by zhaohui-yang · Codex Skill · ★ 99
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 99 |
| Forks | 12 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 50/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-19 |
| Created | 2026-03-15 |
| Platforms | codex, python |
| Est. Tokens | ~13k |
公文写作 Skill 一句话：把你的素材和要求交给 AI，让它按国家《党政机关公文格式》（GB/T 9704-2012）的规范，帮你起草报告、通知、请示、纪要等 22 种公文与正式材料，并可导出 Word。 零、快速上手：先对号入座 不确定从哪开始？先看你手上是什么工具，对号入座走一条路就行。三条路最终遵循的是同一套公文规范，区别只在「怎么把规则喂给 AI」。 先看你手上是什么工具，对号入座走对应一条路。三条路遵循同一套公文规范，区别只在「怎么把规则喂给 AI」。完整操作步骤见 二、使用。 现成提示词直达：报告 ／ 通知 ／ 请示 ／ 纪要（全部文种）；想先看完整效果就翻 样例/。成稿要 Word 时见 五、Word 导出与版式。 这个仓库里，哪些文件夹是给你用的？ 给「能装 skill 的工具」
Looking for a official-document-drafting alternative? If you're comparing official-document-drafting with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
去AI味 skill for Codex: a compact Chinese AI writing humanizer for AI味清理, template sentence shells, and fake eng
台灣正式文件撰寫 AI Skill：公文、存證信函、陳情書、合約 — 匯入 ChatGPT / Claude / Gemini 即可使用
中文去 AI 味与文采增强 Codex Skill，汲取 Mengke / 好事风格，让中文草稿更像人写。
A light-weight and straightforward workflow for spec-driven development with Claude Code and Codex. Written in
Docfork - Up-to-date docs for AI Coding Agents.
A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - imple
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: