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 Bwkyd/wps-skills --skill wps-proofreadgit clone --depth 1 https://github.com/Bwkyd/wps-skillsWrote 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/bwkyd/wps-skills/wps-proofread)<a href="https://agentmods.dev/skills/bwkyd/wps-skills/wps-proofread"><img src="https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-proofread/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/bwkyd/wps-skills/wps-proofread"><img src="https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-proofread.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 | $0.00099 | $0.01816 |
| Opus 5 | $0.00049 | $0.00908 |
| Sonnet 5 | $0.00020 | $0.00363 |
| Haiku 4.5 | $0.00010 | $0.00182 |
Grade A, and why
wps-proofread 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
中文文档校对工具
检查文档中的错别字、标点错误、敏感词和格式问题，提供分级修改建议。
When to Use
- 文档定稿前的校对检查
- 检查错别字和语病
- 检查标点符号规范性
- 公文/正式文件发布前审校
- 用户说"帮我校对""检查有没有错"
When NOT to Use
- 需要重写/润色内容 → 直接对话
- 格式兼容性问题 → 使用
wps-format-fix - 需要翻译 → 直接对话
检查维度
🔴 严重（Critical）— 必须修改
| 检查项 | 说明 | 示例 |
|---|---|---|
| 错别字 | 常见易混淆字词 | "既往不咎"写成"即往不咎" |
| 人名/地名错误 | 专有名词写错 | "国家主席"后的名字 |
| 数字错误 | 数据前后不一致 | 前文"100万"后文"10万" |
| 日期错误 | 日期逻辑不对 | "2月30日" |
| 敏感词 | 政治敏感/违禁表述 | 参照最新规范 |
🟡 重要（Important）— 建议修改
| 检查项 | 说明 | 示例 |
|---|---|---|
| 标点错误 | 全半角混用、误用 | 中文句号用了"."而不是"。" |
| 语病 | 搭配不当、成分残缺 | "提高了效率和质量的提升" |
| 重复表述 | 冗余重复 | "目前的当务之急" |
| 用词不当 | 场合不匹配 | 公文中用口语"搞一下" |
🔵 建议（Minor）— 可选优化
| 检查项 | 说明 | 示例 |
|---|---|---|
| 空格规范 | 中英文间空格 | "使用Python语言"→"使用 Python 语言" |
| 数字规范 | 中文数字vs阿拉伯数字 | 正式文件中数字的使用规则 |
| 一致性 | 同一事物不同表述 | "WPS"和"wps"混用 |
工作流程
Step 1: 读取文档内容
如果用户提供文件路径，读取文件内容。支持：
- .docx — 使用python-docx读取
- .txt — 直接读取
- 直接粘贴的文本
Step 2: 逐项检查
对文档内容进行全面检查，输出校对报告：
📝 校对报告
═══════════════════════════════════
文档：工作报告.docx
字数：3,456 字
检查时间：2026-03-22
🔴 严重问题 (2)
──────────────────────────────────
1. 第3段：「既使如此」→ 「即使如此」
原文："...既使如此，我们仍然..."
2. 第7段：金额不一致
第5段提到"预算100万元"，第7段变为"预算10万元"
🟡 重要问题 (5)
──────────────────────────────────
3. 第1段：全半角混用
「2026年3月,公司决定...」→ 「2026年3月，公司决定...」
4. 第2段：语病
「提高工作效率和质量的提升」→ 「提高工作效率和质量」
5. 第4段：重复表述
「目前的当务之急」→ 「当务之急」
6. 第6段：搭配不当
「解决需求」→ 「满足需求」
7. 第8段：口语化
「搞一个方案」→ 「制定一个方案」
🔵 优化建议 (3)
──────────────────────────────────
8. 全文："WPS"和"wps"混用，建议统一为"WPS"
9. 第2段：中英文之间建议加空格
10. 第5段：阿拉伯数字"3个"建议改为"三个"（正式文件）
═══════════════════════════════════
总计：10 个问题（严重2 / 重要5 / 建议3）
Step 3: 提供修改方案
对每个问题提供具体的修改建议，用户可选择：
- 全部接受 — 生成修改后的版本
- 逐条确认 — 逐个确认是否修改
- 仅查看 — 只看报告不修改
常见中文错误知识库
易混淆字词 TOP 30
| 错误 | 正确 | 区别 |
|---|---|---|
| 既使 | 即使 | "即"表假设，"既"表已经 |
| 费话 | 废话 | "废"=无用 |
| 按装 | 安装 | "安"=安置 |
| 一但 | 一旦 | "旦"=天明 |
| 暂新 | 崭新 | "崭"=鲜明 |
| 题纲 | 提纲 | "提"=提出 |
| 穿插 | 川流不息 | 用"川"不用"穿" |
| 美仑美奂 | 美轮美奂 | 用"轮"不用"仑" |
| 针贬 | 针砭 | "砭"=石针 |
| 震憾 | 震撼 | "撼"=摇动 |
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.
- 9d ago First seen · 191 lines · 99 tokens per session scan A bdb59f1d977a
wps-proofread is a skill published in the GitHub repository Bwkyd/wps-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 1,816 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
shortfilm-prompt
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…
simp
A relationship-advice skill that helps interpret signals, plan respectful approaches, and write sincere messages for someone you like.
chinese-write-checker
A Chinese-language review process for checking an article from an editor's, reader's, writer's, and publishing platform's viewpoints.
packaging-workshop
A final presentation review for finished Chinese content. It works on the title, opening, layout, punctuation, images, and platform format without changing the main body.
editor-revisor
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.
voice-dissolver
A writing-analysis skill that identifies the author's real voice before any rewriting. It marks distinctive passages to preserve and can ask questions to clarify the intended feeling, stance, and audience.