agentmods.dev

wps-gongwen

wps-gongwen is a skill for Claude Code from Bwkyd/wps-skills. It costs 82 tokens per session (3,799 once invoked), scanned A, original, MIT.

A Chinese government-document formatter for creating .docx files according to GB/T 9704-2012, a Chinese national standard for official document layout. It handles formats such as red-header documents.

In plain words
What is it for?
Use it for notices, requests for approval, replies, reports, letters, meeting minutes, decisions, and similar government or administrative documents.
Why use it?
It removes the guesswork from official document structure and page layout. It helps keep documents consistent with the required standard.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

not rated 11repo 6mo ago A scan 82 tokens original MIT

Good fit Use it for notices, requests for approval, replies, reports, letters, meeting minutes, decisions, and similar government or administrative documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bwkyd/wps-skills/wps-gongwen
View source ↗ Bwkyd/wps-skills
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 Bwkyd/wps-skills --skill wps-gongwen
Clone the repo
git clone --depth 1 https://github.com/Bwkyd/wps-skills

Made for: Claude Code.

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 wps-gongwen

README.md
[![agentmods](https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-gongwen/github.svg)](https://agentmods.dev/skills/bwkyd/wps-skills/wps-gongwen)
Your own site
<a href="https://agentmods.dev/skills/bwkyd/wps-skills/wps-gongwen"><img src="https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-gongwen/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 wps-gongwen

Your own site · 80×15
<a href="https://agentmods.dev/skills/bwkyd/wps-skills/wps-gongwen"><img src="https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-gongwen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,799 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.
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 $0.00082 $0.03799
Opus 5.5 $0.00033 $0.01520
Sonnet 5.5 $0.00016 $0.00760
Haiku 4.5 $0.00008 $0.00380

Measured 2mo ago against content hash a8a3f38126f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wps-gongwen 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 2mo 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/wps-gongwen/SKILL.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

公文写作排版助手

按 GB/T 9704-2012《党政机关公文格式》 标准，自动生成规范公文 .docx 文件。

When to Use

  • 用户需要撰写党政机关公文（通知、请示、批复、报告等）
  • 用户需要生成红头文件
  • 用户需要按国标格式排版企业行政公文
  • 用户说"帮我写一份XX通知/请示/批复/报告"

When NOT to Use

  • 普通Word文档（非公文格式）→ 使用 docx-writer
  • 仅需要公文内容不需要格式 → 直接撰写即可
  • WPS宏脚本开发 → 使用 jsa-macro

公文文种速查

文种 适用场景 行文方向
通知 发布规章、转发公文、安排工作 下行
通报 表彰先进、批评错误、传达情况 下行
请示 请求上级批准或指示 上行
报告 向上级汇报工作、反映情况 上行
批复 答复下级请示 下行
函 平级或不相隶属单位间商洽 平行
纪要 记载会议主要情况和议定事项 —
决定 对重要事项作出决策和部署 下行
意见 对重要问题提出见解和处理办法 多向
命令(令) 公布规章、嘉奖有功人员 下行
公告 向国内外宣布重要事项 下行
通告 在一定范围内公布应当遵守事项 下行
议案 提请审议事项 上行
决议 经会议讨论通过的重大决策事项 下行
公报 公开发布重要决定或重大事件 下行

工作流程

Step 1: 确认要素

向用户确认以下公文要素（未提供的合理推断或询问）：

必填要素：

  • 文种：通知/请示/批复/报告/函/纪要/决定/意见 等
  • 发文机关：发文单位名称
  • 主题/事由：公文的核心内容
  • 主送机关：收文单位

可选要素（有则填写）：

  • 发文字号：如"X办发〔2026〕1号"
  • 密级/紧急程度：如"机密""特急"
  • 抄送机关：需知悉的其他单位
  • 附件：附件标题列表
  • 签发人：上行文必须标注

Step 2: 撰写公文内容

根据文种特点撰写内容，遵循以下原则：

语言规范：

  • 使用书面语，语气庄重
  • 避免口语化表达
  • 用语准确规范，不产生歧义
  • 人称使用"本机关/本单位"，不用"我们"

结构规范：

  • 通知：依据→事项→要求→执行期限
  • 请示：缘由→事项→请求语（"妥否，请批复"）
  • 报告：报告缘由→主体内容→结尾（"特此报告"）
  • 函：去函事由→具体事项→希望或要求
  • 纪要：会议概况→议定事项（逐条列出）

成文日期：

  • 使用阿拉伯数字标注完整年月日，如"2026年3月22日"
  • 联合行文以最后签发日期为准

Step 3: 生成 .docx 文件

使用 python-docx 生成标准格式公文文件。

先确保依赖已安装：

pip install python-docx 2>/dev/null || pip3 install python-docx 2>/dev/null

生成脚本必须严格遵循以下格式标准：

页面设置
纸张：A4 (210mm × 297mm)
上边距：37mm（上行文为37mm）
下边距：35mm
左边距：28mm
右边距：26mm
页码：外侧，4号半角阿拉伯数字
版头区域（红头）
份号（如有）：顶格，3号阿拉伯数字
密级和保密期限（如有）：3号黑体
紧急程度（如有）：3号黑体
发文机关标志：红色（小标宋体/黑体），上边缘至版心上边缘 35mm
                字号根据机关名称长度调整，推荐使用上22下20区间
发文字号：3号仿宋，居中（联合行文居中）
签发人（上行文）：3号仿宋，"签发人："后标3号楷体人名
分隔线：红色，上距发文字号4mm
主体区域
标题：2号方正小标宋（备选华文中宋），居中，行距固定值28.95pt
      可分一行或多行排列，回行时做到词意完整
主送机关：3号仿宋，顶格，回行时顶格
正文：3号仿宋_GB2312，首行缩进2字符
      行距：固定值28.95pt
      每面排22行，每行排28个字
结构层次序号：
  第一层 "一、"   黑体
  第二层 "（一）" 楷体
  第三层 "1."    仿宋
  第四层 "（1）"  仿宋
附件说明：正文下一行，左空2字，3号仿宋
          "附件：1. XXXXX"

Read the full file on GitHub · 367 lines

Files

What ships with it

2 files 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.

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. 2mo ago First seen · 367 lines · 82 tokens per session scan A a8a3f38126f8

Subscribe to this mod's changes

wps-gongwen is a skill published in the GitHub repository Bwkyd/wps-skills (11 stars, last pushed 6mo ago), licensed MIT. It adds 82 tokens to every session and 3,799 once invoked, about $0.0003 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 2026-08-31.

Claude CodeDocumentschineseclaude-skillsdocxoffice-automation
Related

wps-gongwen compared with skills from other repositories

wps-gongwen next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
wps-gongwenBwkyd/wps-skillsSkill116mo agoMITA82Claude Code
mqc-chronicle-masterMiaoQichuan/new-litigation-visualizationSkill14510d agoAGPL-3.0A88Claude Code
experiment-report-skilllyzbcy/experiment-report-skillSkill139d agoMITA65Claude Code, Codex
法律文件脱敏处理moyupeng0422/legal-doc-redactorSkill1377mo agoMITA128Claude Code, Codex
docx-template-translatorzouchenzhen/docx-template-translator-skillSkill805mo agoApache-2.0A87Codex
docxlingxling/awesome-skills-cnSkill3291mo agoMITA184Claude Code
note-organizerRenakoni/note-organizerSkill174mo agoMITA228Claude Code, Codex