QA Engineering Suite

Lum1104/bet-on-it

Use when debugging or changing behavior based on an uncertain causal hypothesis that the next action can test.

songlitong521-oss/douyin-doubao-analyzer

抖音视频链接 → 豆包内容分析。收到抖音视频链接（v.douyin.com 短链、www.douyin.com/video 链接、iesdouyin 分享链接或含链接的分享口令文本）且带分析需求时触发。豆包（doubao.com，抖音账号登录、免费）因背靠抖音数据管道，能解析其他 AI 无法解析的抖音视频内容；本技能负责：清洗并展开链接提取视频元信息 → 按场景生成两段式豆包提示词（先发口令触发视频识别，再在同一会话要结构化输出）→ 投喂豆包（人工粘贴为主，Playwright 半自动桥接为辅）→ 等豆包分析完成 → 回收返回内容做校验、去噪、结构化整理并落盘。适用："帮我分析这个抖音链接""抖音视频总结""拆解这条抖音""抖音爆款分析""这个抖音视频讲了什么""用豆包分析抖音视频""抖音选题对标"等请求。只做个人创作学习参考，不批量抓取、不绕过平台限制。

wrsmith108/clerk-claude-skill

Clerk authentication integration for Astro/Next.js. Use when implementing authentication, handling Clerk middleware, testing with Playwright, or debugging auth issues. Trigger phrases include "Clerk auth", "sign in", "authentication", "middleware", "E2E testing with Clerk".

valeria-adiatullina/behavioral-design-claude-skill

Guide users through the complete behavioral design cycle — from defining a target behavior to diagnosing barriers, designing interventions, testing, and scaling. Draws on published frameworks for process design (DECIDE, SIDE), barrier diagnosis (COM-B, 3B, Fogg B=MAP, CREATE), intervention design (EAST, MINDSPACE, BCW), sustained motivation (SDT), and ethics (APEASE). Also guides experiment design, results analysis, and scaling. For UX researchers, product managers, and behavioral designers.

auracura/idea-autopsy

Stress-test a business idea — especially one an AI suggested — before anyone builds it. Use when the user says "autopsy this", "is this a business or bullshit", "test this idea", or pastes a startup/side-hustle idea and wants to know if it's real. Returns one of four verdicts: BUSINESS, BUSINESS WRONG OWNER (real idea, wrong constraints — says which), BULLETIN (it's really just content or information), or BULLSHIT, plus the smallest test that would prove it wrong. Built from a four-hour session in which an LLM pitched twelve businesses and eleven died.

sametcelikbicak/coverage-guard

Use when the user wants to check test coverage, enforce 100% coverage, find uncovered code, add missing tests, or increase code coverage. Works with vitest, jest, react-scripts, and other test runners. Also for 'coverage', 'test coverage', 'cover', 'untested', 'uncovered', 'add tests for', 'increase coverage', 'coverage report', 'write tests', 'test all files'.