Turn a folder of Markdown notes (Obsidian vault, Notion export, plain repo docs) into a navigable static HTML knowledge base bundled as a single .zip file.
Cérebro vetorial com LanceDB — pipeline completo de downloads de livros (Z-Library → sanitização → chunking → vetorização → armazenamento → consulta)
Design, build, and maintain comprehensive knowledge bases. Bridges document-based (RAG) and entity-based (graph) knowledge systems.
Search and locate relevant content within a local knowledge base (files, indices, or PageIndex). Use when you need verifiable citations (file + page/paragraph) to support answers…
Query knowledge artifacts across all locations. Triggers: "find learnings", "search patterns", "query knowledge", "what do we know about", "where is the plan".
Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriate — from…
Компилирует личные книги, PDF/EPUB/TXT/Markdown и длинные материалы в прикладной Claude Code skill с картой источников, решающими правилами, плейбуками, словарём и проверкой…
Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.
Discover relevant skills and knowledge using tiered approach. SKIP for simple tasks, QUICK for single-skill, STANDARD for multi-skill, DEEP for full feature implementation.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT- — from…
Periodic knowledge consolidation for AI coding agents. Synthesize scattered project learnings into durable, well-organized memory files.
Extract tribal knowledge from code, documentation, and commit history to preserve institutional memory
Auto-applies MECE/BFO framework (thesis, Mermaid TD/LR, numbered sections, Ground Truth) to ANY .md file creation.
Designs and builds knowledge graphs to represent entities, relationships, and semantic connections, with query patterns for Neo4j, RDF, and property graphs.
Use when designing and building knowledge graphs from unstructured data. Invoke when user mentions entity extraction, schema design, LPG vs RDF, graph data model, ontology…
Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph
Neue Notes in das Wissensnetz einordnen. PDFs als Markdown-Quellen-Notes anlegen. Properties, Links, MOC-Eintraege setzen.
Process external resources into stored knowledge with quality evaluation, curation routing, and application decisions.
Ingests and prepares codebase documentation, builds internal knowledge graphs, and creates optimized context representations for downstream analysis tasks.
Search and navigate stored knowledge in memory palaces. Use for cross-referencing, context retrieval.
4-layer knowledge capture system for development sessions. Use when user says /mem (quick capture), /distill (extract patterns), /td (post-task retrospective with Before/After…
AI Personal Knowledge Manager — Zettelkasten, Obsidian, PARA, Note-Taking System, Second Brain สำหรับนักเรียนรู้ตลอดชีวิต
Use when choosing the representation paradigm for domain knowledge: knowledge graph, frame, production rule, semantic network, concept map, procedural ontology, or hybrid.
中文优先：用于知识运维相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector…
Batch-Umbenennung von Attachments (PDFs, Bilder) nach Konventionen. Autor-Jahr_Titel fuer Quellen, Kontext-basiert fuer Bilder.
Teaches how to use Bluera Knowledge for accessing library sources and reference material. Explains two approaches - vector search via MCP/slash commands for discovery, or direct…
Retrieves implementation knowledge, code examples, and documentation references. Use to inform technical decision-making when the user requires specific library usage, framework…
Creating processes and tools for sharing knowledge across teams to reduce silos, onboard faster, improve team resilience, and foster innovation through cross-pollination of ideas.
Close lifecycle on a knowledge/ note. Three stages: Close (verify + used_in) → Extract (3 questions) → Backflow (route principle/SOP/signal).
Combines search results from multiple sources into coherent, deduplicated answers with source attribution.
Expert knowledge synthesizer specializing in extracting insights from multi-agent interactions, identifying patterns, and building collective intelligence.
Expert in aggregating, processing, and synthesizing information from multiple sources into coherent insights.
Bootstrap a compile-first project knowledge system with repo-local wiki, raw manifests, provenance tracking, auto-update checks, and platform configs for Claude Code / Codex /…
Categorize extracted information into the appropriate knowledge base subdirectory (tasks, definitions, wiki, project-status, people, jira-drafts).
