No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by luoling8192 · Codex Skill · ★ 208
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is technical-writing safe to install? View the security audit →
technical-writing 中文内部技术写作的 agent skill。约束设计文档、评审稿、postmortem、分享稿等场景的语气、句法、结构，让产出贴近技术汇报，避开营销稿和散文气质。 适用场景 写内部技术方案、设计说明、评审文档、分享稿 改一篇文风过满、结论过快、证据不足的技术文章 把聊天记录、讨论结论整理成可传播的技术文档 解释代码、模块边界、架构演进、可观测性、评测方法 不适用：UI 文案、产品营销稿、面向外部用户的帮助文档、机械 API reference。 安装 通过 skills.sh 一行装，自动检测当前 agent 并写入对应目录： 支持 Claude Code、Cursor、Codex、GitHub Copilot、Windsurf、Gemini、Cline、AMP 等主流 agent runtime。装完在对应 agent 里用 Skill 工具调用 即可，也可以在项目的 CLAUDE.md / AGENTS.md 里把它列为常用 skill。 手动安装（fallback） 如果不想用 skills.sh，可以直接 clone 后软链接： OpenAI Codex 用户可参考 ，按 Codex 文档注册到本地。 核心约束 先观察，再归纳，再判断，不抢结论 中文里不用破折号 和英文连字符 做分句 中文引号统一用 不要黑话连篇（完整词表见 SKILL.md 的 Buzzword Blocklist） 不写抢结论的词、空评价词、对立句法、过场句、英文翻译腔 结构信息直接用 list，论证顺序用 长文主线：背景 → 拆解现状 → 提出猜想 → 分节解答 → 回指前文 → 影响面 → 可观测性 / eval → 收束 完整规则、改写示例、Few-Shot 修正案例见 。 Credits 灵感和反馈来自 @nekomeowww。 License MIT
| Stars | 208 |
| Forks | 11 |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 57.1848990422531/100 |
| Last Updated | 2026-05-27 |
| Created | 2026-05-15 |
| Platforms | claude-code, codex |
| Est. Tokens | ~1k |
Looking for a technical-writing alternative? If you're comparing technical-writing 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.
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured sectio
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
This repository contains documentation created to better understand the open project
Frontend design skill for Claude Code, Codex, and Gemini CLI. Eight aesthetic anchors, each locking palette, t
Complete Kaggle integration plugin/skill for AI coding agents — competition reports, dataset/model downloads,
Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control
Explore other popular codex skill tools:
technical-writing is 中文内部技术写作的 agent skill，约束设计文档 / 评审稿 / postmortem / 分享稿场景的语气、句法、结构. It is categorized as a Codex Skill with 208 GitHub stars.
You can find installation instructions and usage details in the technical-writing GitHub repository at github.com/luoling8192/technical-writing. The project has 208 stars and 11 forks, indicating an active community.
technical-writing is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to technical-writing on Agent Skills Hub include jdocmunch-mcp, compose-skill, open-docs. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: