I-have-ADHD：防止您的编程智能体淹没答案的技巧

I-have-ADHD：防止您的编程智能体淹没答案的技巧
I-have-ADHD: A skill to stop coding agents from burying the answer

原始链接: https://github.com/ayghri/i-have-adhd

**i-have-adhd** 技能是一个专为编程助手设计的插件，旨在强制执行对 ADHD 患者友好的交流习惯，剔除对话中多余的赘述与修饰。 **核心功能：** * **直截了当：** 去除开场白、总结、类似“希望能帮到你！”的客套话以及题外话。 * **以行动为导向：** 优先提供后续步骤，多步骤任务使用编号列表，且列表项不超过五条。 * **高效性：** 提供明确的时间预估，并在每轮对话中重申背景信息，以减轻认知负担。 **安装方式：** 1. 从 [github.com/ayghri/i-have-adhd](https://github.com/ayghri/i-have-adhd) 克隆存储库。 2. 按照 `AGENTS.md` 中的说明配置你的环境。 3. 若需自定义设置，请 fork 该存储库，根据偏好编辑 `SKILL.md`，然后通过命令行工具安装你的版本（例如：`claude plugin install /i-have-adhd`）。 4. 重启你的编程助手并输入 `/i-have-adhd` 以启用。该插件旨在最大程度提升专注力，确保你的 AI 助手保持简洁、客观并专注于任务本身。

最近一则 Hacker News 上的讨论凸显了用户对现代编程代理（尤其是 Claude 3 Opus）冗长和“谄媚”表现的普遍不满。用户反映这些代理经常“废话连篇”，对未执行的操作进行不必要的解释，并充斥着过度的、带有说教意味的废话。讨论围绕一个名为 **“I-have-ADHD”** 的 GitHub 项目展开，该项目旨在强制代理保持简洁直接。尽管许多用户认为该工具很有帮助，但关于其实现方式仍存在争议： * **提示工程 vs. 技能：** 许多参与者认为，专门创建一个“技能”有些多此一举，通过更新全局 `CLAUDE.md` 或 `AGENTS.md` 文件，或者利用内置的“输出风格”即可达到同样的效果。 * **“ADHD”标签：** 该工具的命名引发了争议。一些被诊断为 ADHD 的用户认为这个标签轻视了这种真正的医学状况；而另一些人则指出，为了适应神经多样性而采用的方法（如清晰、结构化且简洁的沟通）对所有用户来说实际上都是更好的选择。 * **模型性能：** 许多用户表示已经弃用 Claude，转向 Codex 或 Gemini 等模型，因为他们发现这些模型不太会出现“Claude 式”的语言习惯和不必要的对话赘述。这表明问题可能源于模型在 RLHF（基于人类反馈的强化学习）训练中被赋予的“人格化”特征。

原文

ADHD-friendly outputs. No ADHD diagnosis needed!

🇬🇧 · 🇨🇳 · 🇧🇷 · 🇯🇵 · 🇻🇳 · 🇰🇷 · 🇹🇭

Copy/paste into your CLI prompt:

Install the i-have-adhd skill/plugin from https://github.com/ayghri/i-have-adhd, refer to the repo's AGENTS.md for instructions.

Or 🔗 check the installation instructions.

A skill for your coding assistant that stops it from burying the answer. Action first. Steps numbered. No "Hope this helps!"

Great question! Let me think about this. Your auth flow has a few moving pieces: the middleware, the token verification, and the cookie handling. Looking at src/auth.ts, the verifyToken function (around lines 42-58) seems to be using an older jsonwebtoken API. One approach would be to update the package and rewrite that function. After making the change, you'd want to run the auth tests to confirm nothing breaks. By the way, you might also want to look at your dependency versions overall. Hope this helps! Let me know if you want to dig deeper.

Run npm install jsonwebtoken@latest, then edit src/auth.ts:42.

Open src/auth.ts

Replace verifyToken (lines 42–58) with the snippet below

Run npm test -- auth.spec.ts

Next: paste the first failing line if any test fails.

10 rules. Full text in SKILL.md.

Lead with the next action.
Number multi-step tasks.
End with one concrete next step.
Suppress tangents.
Restate state every turn.
Specific time estimates (minutes, not "a bit").
Make wins visible.
Matter-of-fact errors.
Cap lists at 5 items.
No preamble. No recap. No closers.

Fork, edit skills/i-have-adhd/SKILL.md, then swap your copy in:

claude plugin uninstall i-have-adhd            # drop the upstream copy first:
claude plugin marketplace remove i-have-adhd   # fork and upstream share both names
claude plugin marketplace add <your-username>/i-have-adhd
claude plugin install i-have-adhd@i-have-adhd

Restart Claude Code, then re-invoke /i-have-adhd.

Loosely based on The Adult ADHD Tool Kit by J. Russell Ramsay and Anthony L. Rostain. Adapted for how an LLM should respond, not how a human should organize their day.

MIT.

Star ⭐ if it saved you one scroll past one "Great question!"

I-have-ADHD：防止您的编程智能体淹没答案的技巧 I-have-ADHD: A skill to stop coding agents from burying the answer

I-have-ADHD：防止您的编程智能体淹没答案的技巧
I-have-ADHD: A skill to stop coding agents from burying the answer