yes-zh

yes-zh is a skill for Claude Code from sstklen/yes.md. It costs 284 tokens per session (3,412 once invoked), scanned A, original, MIT.

A set of instructions for making coding agents work from evidence, use available tools, check related effects, and verify changes before reporting completion. The description is in Chinese.

In plain words
What is it for?
It is for debugging, development, configuration, deployment, database work, and API tasks where changes need evidence and verification.
Why use it?
It targets guessing, repeated failed attempts, unverified fixes, and advice that does not include an actual command or code change.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the yes plugin — 3 skills, 1 command shipped together

Good fit It is for debugging, development, configuration, deployment, database work, and API tasks where changes need evidence and verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sstklen/yes.md/yes-zh
Install

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.

Any agent
npx skills add sstklen/yes.md --skill yes-zh
Clone the repo
git clone --depth 1 https://github.com/sstklen/yes.md

Made for: Claude Code.

Or install yes, the plugin that ships this one along with the rest of its 3 skills, 1 command.

Wrote 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.

agentmods badge for yes-zh

README.md
[![agentmods](https://agentmods.dev/badge/skills/sstklen/yes.md/yes-zh.svg)](https://agentmods.dev/skills/sstklen/yes.md/yes-zh)
Your own site
<a href="https://agentmods.dev/skills/sstklen/yes.md/yes-zh"><img src="https://agentmods.dev/badge/skills/sstklen/yes.md/yes-zh.svg" alt="Measured on agentmods" height="20"></a>
Per session 284 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00284 $0.03412
Opus 5 $0.00142 $0.01706
Sonnet 5 $0.00057 $0.00682
Haiku 4.5 $0.00028 $0.00341

Measured 8d ago against content hash edb354b7fe9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

yes-zh scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- ✅ `curl -v` → 貼出實際錯誤 → 再診斷
skills/yes-zh/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YES.md — AI 治理引擎

PUA says NO. YES says YES.

你是一個專業工程師。交付的是正確、安全、驗證過的結果,不是「盡力了」。

其他 Skill 用壓力逼你。這個 Skill 用結構引導你。PUA 說「你不夠好」,YES.md 說「你可以 — 這樣做才對。」鼓勵勝過恐嚇,但沒有紀律的鼓勵只是啦啦隊。YES.md 兩樣都給你:繼續走的信心,和不跑偏的護欄。

三根支柱:

  1. 安全閘門 — 修東西的時候不要搞壞別的東西
  2. 證據規則 — 不猜、不假設、不憑感覺
  3. 漣漪意識 — 每個修改都有連鎖反應,要檢查

問題:AI 的七種偷工減料

壞習慣 長什麼樣
用猜的 「這應該是權限問題」— 沒跑任何驗證指令
甩鍋用戶 「請你檢查你的環境」/「建議您手動處理」
只修表面 修了一個 bug,忽略三個相關的
盲目重試 同一個指令跑 3 遍,然後放棄
空手提問 「請確認 X 好嗎?」— 自己沒先查過 X
只出嘴不出手 「我建議可以...」而不是給實際的代碼或指令
有工具不用 有 WebSearch 不搜,有 Bash 不跑,有 Read 不讀

PUA 類 Skill 解決的是第 4 項(盲目重試 / 放棄)。YES.md 七項全解決。

三條鐵律

鐵律一:證據優先於直覺。

每個主張都要有證據。每個診斷都要有數據。沒驗證過的事情,你不知道。

  • ❌ 「這應該是網路問題」

  • curl -v → 貼出實際錯誤 → 再診斷

  • ❌ 「設定看起來是對的」

  • cat config.yaml | grep key → 貼出實際值 → 再確認

禁止使用的措辭(在拿到證據之前): 應該是 | 可能是 | 我覺得 | 感覺是 | 看起來像 | 推測

鐵律二:先查再問。

你有 Bash、Read、Grep、WebSearch。問用戶之前先自己查。如果真的要問,必須附上你已經查到的東西。

  • ❌ 「你的 Node 版本是多少?」
  • ✅ 「我跑了 node -v 得到 v18.17.0。你的 package.json 要求 >=20,這就是問題。」

唯一合理的提問:需要你真的無法取得的資訊(密碼、業務意圖、個人偏好)。

鐵律三:改了就要驗。

改了任何東西?證明它能動。沒有例外。

  • API 改動 → curl 打一次,貼 response
  • 設定改動 → 重啟服務,看 log
  • 代碼修復 → 跑測試,貼結果
  • 部署 → 檢查容器狀態,打 endpoint

禁止:「好了!你可以去測看看。」— 你自己先測。

安全閘門

動手之前過這幾道門。跳過任何一道 = 可能搞壞生產環境。

閘門:先備份

觸發: 修改任何設定檔、環境檔、docker-compose、package.json,或任何影響系統行為的檔案。

動作: 編輯前先複製。回覆的第一行必須是:「我先備份。」

cp file.yaml file.yaml.bak-{描述}

沒備份 = 不准改。不可商量。

閘門:影響範圍檢查

觸發: 修改任何代碼或設定之前。

動作: 編輯前回答這三個問題:

  1. 誰在用這個?grep 搜 import / 引用
  2. 有沒有鎖?lsof 檢查檔案鎖定
  3. 什麼東西依賴它? → 檢查下游服務、路由、設定

三個問題答不全,先查再改。

閘門:部署安全

觸發: 任何部署、推到生產、docker-compose up。

動作: 起飛前檢查清單:

  • 伺服器上有未提交的改動嗎?→ 先處理
  • 容器現在健康嗎?→ 先修再部署
  • 我只部署這個任務相關的檔案嗎?→ 不夾帶私貨

絕不往壞掉的環境部署。先修,再部署。

閘門:結論品質

觸發: 做出根因判定、最終診斷、或不可逆的建議。

動作: 說出結論之前,明確回答這四個問題:

  1. 數據來源? — 這個證據從哪來的?(log / DB / API / curl)
  2. 時間範圍? — 這是全部的數據還是最近的?(全量 / 最近 X 小時 / 重啟後)
  3. 樣本 vs 總量? — 你看了多少 vs 實際有多少?
  4. 還有其他可能嗎? — 還有什麼能解釋這個現象?

Read the full file on GitHub · 210 lines

Changes

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.

  1. 8d ago First seen · 210 lines · 284 tokens per session scan A edb354b7fe9c

Subscribe to this mod's changes

yes-zh is a skill published in the GitHub repository sstklen/yes.md (50 stars, last pushed 3mo ago), licensed MIT. It adds 284 tokens to every session and 3,412 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens