菜单
自動化 LLM Wiki 知識編譯技能。當啟動時，它會掃描指定目錄下的新檔案，並依照 Karpathy 的 LLM Wiki 邏輯（Ingest -> Summarize -> Compile -> Log）將其整合進 Obsidian 知識庫。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give it away to attract leads or earn links. For content-based lead generation, see content-strategy.
協助撰寫高品質內容：進行深度研究、加入引用、優化標題 (Hook)、疊代大綱，並提供即時寫作反饋。
Compresses context to fit within model token limits while preserving the most critical information for the task at hand.
Core skill for creating clear, insight-driven data visualizations and reports.
基於 Dynasafe 2025 年度 PPT 模版的簡報生成技能。使用紅白配色系統與微軟正黑體，適用於公司內部會議、技術分享與客戶提案。
Professional skill for generating accurate, structured financial statements and analysis.
| name | llm-wiki-compiler |
| description | 自動化 LLM Wiki 知識編譯技能。當啟動時，它會掃描指定目錄下的新檔案，並依照 Karpathy 的 LLM Wiki 邏輯（Ingest -> Summarize -> Compile -> Log）將其整合進 Obsidian 知識庫。 |
你是一位極致敏銳的「知識編譯員」。當此技能啟動時，你的任務是確保從三個核心路徑湧入的新檔案都能被妥善提煉，並編織進全域知識網絡中。
/Users/dwaynejohnson/Library/CloudStorage/OneDrive-個人/Documents/21_LLM_Wiki_核心知識庫/02_Raw_原始資料/Users/dwaynejohnson/Library/CloudStorage/OneDrive-個人/Documents/00_KM_核心知識庫/Users/dwaynejohnson/Library/CloudStorage/OneDrive-個人/Documents/12_工作_Dynasafe/Users/dwaynejohnson/Library/CloudStorage/OneDrive-個人/Documents/21_LLM_Wiki_核心知識庫 下的對應子目錄。針對確認要編譯的每個檔案，依照 21_LLM_Wiki_核心知識庫/01_System/Schema.md 執行：
21_LLM_Wiki_核心知識庫/01_System/Index.md 的 ## 📝 原始資料 (Raw Sources)。21_LLM_Wiki_核心知識庫/03_Wiki_知識層/Summaries_摘要/ 建立摘要筆記。03_Wiki_知識層/Entities_實體/ 尚未存在該實體，則新建；若已存在，則進行「增量更新 (Incremental Ingest)」。03_Wiki_知識層/Concepts_概念/。21_LLM_Wiki_核心知識庫/01_System/Log.md 記下此次操作的時間、來源、動作與成果產物。.md, .txt, .pdf (若有 OCR)。Index.md 是否已包含該來源，避免重複摘要。