en un clic
prompt-skills_collect
prompt-skills_collect contient 7 skills collectées depuis 1055373165, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Deep codebase knowledge extraction pipeline. Systematically reads a codebase, extracts design philosophy and engineering wisdom, produces an AI-injectable knowledge base and a high-density technical blog series. Use when asked to "understand this codebase", "learn from this code", "write a blog series about this repo", or "extract design philosophy".
Full-lifecycle autonomous development agent. User provides a requirement or refactoring plan, and the agent drives the entire flow: requirement locking → architecture design → tech spikes → task decomposition → MDU execution → review → delivery. Use when asked to "autopilot this", "build this feature end-to-end", "run the full dev workflow", "autonomous development", or when a user provides a requirement and wants hands-off execution. Proactively suggest when the user describes a multi-step feature, refactoring plan, or says "I want this built automatically".
Full-lifecycle autonomous development agent. User provides a requirement or refactoring plan, and the agent drives the entire flow: requirement locking → architecture design → tech spikes → task decomposition → MDU execution → review → delivery. Use when asked to "autopilot this", "build this feature end-to-end", "run the full dev workflow", "autonomous development", or when a user provides a requirement and wants hands-off execution. Proactively suggest when the user describes a multi-step feature, refactoring plan, or says "I want this built automatically".
Full-lifecycle autonomous development agent. User provides a requirement or refactoring plan, and the agent drives the entire flow: requirement locking → architecture design → tech spikes → task decomposition → MDU execution → review → delivery. Use when asked to "autopilot this", "build this feature end-to-end", "run the full dev workflow", "autonomous development", or when a user provides a requirement and wants hands-off execution. Proactively suggest when the user describes a multi-step feature, refactoring plan, or says "I want this built automatically".
https://github.com/garrytan/gstack
抓取英文技术文章网页并翻译为中文 Markdown。输入一个 URL,自动完成: Playwright 抓取 → Readability 正文提取 → 图片下载 → 中文重写。 当用户提供英文文章链接、说"翻译这篇文章"、"把这个链接翻译成中文"、 "translate this article"、或者给出 medium.com / substack.com / x.com 等技术博客 URL 时,使用此 skill。即使用户只是贴了一个链接没有明确说 "翻译",只要链接指向英文技术文章,也应主动建议使用此 skill。
Hardened full-cycle development scaffold for Codex. Use for multi-file, multi-session, high-ambiguity or high-stakes work where Codex must first amplify a vague requirement into an executable expert-grade spec, then keep making durable progress across many context windows with initializer/coding-session discipline, batch verification, and recovery.