Worth Fix logo

Worth Fix

Community
luochang212
worth-fix

分析和判断任何论断、报告、想法或需求的真实性、价值与做法。当用户说"这个 bug 是真的吗"、"分析一下这个问题/这个报告/这个说法"、"这个修复值得做吗"、"帮我看下这个建议靠不靠谱",或用户给出一个待评估的 bug 报告、文章摘录、设计提案时使用。先核验、复现、定级、讲清原理、判断是否值得做,而不是直接相信或直接动手改代码。也适用于评估"要不要重构"。

Overview

Publisherluochang212
Repositoryskill-zoo
Skill nameworth-fix
Stars
124
Forks
13
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by luochang212 on GitHub. Read the source before you install it.

Installation

Install the Worth Fix AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/luochang212/skill-zoo/tree/main/skills/worth-fix
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/luochang212/skill-zoo.git /tmp/skill-zoo
mkdir -p .claude/skills
cp -r /tmp/skill-zoo/skills/worth-fix .claude/skills/worth-fix
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Worth Fix in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Worth Fix on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Worth Fix is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Worth Fix(值得修吗?先验证,再判断)

核心态度

  • 一切论断都是假说。报告、博客、AI 输出、甚至自己的第一印象,都要过一遍"这是真的吗"。来源可信不等于内容正确。
  • 实证优先于推理。能跑就测,能复现就复现。读代码推断的"应该是这样"不如一次实测的"实际是这样"。只有说"我实测过"才有资格说"坐实"。
  • 区分"属实"与"值得修"。真不代表要动,假也不代表不用查。真实性判断与价值判断是两个独立维度,分开做。
  • 敢证伪,也敢修正严重度。报告夸大(如"栈溢出崩溃"实测只是报错)或缩小,都要如实修正,不将就原文结论。

工作流

环节可裁剪性:最小复现、核实前提、判定值得、留痕是必须环节;威胁建模、讲清原理、沟通格式按风险/规模裁剪。小 change、一眼看穿的修复可跳过重环节,不必走全套仪式。

1. 把论断转成可验证的命题

把"报告说 X 会崩"改写成"当条件 C 满足时,行为 B 是否发生"。一个论断拆成几个可独立验证的命题,逐个验证。

2. 最小测试直击真实代码路径

写最小复现(临时测试/脚本),直接调用真实的生产函数,不要测试模拟器或复制逻辑。用 --nocapture 打印关键中间证据(如"外部文件被复制 = true")。

复现验证缺陷后,把同一场景翻转断言固化为回归测试(红→绿:先证明缺陷存在,修复后证明行为正确)。复现是回归测试的原材料,不是看完现象就扔。临时脚手架可删,场景必须留下。

复现不可行时:先评估是否缺少测试注入点(路径硬编码、函数不可注入)或会污染真实环境(写入用户目录、破坏真实数据)。评估后仍不可行,改用结构验证(代码控制流审查 + 全套测试无回归),并把验证边界记录进交付物(如 proposal 的 Impact:哪些实证、哪些审查、为什么)。其中"未实测"必须标注,不得以审查冒充实证。

3. 核实推理链上的每个前提

攻击面/缺陷的可达性由多个环节组成(如:归档保留软链 → 解压物化 → 复制跟随)。每一环都单独验证,不因"看起来显然"跳过。特别注意验证依赖库的真实行为(读库源码或构造输入实测),而不是按常识假设。

4. 判定"属实"程度

对每个命题给出结论分级:坐实 / 部分属实(有夸大或缩小)/ 证伪。逐条说明证据。区分"现象为真"与"影响为真"。现象成立但后果被夸大了,就要如实修正定级。

5. 判定"值得修"

属实 ≠ 值得修。按四维评估:触发概率、影响面、修复成本、不修的后果。高成本低概率的排队,低成本高影响的立即做;报告里"属实但不值得修"的条目要明确列出,并说明为什么。不要为了显得勤快而修不值得修的。

四维之外,对成本极低、影响不明的项,用后悔不对称补充:将来它若造成影响,那时的后悔("我明明早就知道")是否超过现在顺手处理的成本?超过就做。这正是"卫生级"修复(死配置键、未捕获的 rejection)成立的判据,纯期望值在此象限给不出答案。预演终局("将来如何评价这个决定")只用于不可逆或高成本的决定,且产出是"把最可能被质疑的点提前变成显式取舍",不是预测结论。

6. 讲清原理再动手

动手改之前,先用最简单的话讲清楚根因("这个 bug 是因为 A 用 stat 而 B 用 lstat,分支顺序错了"),确保听者能复述。讲不清原理就动手,是没想明白的信号。

7. 威胁建模

涉及安全/边界时,用攻击者视角推演完整链路:攻击者能控制什么 → 受害者做什么动作触发 → 每一步是否成立 → 最终后果。诚实分层后果:区分"确定发生"(无后续动作即成立)与"大概率发生"(还需一个后续步骤),不夸大(不说成自动外传)也不缩小(不说成纯理论)。说明现实摩擦(如需猜测路径、权限失败即回滚),让定级可信。

8. 定级与决策

  • 定性:崩溃 / 数据损坏 / 越权读取 / 文案错误等,再给严重度(高/中/低)。
  • 要不要重构:先判断是"局部缺陷"还是"架构问题"。单函数内的顺序/解析错误 → 局部修复,明确说"不需要重构"并说明为什么(如"与发现阶段已有防护对齐,属补齐既有架构")。只有多个模块共用的地基性问题才谈重构。
  • 决策要给"一句话总结":真实、可被谁触发、涉及什么、成本多高、是否需要重构。

9. 粒度切分

把大报告/大需求按"一个意图一句话能说清"切分。同意图的相邻小修合并成一个单元,互不相关的拆开;typo 级修复不配仪式(文档、多条需求),别过度工程化。粒度 = 一次 review 的自然单元。

10. 留痕

把证据、推理链、勘误(哪些被证伪、哪些被修正)写进项目文档(如 OpenSpec change 的 proposal),让后来的 agent 能复现你的推理,而不只是看到结论。

沟通格式(怎么讲清一个问题)

对"这是什么问题",按此顺序讲,每层都简短:

  1. 一句话说明(用比喻也行,如"传送门文件被钻进去了")
  2. 具体触发链路(分步,每步可验证)
  3. 场景与后果分层(最重/中等/最轻三档)
  4. 不改会怎样(是持续敞开还是自愈,根源是逻辑还是环境)
  5. 小问题还是大问题(按影响面与信任模型,不按修复成本)
  6. 是否需要重构(明确回答,不模棱两可)

反模式

  • 盲信报告、引用、或"大家都这么说"
  • 只读代码不实测,把推断当结论
  • 复现不出就断言"不存在"(复现失败 ≠ 缺陷不存在,先缩小范围或改用结构验证并标注)
  • 为复现而复现(复现成本远超收益仍强行复现)
  • 现象坐实就顺手把影响也夸大
  • 不验证就说"坐实"
  • 小 bug 大手术(顺手重构相邻代码)
  • 修完不留痕,后来者只能看到 git diff 猜动机
  • 为显得勤快而修不值得修的条目

检查清单

  • 论断是否已转成可验证命题?
  • 是否写了直击真实代码路径的最小复现?
  • 复现场景是否固化为回归测试(或已记录"复现不可行"的验证边界)?
  • 推理链每一环是否都有实证?
  • "属实"与"值得修"是否分开判定?
  • 原理是否已用最简单的话讲清?
  • 是否做了威胁建模并诚实分层后果?
  • 是否明确回答了"要不要重构"?
  • 低危项是否用后悔不对称审视过(而非仅看当前影响)?
  • 结论是否已留痕(证据回填)?

Frequently asked questions

What does the Worth Fix AI skill do?

分析和判断任何论断、报告、想法或需求的真实性、价值与做法。当用户说"这个 bug 是真的吗"、"分析一下这个问题/这个报告/这个说法"、"这个修复值得做吗"、"帮我看下这个建议靠不靠谱",或用户给出一个待评估的 bug 报告、文章摘录、设计提案时使用。先核验、复现、定级、讲清原理、判断是否值得做,而不是直接相信或直接动手改代码。也适用于评估"要不要重构"。

Why use Worth Fix on TypingMind?

Because you install it once and use it with any model. Worth Fix is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Worth Fix in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/luochang212/skill-zoo/tree/main/skills/worth-fix. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Worth Fix?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Worth Fix?

As many as you like. As long as a model supports skills, you can use Worth Fix with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Worth Fix AI skill free?

Yes. It is published on GitHub by luochang212 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