xiaoma-durex-copywriter — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 crawfordxx · Claude Skill · ★ 574

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is xiaoma-durex-copywriter safe to install? View the security audit →

About xiaoma-durex-copywriter

xiaoma-durex-copywriter 一个 Claude Code / Claude.ai Skill。用杜蕾斯黄金期(2011–2017,环时互动操盘)那套「双层语义 + 留白」的方法,产出文案与海报。 这套方法能迁移的东西,是一套制造「我懂了」瞬间的机制。污只是杜蕾斯所在品类的表层材料,把材料换成 AI 课程、职场、理财、健身,机制照样成立。 双层语义 一句合格的杜蕾斯式文案,必须同时成立于两个语境。 作者只写表层,里层由读者自己跳过去。那一下跳跃产生的快感,就是传播动力。 光大银行出乌龙那天,杜蕾斯发的是「光大是不行的」。刘翔摔倒那次,它把「快」和「持久」摆到一起,表层说的是运动员。中元节它只说了四个字,「今晚早回家」。 点破即死是铁律。 只要在文案里解释了里层,这条就废了。 它会做什么 Skill 触发后走一条交互式流程,不会闷头给你一版就完事。 为什么默认不提问。 模型天然倾向多问,而每轮提问都在消耗用户耐心。用户找你是要东西的,不是来做问卷的。一个带明示假设的具体方案,比三个精准的问题更有用,因为用户看到具体的东西才知道自己想要什么。方案本身就是最好的提问方式。 这条是跑评测跑出来的。第一轮测试里 Skill 只缺一个槽位也照样停下来提问,还自己发明了四个槽位之外的新问题。详见 。 安装 Claude Code 下次启动即可用。触发词:「写个文案」「借势热点」「节日海报」「想句 slogan」「课程怎么推」「像杜蕾斯那样写」。 出图部分按需安装。 bash npm i @napi-rs/canvas # Canvas 排版 pip install playwright # HTML 排版(二选一即可)

advertisingchinese-copywritingclaude-codeclaude-skillcopywritingposter-design

Quick Facts

Stars574
Forks25
LanguagePython
CategoryClaude Skill
Quality Score61.4864017444321/100
Open Issues1
Last Updated2026-08-08
Created2026-08-04
Platformsclaude-code, python
Est. Tokens~15k

Compatible Skills

These tools work well together with xiaoma-durex-copywriter for enhanced workflows:

  • skills — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)

xiaoma-durex-copywriter alternative? Top 6 similar tools

Looking for a xiaoma-durex-copywriter alternative? If you're comparing xiaoma-durex-copywriter with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • guizang-yingzao-skill by op7418 · ⭐ 451

    🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-direct

  • humanizer-ru by ilyautov · ⭐ 365

    humanizer-ru: очеловечить русский AI-текст для Claude Code, Cursor, Codex и других AI-агентов. 64 признака ней

  • creative-director-skill by smixs · ⭐ 203

    World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociatio

  • ai-marketing-claude by zubair-trabzada · ⭐ 2.3k

    AI Marketing Suite for Claude Code. 15 marketing skills with parallel subagents — audit any website, generate

  • claude-blog by AgriciDaniel · ⭐ 2.1k

    Claude Code blog skill suite: 30 sub-skills, 5 agents, 5-gate v1.9.0 Blog Delivery Contract, dual-optimized fo

  • mono-color-skill by yanliudesign · ⭐ 2.0k

    One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is xiaoma-durex-copywriter?

xiaoma-durex-copywriter is 杜蕾斯式文案与海报 Skill for Claude Code —— 双层语义方法论 + 8 个文案公式 + 从 260 张原始海报拆解的视觉系统 + AI 出图/代码排版管线. It is categorized as a Claude Skill with 574 GitHub stars.

What programming language is xiaoma-durex-copywriter written in?

xiaoma-durex-copywriter is primarily written in Python. It covers topics such as advertising, chinese-copywriting, claude-code.

How do I install or use xiaoma-durex-copywriter?

You can find installation instructions and usage details in the xiaoma-durex-copywriter GitHub repository at github.com/crawfordxx/xiaoma-durex-copywriter. The project has 574 stars and 25 forks, indicating an active community.

What are the best alternatives to xiaoma-durex-copywriter?

The top alternatives to xiaoma-durex-copywriter on Agent Skills Hub include guizang-yingzao-skill, humanizer-ru, creative-director-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools