editor-revisor

editor-revisor is a skill for Claude Code, Codex from taxueseek/say-it-human. It costs 204 tokens per session (3,699 once invoked), scanned A, original, MIT.

A Chinese-language editing assistant that finds unnecessary words, formulaic openings, forced parallel phrasing, and slogan-like endings. It offers a deletion-focused mode and a fuller rewriting mode for any draft.

In plain words
What is it for?
Use it to shorten Chinese drafts, remove filler, make writing sound more natural, improve flow, or rewrite text while protecting selected phrases.
Why use it?
It helps preserve the writer’s real meaning and voice when a draft feels wordy, artificial, or unlike the person who wrote it. It also tells the writer what it changed and why.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to shorten Chinese drafts, remove filler, make writing sound more natural, improve flow, or rewrite text while protecting selected phrases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/taxueseek/say-it-human/editor-revisor
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 taxueseek/say-it-human --skill editor-revisor
Clone the repo
git clone --depth 1 https://github.com/taxueseek/say-it-human

Made for: Claude Code, Codex.

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 editor-revisor

README.md
[![agentmods](https://agentmods.dev/badge/skills/taxueseek/say-it-human/editor-revisor/github.svg)](https://agentmods.dev/skills/taxueseek/say-it-human/editor-revisor)
Your own site
<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.

agentmods 80×15 button for editor-revisor

Your own site · 80×15
<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>
Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00204 $0.03699
Opus 5 $0.00102 $0.01850
Sonnet 5 $0.00041 $0.00740
Haiku 4.5 $0.00020 $0.00370

Measured 11d ago against content hash cf7ae1a3975e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/editor-revisor/SKILL.md · 270 lines

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:

  1. 快速扫描,检查 AI 模式触发数量。
  2. 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。」
  3. 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。
  4. 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

  1. 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)
  2. 只删,不改写。保留所有作者自己的表达。
  3. 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)

Read the full file on GitHub · 270 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. 11d ago First seen · 270 lines · 204 tokens per session scan A cf7ae1a3975e

Subscribe to this mod's changes

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.