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 scene-fitgit 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/scene-fit)<a href="https://agentmods.dev/skills/taxueseek/say-it-human/scene-fit"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/scene-fit/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/scene-fit"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/scene-fit.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 | $0.00155 | $0.01655 |
| Opus 5 | $0.00077 | $0.00827 |
| Sonnet 5 | $0.00031 | $0.00331 |
| Haiku 4.5 | $0.00015 | $0.00166 |
Grade A, and why
scene-fit 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 13d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
场景对位
不是改写得好不好，是改写得对不对——对不对这个平台、这个渠道、这个场景。
五种场景
技术文档
核心就一条：准确先于修辞，清晰先于热闹。
一个段落只说一个信息点。一个句子只说一个主干。不动代码、URL、API路径。先检查目标项目自己的 AGENTS.md 和术语表，别机械替换。
不同内容的开头回答不同问题：
- 入口页/介绍页 → 覆盖什么、适合谁、从哪里开始读
- API文档 → 方法/路径/参数类型+单位+默认值+限制
- 界面文案 → 按钮说明动作+目标，错误提示说明影响+恢复
- 操作手册 → 前置条件+步骤+失败处理+恢复方式
禁用词：赋能、抓手、闭环、沉淀、对齐、对标、拉通、打通、洞察、赛道、调性、战役、势能、兜底、落盘、收口、透传。这些词掩盖实际动作，直接说实际指什么。
广告文案
核心框架是AIDA：注意→兴趣→欲望→行动。
八种标题写法：
- 判断型：主题+关键节点。比如"2026年，资产配置的分水岭"
- 承诺型：人群+结果+方法。比如"新手也能跑赢通胀的3个策略"
- 叙事型：一个/十年+人群+经历。比如"一个散户的十年"
- 痛点型：不想/不懂+痛点+方案。比如"不想再被割韭菜？先看这个"
- 反直觉型：反常识+为什么。比如"买基金的人，都挺能忍"
- 数据型：具体数字+结论。比如"A股单日成交3.6万亿"
- 悬念型：有画面感的事件+悬念。比如"那个凌晨三点还在看K线的人"
- 对比型：A vs B+选择。比如"定投三年vs追涨杀跌"
标题禁用：再论、浅谈、也谈、关于……的思考、……之这些词暗示"这是内部讨论/旧话题"，对新读者是排斥信号。
正文结构：开头3秒制造好奇或共鸣，中段用数据/故事/类比做价值证明，结尾用明确动词+低门槛做行动号召。
CTA对比：
- ✅ "好了，去试试" / "看完就删掉购物车"
- ❌ "立即升级" / "未来可期"
PPT演示
核心原则：一页一论点。每页只有一个核心信息。
视觉层次：一个主色占60-70%，1-2个辅色，一个强调色。别把所有颜色等分。
三明治结构：深色标题+浅色内容+深色结尾。或者全暗色调走到底，别半暗半亮。
能用图就不用表，能用表就别堆文字。每页不超过6行，每行不超过20字。
配色参考：
- 商务汇报 → 藏青+冰蓝+白
- 创业融资 → 深绿+苔藓灰+米白
- 产品发布 → 珊瑚红+金色+藏青
- 技术分享 → 炭灰+白炭+纯黑
演讲者备注：每页不超过50字，写"念什么"不写"说什么"，标注翻页时机。
社交媒体
不同平台的内容逻辑完全不同：
小红书：标题不超过20字，关键词前置。正文300-800字，善用emoji做段落标记。开头直接亮痛点，中间干货密集，结尾引导互动。
公众号：标题15-30字，引发好奇或共鸣。开头3句定生死。结尾留余味或行动指引。
知乎：标题用疑问句，带长尾关键词。内容要有逻辑深度，不套路。
抖音：前3秒必须抓住注意力。每句话都要推动情绪。强烈口语化，适合配音。
即刻：短句+话题标签。洞见、吐槽、互动。别长篇大论。
各平台的语气也有差异：小红书像朋友聊天，公众号真诚有判断，知乎专业有逻辑，抖音强烈口语化，即刻洞见吐槽。
Release Notes
核心：用户可见的变化导向，从git log提取，不从记忆写。
结构模板：
## Breaking Changes
## New Features
## Fixes & Improvements
## Deprecations
规则：
- 按用户可见特征分组，不按内部功能分组。"启动更快了" 不叫 "性能优化"
- 从git log提取，读feat:/fix:提交。不从记忆写
- 一条只说一个变化。不堆砌
- 双语项目：英文块和中文块并列，不逐条混写
禁用："Polish" / "细节打磨" / "Misc improvements" — 用户看不懂。
与其他技能的协作
包装工坊处理完之后，可选做场景适配再发布：
packaging-workshop（包装工坊） → scene-fit（场景适配，可选） → 发布
典型用法：
- "这篇适合发小红书" → 小红书适配
- "帮我改成技术文档格式" → 技术文档适配
- "写个产品发布的PPT" → PPT适配
- "从git log生成Release Notes" → Release Notes适配
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 153 lines · 155 tokens per session scan A 04f0c63687ec
scene-fit is a skill published in the GitHub repository taxueseek/say-it-human (65 stars, last pushed 24d ago), licensed MIT. It adds 155 tokens to every session and 1,655 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 2026-08-30.
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-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.