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 0fuk/OpenACCP --skill cn-prosegit clone --depth 1 https://github.com/0fuk/OpenACCPWrote 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/0fuk/openaccp/cn-prose)<a href="https://agentmods.dev/skills/0fuk/openaccp/cn-prose"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/cn-prose/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/0fuk/openaccp/cn-prose"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/cn-prose.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 | $0.00132 | $0.02052 |
| Opus 5.5 | $0.00053 | $0.00821 |
| Sonnet 5.5 | $0.00026 | $0.00410 |
| Haiku 4.5 | $0.00013 | $0.00205 |
Grade A, and why
cn-prose 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 2d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cn-prose — 书面中文,删出来的
一份对外文档被同一位读者打回三轮,病都一样:AI 味、口水话、为了「说人话」丢了专业度、每个版式槽都塞东西、没有决策价值的信息占着位置。原因不是不会写,是写完就交,没有删减轮,而且「说人话」被执行成了「口语化」。本 skill 把这些变成能机械执行的判据。零项目词,任何中文书面产物通用。
0 · 先定读者,再动笔
一句话写下:谁读、读完做什么决定。此后每一句话都过同一道题:「这句会改变读者的动作或判断吗?」不会 → 删。读者是外部人(总部、客户、投资人、门店)时,内部过程、依赖、前提、未做清单、时间起点一律不进正文。
1 · 五病与判据(逐条可机械判)
| 病 | 长什么样 | 判据(命中即改) |
|---|---|---|
| AI 味 | 每句配一个理由从句;冒号式双段标题「做了什么,接下来做什么」;三段排比;比喻(「交给系统」「接上」「护航」);「不是 X 而是 Y」 | 去掉后半句仍成立 → 后半句删;标题里有冒号或破折号 → 改成一个判断句;连续三个同结构短语 → 留一个 |
| 口水话 | 「好了」「看不懂」「算错了」「不认口头说」「像人一样」;感叹号;「请」堆叠;劝告语气 | 正式文体只用名词短语 + 动宾;引号里的口语一律去引号改陈述;感叹号全删 |
| 失专业度 | 把术语翻成模糊话(「钱的事」「弄好了」);删掉了数字、口径、时间粒度 | 每个业务事实保留三要素:对象 + 动作 + 数量/时点;说人话 = 白话公文,不是聊天 |
| eyebrows 与槽位废话 | 副题、右上注、页脚灰框、前提条、「已明确的只有」——因为版式有这个位置就填一句 | 每个槽问「不填会怎样」,答不出 → 删槽(不是换句话填);副题只许一句且可空;右注只放数字或日期 |
| 无意义信息占位 | 「规范与图纸已备齐」「号段已预留」「工作区已建好」「共同前提 X」「已定不做 Y」 | 过 §0 读者题;内部工程事实对外一律删;留下的必须能被读者验证或行动 |
补充四条,同样机械:
- 数字只出现一次:标题里有的数,大数字区不再放;同一页同一数不重复。
- 不写过程时间句:「自 X 日起」「X 日才定稿」「X 日写成规范」会引出反问「之前呢」;对外只给结果与排期。
- 承诺与保留分开:「预计」「需审批」这类保留统一放一处(图注或页脚),不混进里程碑正文。
- 标点与空格一致:全角标点;阿拉伯数字;数字与中文单位之间的空格全文一种写法;金额千分位;版本号与日期格式全文一种。
2 · 三种场景的文体表
| 场景 | 标题 | 正文 | 该避免 |
|---|---|---|---|
| 汇报 / 报告(PDF、长文) | 一个判断,≤ 16 字,不用冒号 | 结论先行;一段一事;句长 ≤ 25 字;每段末尾不总结 | 「综上」「值得注意的是」「本质上」;段首「首先/其次」;结尾展望 |
| deck / PPT | 每页一句判断 = 标题;标题读完即知本页结论 | 每页 ≤ 5 条,每条 ≤ 12 字;数字配单位;图表标题写结论不写「X 趋势图」 | 副标题解释标题;项目符号里套句子;一页两主题;装饰性图标 |
| 网站 / app / SaaS 界面 | 按钮 = 动词 + 名词;页面标题 = 名词短语 | 报错 = 发生了什么 + 怎么办;toast 命名对象,无「成功」无句号;空态 = 一句为什么 + 一个动作;进行中用「…中」 | 「确定 / OK」;「操作成功!」;「暂无数据」;营销腔与夸张副词;用中文数字 |
| 营销与落地页:一屏一个主张;主张是可验证的事实,不是形容词;证据(数字、客户、截图)紧跟主张;删掉所有「极致」「赋能」「一站式」。 |
3 · 黑名单(命中即删或换)
- 词:本质上、从某种意义上、这意味着、赋能、抓手、闭环、沉淀、打通、对齐、落地、链路、极致、一站式、全方位、护航、深度、助力、拥抱。
- 句式:不是 X 而是 Y;不仅 X 更 Y;让我们…;接下来我将…;首先需要指出;X,Y,Z 三段排比;冒号式双段标题;破折号解释。
- 标点:感叹号;正式文体里的引号口语;省略号表情绪;全半角混用。
- 版式:为对称而加的第二列;为填白而加的说明句;图注写「如图所示」。
4 · 删减轮(交付前必做,输出一行记录)
写完 ≠ 完成。按顺序跑一遍,每条记「删了几处」:
- 读者题:逐段问「改变读者动作吗」,不改 → 删。
- 槽位题:逐槽问「不填会怎样」,答不出 → 删槽。
- 半句题:每句去掉后半句还成立 → 删后半句。
- 重复题:同一数、同一事、同一结论出现第二次 → 删第二次。
- 过程题:时间起点句、内部依赖句、未做清单 → 对外删。
- 黑名单扫描(§3)+ 标点空格扫描(§1 末条)。
- 读一遍标题链:只看标题能否讲完整个故事;不能 → 改标题,不加正文。
记录格式:
删减轮:读者 n / 槽位 n / 半句 n / 重复 n / 过程 n / 黑名单 n。n 全为 0 的初稿几乎不存在,全 0 = 没跑。
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.
- 2d ago First seen · 63 lines · 132 tokens per session scan A e6af5890ea6a
cn-prose is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 2,052 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
handoff-mesh
Built-in communication layer for multi-agent setups. Full-mesh handoff folders (any agent can hand off to any other), an hourly watcher that surfaces open handoffs, weekly archive cleanup, and a completion-reporting loop so every handoff is handled AND verified. The durable 'brain' counterpart to real-time channels…
agent-teams
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
orchestrate
This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.
silicon-steward
A planning guide for coordinating work between a person and a coding agent. It turns required information, resources, feedback, actions, and handoffs into explicit checklists and protocols.
coordinate-recover
Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.
coordinate-setup
Discover or configure implementation agents for Coordinate Agents when setting up or changing its agent configuration.