
```
--bail
```
or
```
--fail-fast
```
flags to stop at the first failure for faster iteration.
The agent will be thorough but not creative — if the fix requires a design change, it'll need human guidance.

此功能在测试套件运行速度快时效果最佳。如果测试需要5分钟以上，循环执行会很慢。
使用
```
--bail
```
或
```
--fail-fast
```
标志在第一个失败点停止，以加快迭代速度。
Agent会执行得很彻底但缺乏创造性——如果修复需要设计变更，则需要人工指导。