Loading...
Loading...
Found 53 Skills
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local web viewer. Use when (1) scaffolding a new knowledge base for any research topic, (2) ingesting articles/papers/PDFs/web pages into raw/, (3) compiling or restructuring wiki articles from existing raw material, (4) answering questions against the wiki and filing durable answers back, (5) running lint passes for dead links / orphan pages / coverage gaps / audit shape, (6) processing human feedback from the audit/ directory and applying corrections. Not for general note-taking, daily journals, or non-wiki Obsidian use.
Extract full transcripts from video content for analysis, summarization, note-taking, or research. Use when the user wants a written version of video content, asks to "transcribe this", "get the text from this video", "convert video to text", or shares a video URL for content extraction.
Personal Knowledge Management documentation system based on Zettelkasten principles. Use when documenting conversations, decisions, development work, learnings, or any knowledge that should persist. Triggers on new projects, technical decisions, completed tasks, lessons learned, meeting notes, or when the user says "document this". Apply this workflow to all daily memory notes and long-term memory updates.
Quickly capture ideas, thoughts, and fleeting notes to your personal Yuque knowledge base. For personal/individual use — saves to your own repos.
Blind Spot Scan —— Read all your conversations with AI from yesterday, identify exposed cognitive blind spots (not gaps in knowledge, but thinking habits that keep certain truths consistently invisible), then select a precise chapter from WeChat Reading to fill the gap and compile a complete analysis note. Use when user says '扫盲区', '盲区', '照盲区', '看看我的思维盲区', '我昨天想漏了什么', 'blind spot', 'ljg-blind', '/ljg-blind', or requests analysis of yesterday's AI conversations for cognitive blind spots along with a targeted weread chapter to address them. Optional parameter: Pass a date (YYYY-MM-DD) to scan that day instead of yesterday. NOT FOR deep diving into a single opinion (use ljg-think), ranking down a field (use ljg-rank), reading along with a text (use ljg-read), or finding constraints in a field (use ljg-constraint).
How to write well-structured Basic Memory notes: frontmatter, observations with semantic categories, relations with wiki-links, and best practices for building a rich knowledge graph. Use when creating or improving notes.
Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode, track domain-specific notes, add observation types or tags, or send Telegram notifications for particular memories—even if they do not use the word "mode."
Transforms knowledge sources into an Obsidian StudyVault. Two modes: (1) Document Mode — PDF/text/web sources → study notes with practice questions. (2) Codebase Mode — source code project → onboarding vault for new developers. Mode is auto-detected based on project markers in CWD.
Intelligent Q&A Appender that appends Q&A content from conversations to existing notes or creates new independent cards. Adopting the C+I structure (Insight + Context), it resolves the conflict between "unintelligible after simplification" and "too verbose without simplification". Triggers: /qa, /ask
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on '解剖概念', '概念解剖', 'explain concept', 'learn concept', '/ljg-learn'. Produces org-mode output.
Deconstructs academic papers like an X-ray machine, extracting core contributions, critical assumptions, and napkin-worthy insights from research papers.
Enables Claude to create and manage notes with supertags in Tana via Playwright MCP