2,078 件 ・ 関連度順
概要と使いどころ
Load relevant long-term memory from Hindsight before starting work. Use at the start of every task or request, before planning or answering, and whenever the user mentions people, projects, decisions, preferences or anything done before.
日本語の概要は準備中です。原文の説明を表示しています。
Scales pandas, NumPy, and custom Python research workflows beyond memory or across clusters with Dask. Covers DataFrames, Arrays, Bags, Futures, chunking, schedulers, and distributed diagnostics. Use for partitioned file processing, scientific array computation, or parallel tasks whose memory and dependency structure require Dask.
日本語の概要は準備中です。原文の説明を表示しています。
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
日本語の概要は準備中です。原文の説明を表示しています。
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
日本語の概要は準備中です。原文の説明を表示しています。
A hybrid memory system that provides persistent, searchable knowledge management for AI agents.
日本語の概要は準備中です。原文の説明を表示しています。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
日本語の概要は準備中です。原文の説明を表示しています。
Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user mentions Pinecone, wants to index documents for semantic search, build a retrieval-augmented generation system, store agent memory across sessions, implement hybrid search, or connect an LLM to a searchable knowledge base — even if they don't say "Pinecone" explicitly. Also use when the user asks about vector databases for RAG, namespace isolation for multi-tenant agents, embedding pipelines, or scaling a knowledge base beyond what local storage can handle. DO NOT use for local-only vector stores (Chroma, FAISS, pgvector) or pure keyword search with no semantic component.
日本語の概要は準備中です。原文の説明を表示しています。
Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies, assessing impact, auditing dead or complex code, or handling explicit Codebase Memory requests. Otherwise skip tasks confined to a supplied known file, tiny one-file check, exact literal, configuration value, error string, or non-code text.
日本語の概要は準備中です。原文の説明を表示しています。
Recall and persist long-term memory through the OpenViking MCP tools. Use at the start of any substantive task (coding, configuration, debugging, multi-step or tool-based work) to retrieve relevant prior knowledge with find/search/read, and during or after work to persist durable facts, preferences, decisions, and lessons with remember. Do not use for casual chat or simple factual questions the model can answer directly.
日本語の概要は準備中です。原文の説明を表示しています。
Compute the optimal --mamba-full-memory-ratio (or --max-mamba-cache-size pin) for a hybrid attention + linear-attention (Mamba / GDN / KDA) model's two serving memory pools, from the workload and serving config. Use when a user asks what ratio to set, why concurrency is clamped, or how to size the state vs KV pools for a hybrid model.
日本語の概要は準備中です。原文の説明を表示しています。
Detects rootkit presence on compromised systems by identifying hidden processes, hooked system calls, modified kernel structures, and covert network connections using Volatility memory forensics, cross-view detection, and tools like GMER, rkhunter, chkrootkit, and RootkitRevealer. Use when standard tools (Task Manager, netstat, AV/EDR) show nothing abnormal but compromise is suspected.
日本語の概要は準備中です。原文の説明を表示しています。
Detect and analyze heap spray attacks in memory dumps using Volatility3 plugins to identify NOP sled patterns, shellcode landing zones, and suspicious large allocations in process virtual address space.
日本語の概要は準備中です。原文の説明を表示しています。
Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (check_syscall, lsmod, hidden_modules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify hooked syscalls, hidden kernel modules, and tampered system structures.
日本語の概要は準備中です。原文の説明を表示しています。
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
日本語の概要は準備中です。原文の説明を表示しています。
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
日本語の概要は準備中です。原文の説明を表示しています。
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
日本語の概要は準備中です。原文の説明を表示しています。
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
日本語の概要は準備中です。原文の説明を表示しています。
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
日本語の概要は準備中です。原文の説明を表示しています。
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.
日本語の概要は準備中です。原文の説明を表示しています。
Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together. Use when someone wants to connect their company's database, tickets and docs, or asks who owns, decided or is handling something across them. Runs locally; reads the sources, writes only to cognee's memory.
日本語の概要は準備中です。原文の説明を表示しています。
Chat with a companion that knows your notes folder (a journal, an Obsidian vault, any .md or .txt files) and every earlier chat, using cognee memory with local databases. Use when someone wants to ask questions about their own notes, or to talk with a companion that remembers past conversations. Runs locally; reads the notes folder, writes only to cognee's memory.
日本語の概要は準備中です。原文の説明を表示しています。
Use when removing data from cognee memory with forget() in the SDK, HTTP API, or CLI — finding which dataset and document hold the content to delete (listing datasets and data items, reading raw content), choosing between deleting one document, a whole dataset, or only the graph/vector memory, and doing it safely.
日本語の概要は準備中です。原文の説明を表示しています。
Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the bootstrap-rendered identity files (SOUL.md, USER.md, ACCESS_POLICY.md, HEARTBEAT.md) or their harness equivalents. Finds redundancy, contradictions, stale content, compression candidates, and skill-extraction candidates; produces a ranked action list sorted by token savings with a risk class per finding. REPORT-ONLY: this skill never edits any audited file. Recommendations for bootstrap-rendered files target the interview answer bank / templates, never the rendered output. Judging routes through `gbrain eval cross-modal` (single cheap model by default; full multi-model panel is explicit opt-in).
日本語の概要は準備中です。原文の説明を表示しています。