Knowledge doc utilization tracking. After a dev task, analyzes how AI actually used knowledge docs during the conversation.
Automated skill for keeping AI knowledge bases current with latest model versions, framework updates, and best practices
pce-memory + shirushiを活用した知識検証・整合性チェックスキル。 以下の場合に使用: (1) 資料・ドキュメント間の矛盾チェック (2) 指示・意思決定の追跡と検証 (3) 作業途中のリアルタイム整合性チェック (4) 成果物と要件の照合検証 (5) shirushi Doc-IDとコードのトレーサビリティ検証…
Comprehensive global knowledge worker salary data with total market value calculations, sector breakdowns, geographic comparisons, and authoritative sources.
Kuma Vault SSoT retrieval. Trigger on 새 작업/플랜, vault-backed 도메인/프로젝트 키워드, domains/* edits, previous-context recall, decisions/6원칙. Modes: search/timeline/get/ingest/curate.
Rust 1.92+ development specialist covering Axum, Tokio, SQLx, and memory-safe systems programming. Use when building high-performance, memory-safe applications or WebAssembly.
LangGraph v0.2 ядро (import langgraph). ТОЛЬКО при: StateGraph, add_node/add_edge, conditional_edges, @entrypoint/@task, Command/Send, interrupt, subgraph, MessagesState, Pregel,…
Process large documents (200+ pages) with structure preservation, intelligent parsing, and memory-efficient handling.
Use Pro Workflow when Claude Code sessions keep repeating the same mistakes and you want corrections, quality gates, and parallel worktree routines to persist across sessions…
Generate comprehensive undergraduate lecture notes for social sciences (especially economics) with mathematical foundations, daily-life examples, and practice questions — from…
Generate comprehensive undergraduate lecture notes for social sciences (especially economics) with mathematical foundations, daily-life examples, and practice questions — from…
life-os/ 目录的文件读写规范。处理 Markdown 笔记、YAML frontmatter、wiki-links、模板变量。当需要在 life-os/ 目录中创建、编辑、查找笔记时使用此技能。
Discover and add wiki-links between notes. Use when asked to "find connections", "link this note", "what should I link to", or "connect my notes".
LLM.int8() and bitsandbytes 4-bit quantization (NF4/FP4) for memory-efficient LLM loading. Mixed-precision decomposition, QLoRA fine-tuning, double quantization, and GPU OOM…
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。
Operate and maintain the LLM Wiki knowledge system in the Megingjord source workspace.
Operate an LLM Wiki knowledge system in any workspace using the Karpathy pattern
Check LLM Wiki health. Finds orphan pages, broken wikilinks, contradictions, stale content, missing pages, cross-reference gaps, and suggests improvements.
Initialize the LLM Wiki. Creates directory structure, index, log, sets up qmd collection, and runs initial ingest of all existing content from raw/, docs/, and notes/.
Optimize the LLM Wiki. Compacts verbose pages, merges near-duplicates, reorganizes misplaced content, strengthens cross-references, improves consistency, and generates missing…
Ultra-fast data discovery and loading skill for industrial finance datasets. Handles CSV, JSON, DuckDB, Parquet, and Feather with memory-efficient 2-step discovery and loading.
Provide commands for interacting with a local Logseq instance through its Plugin API. Use for creating pages, inserting blocks, querying the graph database, managing tasks,…
Format any content as a Logseq-compatible outline using nested bullets (no markdown headers, no bold). Works in both Claude Code and Claude Desktop.
Migrate Logseq graphs to Obsidian vaults. Use when the user wants to convert their Logseq notes to Obsidian format, migrate from Logseq, or mentions both Logseq and Obsidian in a…
Sync Logseq pages tagged with #zotero to Zotero by adding 'in_logseq' tag. Uses batch checking for efficiency. Claude Code only.
Fähigkeit, das gesamte Wiki-Wissen zu aggregieren, Inkonsistenzen zu finden und präzise Auskunft zu geben.