CLAUDE.md 메모리 관리 워크플로우. 추천(recommend) → 정리(cleanup) → 관리(manage)를 통합하여 프로젝트 컨텍스트를 최적화한다.
Stand up a recurring scheduled agent for standing work (triage, monitoring, audits, digests): a self-contained IDEMPOTENT brief (each run wakes memory-less and must dedup prior…
Work with sparse matrices for memory-efficient storage of count data. Use when dealing with single-cell data or large bulk RNA-seq datasets where most values are zero.
Align RNA-seq reads with HISAT2, a memory-efficient splice-aware aligner. Use when STAR's memory requirements are too high or for general RNA-seq alignment.
Use when managing memory in C programs with malloc/free, pointers, and avoiding common memory safety pitfalls.
Sincroniza documentacao com GitHub Wiki via Git. Publica ADRs, docs de arquitetura e API automaticamente. Use quando: publicar ADR, sincronizar docs apos release.
Profiles Meta Quest and Horizon OS application CPU performance using simpleperf — workload classification, CPU hotspot recording, kernel overhead measurement.
Build structured knowledge frameworks from scattered vault notes with source attribution
Choose what kind of knowledge to transfer between teacher and student models: response, feature, or relational, and decide among offline, online, self, or cross-modal distillation…
Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.
Standard change process for the LLM Wiki engine. Every feature change follows 5 phases: Concept → Verify → Implement → Document → Visualize.
Memory-as-a-Service for AI agents. Store and recall memories with semantic vector search. 100 free calls per wallet, then x402 micropayments. Your wallet address is your identity.
Expert skill for custom memory allocator design optimized for language runtime needs
memory/{gotchas,learned}/observations.jsonl raw 관찰을 정제 .md로 변환하는 사용자 트리거 스킬. 핸드오프 의존이 약할 때 의지로 호출. Dreaming-like rebuild 모드 지원 (기존 정제 .md + 새 관찰 통합 + 중복/모순 제거).
Evidence-based memory optimization from real usage patterns. Analyzes recall performance, identifies bottlenecks, suggests consolidation/pruning/enrichment, and tracks improvement…
Gerencia persistencia de contexto, decisoes e learnings do projeto. Armazena e recupera informacoes entre sessoes para manter continuidade.
AI-powered NK cell therapy design for cancer immunotherapy including CAR-NK engineering, memory-like NK generation, and KIR/HLA matching optimization.
Create Obsidian-compatible Mermaid diagrams. Prefer square layouts (TB + subgraph LR), avoid markdown in labels.
Shared memory workflow for Claude Code agents connected to Remnic — recall before acting, observe during work, remember at the end.
Gestion de la mémoire projet avec Serena MCP. Utiliser pour stocker et récupérer des informations persistantes sur le projet, les décisions architecturales, et le context — from…
Создаёт новые Claude Code Skills в текущем проекте. Используй когда пользователь просит: - Создать новый навык или скилл - Добавить автоматизацию для рабочего процесса - Построить…
Initialize the Everything is Knowledge wiki. Creates directories, configures API keys, and sets up PDF parsing options. Run once to set up a new wiki.
Zep memory server integration for long-term conversation memory and user profiling
Scaffolds an Obsidian-compatible vault from the user manifest. Two modes — fresh-vault (creates Inbox/Logs/Plans/.coordination plus a personalized CLAUDE.md and System Backlog…
Создать Anki карточки из фото с рукописными словами от Даши (репетитор немецкого)
Pattern notlarındaki Q&A bölümlerini Anki-uyumlu CSV formatına dönüştürür. patterns/, modern-patterns/, anti-patterns/ altındaki tüm .md dosyalarını tarar.
Save and manage bookmarks in Obsidian vault. Automatically fetches page title and description. Use when you want to save URLs for later.
Trigger on: /coeus:router, /coeus-router, "route this", "which coeus skill", "pick the right coeus skill", "coeus help me decide", "not sure which coeus", "coeus guru", "skill…
Convert a markdown string/file to Confluence-compatible XHTML and publish it as a page to Confluence Cloud. Supports create, upsert, and update modes.
