qingsheng-skill — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

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 tomwong001 · Claude Skill · ★ 145

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

🔒 Is qingsheng-skill safe to install? View the security audit →

About qingsheng-skill

情圣.skill "在吗起手,必是小丑。" 她发了一条消息,你盯着屏幕看了半小时不知道怎么回? 聊得好好的突然被已读不回,不知道是自己说错了还是她在忙? 朋友圈点赞怕太随便,评论又怕太刻意? 约她被"下次吧"挡了一下,不知道是真下次还是永远不会有? 暧昧期三个月了推不动,表白怕死得太惨,不表白又怕拖没了? 脑子里一堆话想跟她说,打出来又全删了,最后发了个"在吗"? 把你最慌的那一刻,交给一个站在你这边的军师。 不是 PUA 教学 · 不是 ChatGPT 套壳 · 不教你装高价值 基于 1TB+ 过去十年中文情感付费课程语料(语音 · 视频 · 文字 · 真实聊天记录)蒸馏而成 效果示例 · 方法论 · 安装 · 使用 · 适用场景 · 对比其他方案 · 常见问题 情圣 skill 适用场景:微信聊天记录分析、探探 / Soul / Bumble / 青藤之恋 / Tinder 匹配话术、朋友圈展示面诊断、约会邀约模板、女生已读不回应对、高情商回复生成、关系阶段判断、冷启动挽回、同时追多个对象的档案管理。一个在 Claude Code / Cursor 里加载的中文恋爱 AI 私教,基于 1400+ 真实聊天语料蒸馏,本地运行不上传,完全免费开源(MIT License)。付费 PUA 课程、情感咨询、恋爱话术小册子的替代方案。 效果示例 场景一:微信——被动模式警报 你 ❯ 帮我看看这段,她好像有点冷了 情圣 ❯ 微信场景,你们现在卡在阶段 3 的尾巴——问题不在她,在你追得太直。 "周六有空吗 → 周六有事 → 那你什么时候方便" 两轮追时间,需求感 直接拉满,她只能用"最近挺忙"这种万能挡箭牌收尾。

ai-coachbumblechat-assistantchinese-aiclaude-codeclaude-code-skillclaude-skilldating-coachlove-adviceocr

Quick Facts

Stars145
Forks13
LanguageShell
CategoryClaude Skill
LicenseMIT
Quality Score61.6383275334933/100
Open Issues2
Last Updated2026-09-29
Created2026-03-12
Platformsclaude-code, cli
Est. Tokens~13k

qingsheng-skill alternative? Top 6 similar tools

Looking for a qingsheng-skill alternative? If you're comparing qingsheng-skill 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.

  • creative-director-skill by smixs · ⭐ 203

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

  • skill-conductor by smixs · ⭐ 160

    Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca

  • claude-for-safari by SDLLL · ⭐ 68

    Give your AI Agent the power to control Safari on macOS. No extensions, no separate browser.

  • claude-code-workflows by shinpr · ⭐ 686

    Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.

  • soul.md by aaronjmars · ⭐ 606

    The best way to build a personality for your agent. Let Claude Code / OpenClaw ingest your data & build your A

  • compose-skill by aldefy · ⭐ 561

    Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is qingsheng-skill?

qingsheng-skill is 情圣 · Claude Code 中文恋爱教练技能 · 微信/探探/Soul/Bumble/青藤之恋聊天截图分析 · 高情商回复生成 · 7阶段关系推进. It is categorized as a Claude Skill with 145 GitHub stars.

What programming language is qingsheng-skill written in?

qingsheng-skill is primarily written in Shell. It covers topics such as ai-coach, bumble, chat-assistant.

How do I install or use qingsheng-skill?

You can find installation instructions and usage details in the qingsheng-skill GitHub repository at github.com/tomwong001/qingsheng-skill. The project has 145 stars and 13 forks, indicating an active community.

What license does qingsheng-skill use?

qingsheng-skill is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to qingsheng-skill?

The top alternatives to qingsheng-skill on Agent Skills Hub include creative-director-skill, skill-conductor, claude-for-safari. 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