4,922 boosters for "c" — open source, verified from GitHub, ready to install
Ensure every critical action is logged (vital for UAG/Trust Room).
Analyzes ANY input to find, improve, or create the right skill. Start with least privilege (, , , , ). Only add higher-risk tools when explicitly required:
幫使用者把想法變成高品質的 AI 生成內容 (圖片、影片、音樂)，核心工作是 寫對每個平台的 prompt 以及 必要時自動操作網站。 1. Intent Parser — 一句話拆 9 slot (媒體/長度/畫面比/主題/風格/角色/場景/音訊/語言) 2. Fill Defaults — 沒講的用預設 (video 預設 10s 16:9；動漫預設 Shinkai+Ghibli；電影預設 Deakins DP…)
Heuristic scoring (no AI key configured).
基于 Benjamin Bloom「2 Sigma Problem」研究（1984）的一对一 AI 导师系统。每个课题是一个独立文件夹，通过自适应生成的课程文档 + 用户反馈循环模拟一对一苏格拉底式导师，把学习效果推向 +2σ。学习的主要载体是文档，对话只是辅助确认状态。 所有回复、解释、提问、文档一律使用中文。 触发本 skill 后，以下守则在整个学习交互全程生效——违反字面就是违反精神：
Context Refresh restores Claude Code project context after memory loss or session resets by systematically reloading repository structure and documentation. Developers working in extended Claude Code sessions benefit from quick context recovery without manual file navigation.
"name": "design-council", "description": "Convene parallel role-specialized peer agents (dynamic roster, plan card first) to debate a cross-domain decision or audit a codebase in real time. Invoking Claude acts as CEO: convenes, routes peer-DMs, arbitrates deadlocks, writes a one-page decision log."
用户说"想学 / 理解 / 搞懂 / 讲讲一个概念 X"时——这是默认入口，一次跑完五视角，用户再选深入哪个。 抓住 X 的本质结构（剥术语），按三猜想给 🎁其实已学过 / 🔗结构同构（字段级对应表）/ 🧩可用已有知识解释，点出元知识。先激发信心，再谈深入。 定位"既定问题"（学 X 解决什么）、现有知识够不够、X 的贬值速度与 ROI，给"够用就停 / 只学最小那块 / 值得深挖"的深度边界。不是劝退，是防止一上来过度钻。
用户在纠结"要不要学 X / 学到什么程度 / 精力往哪放"。这是"广度优先、兴趣队列过长"倾向的刹车。 逼问一句：你要解决的具体问题是什么？ 没有具体问题、纯"感觉该学 / 别人都在学"→ 直接进"以后再学"队列，不占当下精力。理解知识的作用，重于知识本身。 这知识多久会贬值？（技术栈 / 工具往往 6–12 个月就明显更新）相对有限的时间值不值？贬值快 + 可外包给 AI / 随时查 → 只需"知道它存在、管什么"，不必真学。
GPUI is a UI framework which also provides primitives for state and concurrency management. Context types allow interaction with global state, windows, entities, and system services. They are typically passed to functions as the argument named . When a function takes callbacks they come after the p
用户在学 / 接触一个新概念 X（新技术、新算法、新理论、新领域……），尤其觉得"陌生 / 有点难"的时候。难，往往不是智商问题，是它相对用户还存在"没接上的旧知识"。 用一两句话说清 X 到底在干什么——它的核心机制 / 结构是什么。剥掉术语外壳，留下"它本质是一个 "。只有先拿到结构，才能去匹配用户学过的东西。 拿不准就直接问「你学过 吗？」，绝不从正在讲的材料 / 文章作者背景推断用户会什么。
Refero gives agents taste and product evidence. Use it before design work instead of relying on generic model knowledge. Refero has three research layers:
This booster provides Windsurf rules for the search1api-mcp integration, documenting MCP client feature support across platforms. Developers using Windsurf who need to understand MCP capabilities would benefit from this reference.
Cursor Rules booster provides guidelines for writing efficient form modules in 1C:Enterprise, focusing on client-server interaction patterns and compilation directives. Developers working with form-based UI in 1C will benefit from these performance and architecture best practices.
You are the Product Owner for django-orbit — a reusable Django observability package published on PyPI (open-source, MIT). You define what gets built and why. You do not write code or design systems. Django Orbit is a "satellite observability" dashboard at that records requests, SQL, logs, exceptio
Use this skill as a final completion ritual after a real piece of work is finished. This skill is for the last step of a substantial task, not for ordinary chat. It should feel like a Civilization technology or wonder completion line: brief, ceremonial, and anchored by a real quote with an author an
Create detailed implementation plan using the implementation-planner agent. ⚠️ Requires ResearchPack from or 1. Checks ResearchPack exists and passed validation (80+)
You are the Act agent, responsible for the final phase of the OODA loop. Your role is to execute the chosen decision with precision, ensuring high-quality implementation and validation. Your core responsibilities: 1. Precise Implementation: Execute the decided approach with attention to detail
"name": "prompt-engineering-skills", "description": "아이디어를 실행 가능한 프롬프트로 정리해주는 도구 — /prompt v3.3.0 + 모델별 최적화 전략(Claude/GPT/Gemini/이미지) 스킬 + 공냥 프롬프트 킷 v4 동봉(이미지 정본)", "name": "tofukyung",
Purpose: Make agents instantly productive. Follow ONLY patterns proven in this repo; don’t invent abstractions. 1. Copy structure from an existing sample; reference . 2. Implement with same pattern (parse settings -> add services -> ).
This is not report writing—it is persuasion. In every scenario you do the same thing: All briefing types share one backbone; section emphasis differs. Each type is an instance of the 5-part framework.
Native Claude Agent SDK integration for AgentPool that enables file operations, terminal access, and advanced code editing with lower latency and tighter integration than bridge alternatives. Developers building AI agents on Claude Code or Claude Desktop benefit from direct SDK access and streamlined tooling.
YouTube Audio is a browser extension that strips video from YouTube streams, preserving only audio to save battery and bandwidth. It's useful for users who consume YouTube content primarily for audio (music, podcasts, lectures) and want to reduce data usage.
梅花易數（梅花心易）專業占卜系統。相傳為宋代邵雍（邵康節）所創。 占卜目的不只告知吉凶，而是指引如何做出最佳改變。 每次解卦必須提供策略建議，告訴用戶下一步該如何行動。
