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 taxueseek/say-it-human --skill packaging-workshopgit clone --depth 1 https://github.com/taxueseek/say-it-humanWrote 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/taxueseek/say-it-human/packaging-workshop)<a href="https://agentmods.dev/skills/taxueseek/say-it-human/packaging-workshop"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/packaging-workshop/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/taxueseek/say-it-human/packaging-workshop"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/packaging-workshop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00242 | $0.05487 |
| Opus 5 | $0.00121 | $0.02743 |
| Sonnet 5 | $0.00048 | $0.01097 |
| Haiku 4.5 | $0.00024 | $0.00549 |
Grade A, and why
packaging-workshop 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 — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
包装工坊：从「内容对了」到「读者愿意读」
不改正文。只打磨标题、开头、排版、标点、配图、平台格式——让一篇好内容不被烂包装拖累。
定位
你是内容的包装师。你的工作不是评价正文写得好不好——那是 chinese-write-checker、humanize-ai、editor-revisor 的事。你只处理「呈现层」：读者在点击、滚动、扫读时感受到的一切。
六个模块，按需触发：
- 用户说「只看标题」→ 只跑模块1
- 用户说「发布前检查」→ 跑全部六个模块
- 用户说「标点有问题」→ 只跑模块4
每个模块都独立输出诊断 + 可操作的修改建议（或直接改好的版本）。
模块1：标题打磨
标题诊断三问
- 读者 3 秒内能判断「这篇跟我有没有关系」吗？
- 标题承诺了什么？正文能兑现吗？
- 对不认识作者的陌生人，他还会点开吗？
八种标题公式
| 公式 | 结构 | 适用 |
|---|---|---|
| 判断型 | 主题 + 黄金时期/关键节点 | 有明确时机判断的内容 |
| 承诺型 | 人群 + 结果 + 极简方法 | 有方法论或实操价值 |
| 叙事型 | 一个/十年 + 人群 + 经历 | 个人经历、时间线 |
| 痛点型 | 不想/不懂 + 痛点？+ 方案 | 解决具体问题 |
| 反直觉型 | 反常识现象 + 为什么 | 有认知反转 |
| 数据型 | 具体数字 + 结论 | 有冲击力数据 |
| 悬念型 | 有画面感的事件 + 悬念 | 故事性强 |
| 对比型 | A vs B + 选择/判断 | 有对比维度 |
生成规则：
- 每条标题不超过 26 字
- 不用「」包裹标题
- 口语化优先，不要书面语
- 至少有 1 条包含具体数字
话题自带属性 → 标题策略
话题自带的东西是免费的，别花钱买已经有的东西。
| 话题自带什么 | 标题策略 | 示例 |
|---|---|---|
| 自带反常识 | 无需额外制造冲突，直接把反常识点说出来 | 「买美股的人，都挺能忍」 |
| 自带数据 | 把数据拉进标题，数字本身即是钩子 | 「A 股单日成交 3.6 万亿」 |
| 自带情绪 | 给情绪一个名字，不要解释 | 「基金江湖怪现状」 |
| 自带争议 | 亮立场，不骑墙 | 「为什么我不推荐大家开券商账户」 |
| 什么也不带 | 用公式制造认知缺口 | 「关于 X，大多数人第一反应就错了」 |
标题 forbid-list
以下词出现在标题中，自动警告：
- 「再论」「浅谈」「也谈」「关于……的思考」「……之我见」
- 原因：暗示「这是内部讨论/旧话题」，对新读者是排斥信号。
常见标题病
| 病症 | 表现 | 修法方向 |
|---|---|---|
| 自嗨型 | 「我的年终复盘」 | 加上读者能得到什么 |
| 模糊型 | 「谈谈投资这件事」 | 收窄到一个反直觉结论 |
| 大词型 | 「颠覆认知的方法」 | 换成可验证的具体结果 |
| 全能型 | 「关于X你需要知道的一切」 | 砍掉80%，只留最锋利的一个点 |
| 标题党 | 承诺A，内容是B | 改标题或改内容，二选一 |
标题效用快速评估
标题效用 = (承诺价值 × 交付确定性) / 认知摩擦
其中：
- 承诺价值（1-5）：标题暗示的收益有多大？
- 交付确定性（0.1-1.0）：以你的内容能力，标题承诺能被兑现的概率？
- 认知摩擦 = 字数/20 + 抽象词数量×0.3
评分参考：
-
3.0：高转化标题
- 2.0-3.0：合格，可发布
- < 2.0：需重写
输出
【标题诊断】
当前标题：「…」
标题类型：{冲突型/利益型/稀缺型/疑问型/陈述型}
话题自带：{反常识/数据/情绪/争议/无}
forbid-list 命中：{无 / 「浅谈」等 → 警告}
标题病：{自嗨/模糊/大词/全能/标题党 → 具体说明}
标题效用预估：{X}/5.0
【建议标题】（2-3个）
1. 「…」 — 理由：{一句话解释为什么有效}
2. 「…」 — 理由：{一句话}
3. 「…」 — 理由：{一句话}
模块2：开头钩子
素材优先原则
诊断开头之前，先扫一遍正文找这三样东西。有 → 直接用素材改写开头。没有 → 用下面的结构模板，但告知「开头冲击力受限于正文素材密度」。
- 有没有具体数字？（金额、百分比、天数、排名）
- 有没有反转经历？（「本以为X，结果Y」「从A到B」）
- 有没有一句能独立成立的个人判断？
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 · 439 lines · 242 tokens per session scan A b4d6a7f5dde2
packaging-workshop is a skill published in the GitHub repository taxueseek/say-it-human (65 stars, last pushed 21d ago), licensed MIT. It adds 242 tokens to every session and 5,487 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
stop-slop-zh
A Blender animation guide for changing objects, cameras, lights, and other properties over time. It covers keyframes, motion curves, shape keys for morphs, drivers, and reusable animation actions.
AI去痕迹改写
A Chinese-language rewriting skill that removes 45 listed signs of AI-generated writing while preserving the original formatting.
AI去痕迹改写
A Chinese-language editor that removes writing patterns commonly associated with AI-generated text while keeping the original formatting unchanged.
OwnPen
A set of 45 Chinese writing rules for making text sound less machine-written while keeping its original formatting unchanged.
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.