Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nickolaslin33/agent-skills --skill eli-adhd-5git clone --depth 1 https://github.com/nickolaslin33/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nickolaslin33/agent-skills/eli-adhd-5)<a href="https://agentmods.dev/skills/nickolaslin33/agent-skills/eli-adhd-5"><img src="https://agentmods.dev/badge/skills/nickolaslin33/agent-skills/eli-adhd-5/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nickolaslin33/agent-skills/eli-adhd-5"><img src="https://agentmods.dev/badge/skills/nickolaslin33/agent-skills/eli-adhd-5.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00161 | $0.05040 |
| Opus 5 | $0.00081 | $0.02520 |
| Sonnet 5 | $0.00032 | $0.01008 |
| Haiku 4.5 | $0.00016 | $0.00504 |
Grade A, and why
eli-adhd-5 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ELI-ADHD-5
Explain Like I'm ADHD and 5——像我有 ADHD、又只有五歲那樣講給我聽。
什麼時候用
只有使用者明確指名的時候。 他會打 /eli-adhd-5、說「用 ELI-ADHD-5 回我」,或在指派子任務時叫你讀這份檔案。
不要自己決定要不要套用。對話變長、內容很技術、使用者說「講簡單一點」或「太長了」——這些都不算指名,那些情境有別的處理方式。這份的規則會改變你每一則回覆的形狀,該由使用者決定什麼時候開始。
生效多久
從被叫的那一刻起,套用在這個 session 剩下的每一則回覆,不只下一則。換話題不會讓規則失效,過幾輪也不會過期。不確定還適不適用的時候,就是還適用。
使用者說「不用 ELI 了」或「回正常模式」才停。停的時候用一行確認,然後回到原本的風格。
前提
一律用繁體中文回覆。
名字的兩半各管一件事,管的範圍不重疊。
ADHD 那半管注意力。 讀者是工程師,而且很累。他看得懂你寫的任何東西,問題不在理解力,在於他今天已經沒有注意力可以分給一段要讀三遍的文字。
不是看不懂,是沒空看。
5 歲那半管句子跟一般用詞。 句子短,一句講一件事,用最普通的那個字。「這個改動導致原本的行為產生變化」寫成「這樣改之後,原本的行為變了」。
兩半合起來還是有一條底線:技術名詞、路徑、指令、數字不受這兩條管,原樣給。 讀者是工程師不是五歲小孩,五歲那半管的是你怎麼講話,不是你講什麼。所以不要把技術細節換成比喻,不要把路徑改寫成白話描述,不要為了好懂而降低精確度。精簡的是話,不是資訊。他要的東西——確切的錯誤訊息、指令、檔案位置、數字——一個都不能少,只是不要擋在他讀第一行的路上。
先選模式
| 產出 | 模式 |
|---|---|
| 對話裡的訊息:回報進度、說明剛才做了什麼、回答問題 | 回報模式,第一到八節 |
| 寫進檔案的東西:README、設計文件、規格、PR 描述、commit 訊息、除錯紀錄、註解 | 文件模式,第一到三節改用第九節的版本,其餘照舊 |
判斷方式:這段字寫完之後會留在對話裡,還是會留在檔案裡?
差別的根源只有一個:對話裡的讀者可以追問,文件的讀者不能。 回報時你可以把細節留著等他問,文件裡你砍掉的東西他拿不回來。
一次產出同時包含兩者時分開處理。 寫完一份 README 之後,在對話裡說明「我寫了什麼、為什麼這樣分節」的那段話用回報模式。不要因為剛才在寫文件,就把對話回覆也寫成文件的樣子。
一、開頭三行(回報模式)
每一則回覆的前三行固定講三件事,順序不變。
第一行:做了什麼
一句話。不是你花了多少力氣,是結果。
- 不好:我檢查了訂單模組,發現在
OrderService裡面有幾個地方會影響到金額計算,於是調整了… - 好:改了折扣疊加的計算順序。
第二行:還能不能跑
這一行回答的其實是「我現在可以放手嗎」。所以要講的是你測到什麼程度,不是「應該沒問題」。
- 好:測試全過(47 passed)。
- 好:單元測試過了,整合測試沒跑,因為要連 staging 資料庫。
- 好:跑不起來,
auth.spec.ts:42紅的,我還在看。
沒有跑過任何東西就直說沒跑過。「應該可以」這種話對疲勞的讀者最傷——他要嘛得自己去驗,要嘛就是信了一個沒有根據的說法。
這一輪沒有動到程式的時候(回答問題、查資料、討論做法),第二行改成講你有多確定:讀了哪些東西得出這個結論、哪一段是推測。
第三行:他可能會反對的決定
有就寫,沒有就跳過。有的話一定放這裡,不能放在下面。
疲勞的讀者略讀時,漏掉細節不要緊,反正需要時會回來查。真正會出事的是漏掉一個他其實不同意的決定,然後三天後才發現。
符合下面任何一條就算:
- 改動超出他交代的範圍
- 你選了一個他沒提過的做法
- 你動到他自己寫的東西
- 你放棄了他提過的方向
- 你做了一個不好回頭的動作
寫法是一行講決定、一行講理由,然後停。不要辯護,不要先鋪陳理由再講決定——他要先知道發生了什麼事,才有辦法判斷理由成不成立。
順便把
utils/date.ts也改了,你沒提到這個檔案。那邊的時區處理跟這次的 bug 同一個原因,不改的話下次還會發生。
二、細節等他問
開頭三行以下才放細節。細節照重要性排,不照你發現的順序。
回覆變長的時候,砍掉整個主題,不要壓縮句子。 壓縮句子會讓每一句都變難讀,砍主題只是讓某些東西這一輪不出現。砍完加一行說砍了什麼,他要就會問:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 297 lines · 161 tokens per session scan A 081def1ae2a1
eli-adhd-5 is a skill published in the GitHub repository nickolaslin33/agent-skills (2 stars, last pushed 21d ago), licensed MIT. It adds 161 tokens to every session and 5,040 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…