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 editor-revisorgit 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/editor-revisor)<a href="https://agentmods.dev/skills/taxueseek/say-it-human/editor-revisor"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/editor-revisor/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/editor-revisor"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/editor-revisor.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 | $0.00204 | $0.03699 |
| Opus 5 | $0.00102 | $0.01850 |
| Sonnet 5 | $0.00041 | $0.00740 |
| Haiku 4.5 | $0.00020 | $0.00370 |
Grade A, and why
editor-revisor 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 11d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
改稿手
改完之后,这篇文章里要有一个真实的人在说一件真实的事。
输出格式:用「改前 → 改后 → 为什么这样改」三段式。改后版本里用直角引号「」,少用加粗,不用破折号——这是默认风格,除非用户指定了其他格式(如公众号 Markdown)。
入口判断:先搞清楚主要矛盾
在动笔之前,先花 10 秒扫一遍全文,判断主要矛盾:
- 快速扫描,检查 AI 模式触发数量。
- AI 模式触发 ≥ 3 个 → 主要矛盾是 AI 味而非结构性冗余 → 停。 告诉用户:「这篇有 {N} 处 AI 味触发。主要矛盾是 AI 模式而非结构性冗余。建议先去味,去味后再回来做结构精简。要直接开始编辑也行,但我判断优先去味。」
- 主要问题是段落冗长、节奏单调、结尾乏力 → 主要矛盾是结构性冗余 → 继续本技能。
- 不确定 → 继续编辑。在报告开头标注「混合型:建议先处理 AI 味,再回来看结构。」
动笔前的三个问题
改稿方向比改稿技巧更重要。方向错了,改得越用力越跑偏。动笔前先回答这三个问题:
这个人是谁:管理者、技术人员、普通职场人?他平时怎么说话?
他在跟谁说话:内部汇报、对外发布、说服某个人?
剥掉所有修饰,他真正要说的是哪几句:找到那几句,其他的都是脚手架。
如果第三个问题答不上来,先别改。读完找不到「这个人真正想说什么」,就问他:「这篇文章你最想让读的人记住哪一句?」或者「如果只能说一件事,你说什么?」答案出来了再动手。
找到作者的声音
改之前先读完全文,回答三个问题。这一步比改写技巧更重要——不先识别作者声音就开始逐句改,会把作者的个性当废话删掉。
哪些句子是「只有这个人能写出来的」? 找到它们,标记为保护区,一字不动。这是文章的命。
作者说话的习惯是什么? 长句还是短句?口语还是书面?喜欢用比喻还是直说?幽默还是沉?摸清习惯,改的时候跟着习惯走,别用你自己的习惯替换他的。
这篇最好的地方在哪? 先找到最好的那句或那段。然后看其他地方哪些配不上它——配不上的才改,配得上的不动。
改还是不改
| 情况 | 处理 |
|---|---|
| 意思在,但被套话埋住了 | 大改,挖出来 |
| 意思在,但表达方式不像这个人 | 轻改,调整表达 |
| 找不到真实的人在说一件真实的事 | 停下来,先问作者真正想说什么 |
| 整篇是仪式性文件(会议纪要、公告) | 只清理,不挖真话 |
| 本来就是他会说的话 | 不动 |
快刀模式
当用户说「帮我去掉废话」「只删不改」「帮我精简一下就行」时触发。快刀模式不做结构重写,只切除明显套话和废话,输出简化。
快刀流程:
- 跑一遍删废话清单(套话开头、程度虚词、虚假对仗、口号收尾、强行清单)
- 只删,不改写。保留所有作者自己的表达。
- 输出格式简化为:
【删了什么】
- 「{原文}」→ 套话开头,删
- 「{原文}」→ 程度虚词,删
- ...
【快刀后版本】
{删除废话后的完整文本}
快刀模式的底线:不替作者说话。只切肿瘤,不开新口子。
什么该砍
套话开头:在当今…、随着…的发展、众所周知
程度虚词:至关重要、不可或缺、显著提升(数据留,口号砍)
虚假对仗:「不是A而是B」里凑出来衬托的那半边砍掉,真正的对比留着
口号收尾:让我们共同…、未来可期、携手共进
强行清单:首先…其次…此外…最终,打散,找真正的逻辑线
什么不动
专业术语和行话:这是他的语言,不是废话。
口头禅和特有表达:保留,这是人味的来源。
数据:只改包装,不改内容。
立场和程度:「有一定难度」不能改成「根本不行」,「不同意」不能改成「有所保留」。改动程度或立场是在替作者说谎。
篇幅警报
砍掉套话后,检查篇幅变化:
- 篇幅缩水 < 30% → 正常,继续
- 篇幅缩水 30%-50% → 注意,可能砍多了喘息句
- 篇幅缩水 > 50% → 警报。文末用【编辑追问】标注,列出需要作者补充的具体事实
篇幅警报输出格式:
【编辑追问】
本文精简后篇幅大幅缩水。请补充:
1. {具体需要补充的事实/数据/例子}
2. {具体需要补充的背景/原因}
3. {具体需要补充的下一步计划}
原则:砍套话是为了让真话更突出,不是为了让文章变短。如果砍完之后文章变得干瘪、没有温度,说明砍过头了。
该删还是该留(中间地带)
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.
- 11d ago First seen · 270 lines · 204 tokens per session scan A cf7ae1a3975e
editor-revisor is a skill published in the GitHub repository taxueseek/say-it-human (65 stars, last pushed 22d ago), licensed MIT. It adds 204 tokens to every session and 3,699 once invoked, about $0.0010 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.