1,330 boosters — open source, verified from GitHub, ready to install
用户要系统进入一个新领域，或焦虑"学得不够系统 / 不知何时算够"。 用户为什么学 X？（接 的"既定问题"）目的决定图谱画到多细。 从入门点出发、沿父子关系排一条有效路径。颗粒度按需自由切换（领域图 → 细分学科图）。"学到哪算够"= 覆盖到能解决第一步那个目的的节点即可，不必学满。
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.
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。
用户学完一个东西想验真伪，或隐约觉得"好像懂了但不踏实"。也是"重输入轻输出"的一次强制输出。 请他用自己的话、把你当外行，把概念讲一遍。别让他背定义——要他解释、打比方。 专挑他含糊带过、用术语糊弄、跳过的环节追问："为什么？""那这个是怎么来的？""举个例子？"命中他答不上来或开始绕的地方。
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。
用户要动手做 / 研究一个东西，或想把某个已有产出改得更好。这是"重输入、轻输出"短板的解药——逼用户从输入切到输出。 别追求完美，先有一个能跑 / 能看的最小版本。卡在"还没准备好"就是没进改良主义。 针对缺陷提一个改良策略（视为假说，可对可错），动手改，看效果。错了也有用——错误暴露后，下次自动规避这个方向。
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。
Refero gives agents taste and product evidence. Use it before design work instead of relying on generic model knowledge. Refero has three research layers:
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+)
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。
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.
A fully autonomous AI research agent that ingests sources into Google NotebookLM, runs deep web research, synthesizes knowledge through cited Q&A and 9 downloadable artifact types, creates polished content drafts, and optionally publishes to social platforms.
When building or rebuilding fragments, use the sequence and model from NCS-related (non-crystallographically related) or molecular symmetry-related molecules as a reference. If one copy is better built, use it to guide building of the other copies. Before building, compare sequences between related
This booster generates a structured requirements document template in Chinese, helping product managers and developers quickly create comprehensive requirement specifications with sections for background, features, business processes, and acceptance criteria.
A structured quick-fix skill for Claude Code that systematizes bug resolution through problem localization, repair, and verification—with strict constraints for code-review contexts to prevent unintended refactoring or scope creep.
Automatically extracts knowledge from Amp threads and synchronizes project documentation, keeping AGENTS.md and other docs up-to-date after epics and major work. Ideal for teams that need to maintain living documentation without manual overhead.
Voice conversations with Claude (Opus 4.5) about your projects. That's it! Now you can: Claude greets you by name: "Hey Sarah! I've got my-project loaded up."
Auto-loaded when writing documentation, content, or user-facing text. Enforces consistent, direct voice and eliminates LLM rhetoric. Also loaded when a project sets or in , to govern conversational response length and structure (see Output Modes). Bad (filler, marketing, generic):
Convert documents (PDF, DOCX, XLSX, TXT) to clean, structured Markdown. The flag prints a JSON summary to stdout after processing: PDF (native, scanned, encrypted), DOCX, XLSX, XLS, CSV, TXT, MD
Automates creation of standardized research project structures with pre-configured folders, documentation templates, and guidelines. Ideal for researchers and teams starting new projects who need consistent organization and onboarding rules.
Beads is available for task tracking. Use tools to manage issues (the user interacts via commands). Create a pull request for the current branch using GitHub MCP tools. Current branch status:
This command queries the BEADS knowledge base for facts relevant to your current context and injects them into the conversation, ensuring you: 1. Follow established patterns and rules 2. Avoid known gotchas and pitfalls
你是 OpenClaw 内部负责操作 Codex CLI 的执行器。你的职责不是“给用户解释 Codex 是什么”，而是基于当前仓库提供的 runtime 层，把 Codex 任务稳定启动、持续跟踪、必要时接管和汇报。 可以借鉴 的 runtime/session 思路，但不照搬 Claude 专用逻辑。 优先直接使用 Codex review，而不是自己拼一套“审查 prompt 模拟 review”：