複数リポジトリを横断して調査・影響分析を行う。 「横断調査」「影響調査」「クロスリポ」「cross-repo」「複数リポジトリで調べて」 「他のリポジトリに影響ないか」「APIの利用箇所を全リポで探して」などで使用。 リポジトリ間の依存関係やAPI呼び出し、DBスキーマの影響範囲を調査し、 結果をObsidian…
Summarize the current agent session, create an Obsidian note for it, and link it from today's daily note.
Build a graph-structured dossier on a seed entity via parallel fan-out + recursive expansion across web, memory, knowledge-graph, codebase, ADR index, and git intel
Generate technical documentation retroactively for completed stories — fetches ADO story, finds linked PRs, searches codebase, and produces wiki-ready docs without needing spec…
Generate categorized reports for multiple PR reviews — lists reviewed PRs, generates a report for each, and posts all to ADO Wiki or Confluence.
Fetch internal company documentation, framework examples, or platform guidelines into the current AI context.
Generate spaced repetition flashcards from notes or topics. Use when user wants to create flashcards, make review cards, prepare for spaced repetition, or convert notes to quiz…
Install, analyze, bootstrap, run, review, or migrate a Handyman agent harness: leader/implementer/reviewer roles work one feature at a time with disk state and executable…
Four-stage pipeline that takes a corpus of seed content (your existing notes), clusters by semantic similarity, proposes a vault taxonomy via LLM, renders a user-reviewable import…
This skill should be used when the user asks 'what do I know about [topic]',
Ajout rapide de notes dans la documentation personnelle (tips, todo, veille, changelog)
This skill should be used when the user asks to 'prime context', 'load project knowledge', 'what do we know about this project', 'knowledge brief', 'project context', 'what…
Leo 的結構化學習迴圈（先教後考 + 來源查證），把一個新概念精煉成 Obsidian vault 的知識結晶。 僅在 Leo 明確叫用（Claude Code `/learn-loop`、Codex `$learn-loop`，或明說「跑 learn-loop 流程學 X」）時啟動； 不要因為對話中提到想了解某事就自動觸發 ——…
Use when the user wants to lint a repo following the Karpathy LLM Wiki pattern (raw/ + wiki/ + SCHEMA.md / index.md / log.md).
Ingest new sources into the LLM Wiki. Reads unprocessed files from raw/, docs/, and notes/, creates source summaries, updates entity/concept pages, maintains cross-references, and…
Search the LLM Wiki using qmd (hybrid BM25/vector search). Finds relevant wiki pages, reads them, and synthesizes an answer with citations.
Finalize cross-session memory on demand; --finalize-all sweeps every dirty scratch. Use when ending a long session or before switching branches.
Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search
Use when designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-context / RAG / graph / agentic memory, auditing what a…
A running log of favourite shared moments. Not dates — the small things worth keeping. Run /memory-jar read on bad days.
Run monthly maintenance on the exomemory system: expire stale entries, promote frequently-referenced memories, compress old logs, and verify index integrity.
This skill should be used when the user asks about "past decisions", "previous learnings", "what did we decide", "how did we solve", "remember when", or mentions topics that may…
노션 MCP로 페이지·문서를 만들 때 가독성 좋은 구조로 작성하도록 안내하는 스타일 가이드. 사용자가 "노션에 정리해줘", "노션에 작성/문서화해줘", "노션 페이지 만들어줘", "이 내용 노션에 올려줘", "노션에 보고서/가이드/위키 만들어줘" 같은 표현을 쓰거나,…
Dış kaynağı (URL/library/PDF/repo) global Obsidian docs/ altına sectioned dokümante eder.
Primes the agent with focused understanding of the backend portion of the codebase — API routes, services, data models, and database layer — without loading unrelated frontend…
Primes the agent with deep codebase understanding by analyzing structure, documentation, and key files.
Primes the agent with focused understanding of the frontend portion of the codebase — components, routing, state management, and styling — without loading unrelated backend code.
Releases a new version of the WpfDevPackMcp NuGet MCP server (the server under mcp/), which is versioned independently of the wpf-dev-pack plugin and of knowledge content.
One-time wizard (5) that configures KeiSeiKit sleep layer. Phase 0 picks mode (local-only / remote-only / hybrid); Phase 0b picks local trigger time (6 options incl.
Deep cross-domain synthesis engine for the vault. Triggers on "synthesize X", "what do I know about X", "connect ideas about X", "cross-domain analysis of X", "map everything in…
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.