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 TashanGKD/tashan-writing-system --skill article-proofreadinggit clone --depth 1 https://github.com/TashanGKD/tashan-writing-systemWrote 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/tashangkd/tashan-writing-system/article-proofreading)<a href="https://agentmods.dev/skills/tashangkd/tashan-writing-system/article-proofreading"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-writing-system/article-proofreading/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/tashangkd/tashan-writing-system/article-proofreading"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-writing-system/article-proofreading.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 | $0.00080 | $0.03951 |
| Opus 5 | $0.00040 | $0.01975 |
| Sonnet 5 | $0.00016 | $0.00790 |
| Haiku 4.5 | $0.00008 | $0.00395 |
Grade A, and why
article-proofreading 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.
This is a copy
86% identical to smart-search — 393 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文章审稿 Skill
基于郑总历次亲手修改、明确批注的审稿标准。五轮检查,每轮独立列问题清单,最后给出优先级。
参考文档:_内部总控/AI思维碎片/写作习惯与风格手册.md
知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| D0 认知根(必读) | _内部总控/AI思维碎片/写作习惯与风格手册.md |
郑总审稿标准的完整来源:AI腔定义/标题4种错误/绝对表达清单/结语要求(本 Skill 的知识根) |
| D3 规范参考 | — | 本 Skill 本身就是规范定义,无需外部规范参考 |
| D4 运行时数据 | 目标文章草稿(用户提供) | 被审稿的文章(审查对象) |
核心概念速查: ① AI腔 = 「此外」「总之」「值得注意的是」「不仅如此」「综上所述」等AI写作套话 ② 标题4种错误 = 过度承诺/空泛标题/AI腔标题/不够具体 ③ 审稿顺序不变:AI腔→标题→绝对表达→结构层次→结语,五轮独立,不合并
第一轮:AI腔检测
1.1 翻译感词汇
逐句扫描,标记所有让人感觉是从英文直译的词:
| 常见AI腔词 | 改法 |
|---|---|
| 人层 | 人类层 |
| 工具层(指代"人"所在的层次时) | 视语境调整 |
| 首先/其次/最后 作为枚举句式 | 直接说内容,不用序数铺垫 |
判断原则:读出声来感觉别扭、或是翻译腔的,就标记。
1.2 元评论过渡句(零信息量的宣告)
❌ 直接删除下列句式,不要任何替换,直接说内容:
- "核心推论只有一句话:"
- "这张表说明一件事:"
- "有以下几点值得关注:"
- "这里有X条标准……"
- "值得注意的是,"
- "总的来说,"(在段落中间出现时)
- "不难发现,"
✅ 替换方式:删掉这句话,下一句直接用"所以,""因此,"开头,或无连接词直接开始。
为什么是AI腔:这类句子是在"宣告接下来要说什么",本身没有任何信息量。真正有力的表达直接说出内容,不需要预热。
1.3 防守性修饰(替读者预设反驳)
❌ 检查并删除以下模式:
- "这不是X,而是Y"——当Y是在为自己的判断辩护时
- "这不是未来的预测,而是正在发生的结果"
- "很多人可能会认为……但实际上……"(不必要的假想敌)
- "这一点很重要"(让读者评判,不要自己标注)
- "不可否认……但……"
✅ 正确做法:直接陈述结论,不加防守。读者自会判断。
例外:"不是X,而是Y" 用于积极的对比陈述(如"不是界面做简洁,而是设计路径的根本颠倒")可以保留——区分在于它是断言,不是辩护。
1.4 "这里有" 套话
❌ 删除:
- "这里有一条核心原则……"
- "这里有五条判断标准……"
- "接下来我们来看……"
✅ 直接进入实质内容。
第二轮:标题质量(四种错误类型)
对每个章节/小节标题,依次用四个问题判断:
2.1 是结论,还是话题/方法描述?
检测:标题能否独立表达一个观点?还是只在描述"这节讲什么"?
❌ 错误例:产品机会的来源:三类永恒坐标 × AI 带来的成本变化
→ 说的是"我用什么框架分析",不是"分析得出什么"
✅ 正确例:旧瓶颈正在消失,把它们做好是把错的做对
→ 表达一个判断,读者读到标题就知道该相信什么
识别错误标题的特征:
- "X 的来源:A × B"(描述分析框架)
- "X 的结构:A、B、C"(描述内容组成)
- "X 的维度/原则/方法"(描述分类方式)
2.2 是机制,还是本质/原则?
检测:标题里有"设计/使用/实现/建立/优化"等动词 → 往往是机制描述,不是结论。
❌ 错误例:为人与智能体同时设计两层界面
→ 说的是"如何做"(机制)
✅ 正确例:产品设计的第一性原理:Human-Readable + Agent-Operable
→ 说的是"这个机制揭示了什么设计原则"(本质)
改法:把"如何做"升级为"这样做意味着什么、揭示了什么"。
2.3 是定性,还是从定性推出的原则?
检测:标题只是给某个概念贴了一个标签(定性),而没有给出从这个定性推导出的行动原则。
❌ 错误例:产品的本质变了:人与其数字员工协作的介质
→ "介质"是定性(说"是什么"),信息量低
✅ 正确例:产品设计的第一性原理:Human-Readable + Agent-Operable
→ 从"介质"这个定性推出的设计原则,信息量更高
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 · 344 lines · 80 tokens per session scan A 1a1689e6a3a5
article-proofreading is a skill published in the GitHub repository TashanGKD/tashan-writing-system (2 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 3,951 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to smart-search, differing in 393 lines, and is treated as a copy.
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…