跳到正文
cccskills
免费在 GitHub 公开

read-the-trace

Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md821 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Read the Trace

LLMs love to see "TypeError" and generate a generic fix without reading the trace. Don't.

  • Find the deepest frame in YOUR code — not the library frame at the top. That's where the bad value entered.
  • Read the actual values: what was null/undefined/wrong-type, and where it came from.
  • Trace it one level up: why was that value bad? The root is usually 1-2 frames above the throw.
  • Reproduce with that exact input before fixing. A TypeError can mean a hundred things. The trace tells you which one — read all of it, including the "caused by".

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

a11y-pass

免费

Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.

中文简介正在准备中。当前显示原文说明。

Archive228/loopkit7552026年7月15日 更新

Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.

中文简介正在准备中。当前显示原文说明。

Archive228/loopkit7552026年7月15日 更新

Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.

中文简介正在准备中。当前显示原文说明。

Archive228/loopkit7552026年7月15日 更新

Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.

中文简介正在准备中。当前显示原文说明。

Archive228/loopkit7552026年7月15日 更新

Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.

中文简介正在准备中。当前显示原文说明。

Archive228/loopkit7552026年7月15日 更新

Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.

中文简介正在准备中。当前显示原文说明。

Archive228/loopkit7552026年7月15日 更新

查看 Archive228 的全部技能

报告此技能的问题