226 件 ・ 関連度順
概要と使いどころ
Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.
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。
Provides Amazon Bedrock patterns using AWS SDK for Java 2.x. Invokes foundation models (Claude, Llama, Titan), generates text and images, creates embeddings for RAG, streams real-time responses, and configures Spring Boot integration. Use when asking about Bedrock integration, Java SDK for AI models, AWS generative AI, Claude/Llama invocation, embeddings for RAG, or Spring Boot AI setup.
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。
Delegates tasks to a locally served Muse Glimmer via ollama. Use when delegation-core selects glimmer or the prompt must not leave the machine.
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。
Route Chinese-LLaMA-Alpaca model reconstruction, inference/deployment, training/fine-tuning, and evaluation workflows.
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。
Routes Chinese-LLaMA-Alpaca-2 training, inference, serving, evaluation, and integration workflows.
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。
An almost defiantly minimal documentation-first system that treats the home page like a Markdown README — paper-white canvas, 36px center-aligned heading, a single black pill CTA, an inline terminal install snippet, and a hand-drawn llama mascot as the only ornamental element. No gradient, no hero photography, no marketing pyrotechnics. The chrome is a tiny utility palette of pure black, pure white, and three neutral grays; every interactive element is fully rounded into a pill (`{rounded.full}`); typography is SF Pro Rounded for headings paired with system sans for body and ui-monospace for code. Pricing tiers, FAQs, and "your data stays yours" guarantees all sit on the same flat canvas inside thin-border cards — the system is the documentation, and the documentation is the system.
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。
AWS Bedrock — fully managed foundation models on AWS infrastructure. Use when deploying AI in AWS-native environments, needing enterprise compliance (SOC2, HIPAA), running Claude, Llama, Titan, or Mistral on AWS, leveraging Knowledge Bases for RAG, or applying Guardrails for content safety.
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。
加密链上交易 (加密 / 链上交易 (Crypto & On-chain Trading) — 以加密资产为标的、强调链上活动的主动交易认知操作系统：从「看叙事/选赛道 → 找标的 → 链上尽调与风控 → 选场所(DEX/CEX/链上合约) → 建仓与仓位管理 → 监控链上流向与情绪 → 退出与复盘」的完整决策链。覆盖 (a) 第一性张力 — **链上 on-chain (DEX 现货/AMM、钱包追踪 wallet tracking、资金流向 flow、MEV、memecoin、链上衍生品 Hyperliquid/GMX、自托管 self-custody, 'not your keys not your coins') ⇄ 链下 CEX (中心化交易所现货/合约 Binance/OKX/Bybit、订单簿、托管、出入金法币)**; **合约/杠杆/衍生品 (perps 永续、资金费率 funding、清算 liquidation、爆仓、做多做空、高频/择时) ⇄ 现货/价值/长持 (spot、HODL、定投 DCA、基本面/估值、'time in market > timing the market')**; **价值/基本面派 (协议收入、TVL、代币经济学 tokenomics、真实使用、估值模型) ⇄ meme/叙事/情绪派 (memecoin、narrative rotation 叙事轮动、attention is the asset、纯博弈/PvP、Ponzinomics)**; **链上数据/量化/客观 (on-chain analytics, Nansen/Arkham/Dune、聪明钱 smart money、链上指标、系统化/机械化) ⇄ 直觉/盘感/叙事阅读 (narrative、KOL alpha、社群情绪、tape reading)**; **自托管/去中心化/抗审查 (DeFi、自托管钱包、抗审查、'be your own bank') ⇄ 便利/合规/中心化 (CEX、合规出入金、KYC、托管、ETF)**; **主动交易/择时/高换手 (trading、波段、合约、撸毛/空投 airdrop farming、套利 arbitrage) ⇄ 被动配置/低换手 (配置 BTC/ETH、ETF、长期叙事 beta)**; (b) 核心工作流 / pipeline (最标准、最易蒸高质量 + CLI 化) — 通用链: 叙事/赛道判断 (宏观周期/减半/流动性/板块轮动) → 标的发现 (链上扫链/聪明钱跟单/新币/叙事映射) → 尽调 due diligence (代币经济学/解锁 unlock/团队/合约审计/honeypot 检测/流动性与持仓分布) → 风控前置 (仓位 sizing/最大回撤/止损/相关性) → 场所与执行 (CEX vs DEX、滑点/MEV/gas、限价 vs 市价、TWAP) → 持仓监控 (链上流向/巨鲸/资金费率/解锁日历/情绪指标) → 退出与复盘 (止盈分批/再平衡/记录交易日志); 子流派 SOP: 链上 degen 打新与 memecoin 流程、合约交易者的资金费率与清算地图、空投/撸毛 farming、套利与 MEV、被动配置与定投; (c) 工具栈 — 链上分析 (Nansen 聪明钱/Arkham 实体标注/Dune 自建仪表盘/Dexscreener & DEX Screener 新币/GMGN & Photon & BullX memecoin 终端/Etherscan & Solscan 区块浏览器/DeBank 钱包总览/Token Terminal 协议基本面/DefiLlama TVL/Glassnode & CryptoQuant 链上指标)、交易场所 (CEX: Binance/OKX/Bybit/Coinbase; 链上现货 DEX: Uniswap/Jupiter/Raydium/Aerodrome; 链上衍生品: Hyperliquid/GMX/dYdX)、钱包与安全 (MetaMask/Rabby/Phantom 热钱包、Ledger/Trezor 硬件冷钱包、Revoke.cash 授权管理、honeypot/合约扫描)、行情与图表 (TradingView、CoinGecko/CoinMarketCap)、信息与聚合 (Twitter/X、Telegram、DeFiLlama、RootData/ICO 日历、解锁日历 Token Unlocks)、自动化 (交易机器人、链上 bot/sniper、Telegram trading bot); (d) 知识正典 — 注意加密交易 canon 偏少且新: 通用交易/风控经典 (Edwin Lefèvre 'Reminiscences of a Stock Operator'、Van Tharp 'Trade Your Way to Financial Freedom' 仓位管理、Mark Douglas 'Trading in the Zone' 交易心理、Michael Mauboussin、Nassim Taleb 'Fooled by Randomness/Antifragile')、加密原生 (Bitcoin whitepaper 中本聪、'The Bitcoin Standard' Saifedean、Vitalik 博客与 Ethereum whitepaper、'DeFi and the Future of Finance'、Lyn Alden 宏观、a16z crypto 文章、Messari/Delphi/Bankless 研报)、链上分析方法 (Glassnode/CryptoQuant 教程、Nansen/Arkham/Dune 文档、Dune Analytics SQL)、交易方法论散见于 podcast/Substack/Twitter thread 而非书; (e) figures/流派 — 价值/基本面派 (Vitalik Buterin 以太坊、Hasu/Su Zhu(争议)、Arthur Hayes BitMEX 创始人/宏观+衍生品、Raoul Pal、Lyn Alden 宏观、Cobie/Jordan Fish UpOnly podcast、DeFi 研究 Bankless Ryan Adams/David Hoffman); 链上分析派 (Nansen Alex Svanevik、Arkham、Adam Cochran、Ansem(blknoiz06) 链上交易、Murad memecoin supercycle、链上侦探 ZachXBT 反诈); 合约/衍生品派 (Arthur Hayes、GCR(GiganticRebirth) 传奇合约、Pentoshi、CryptoCred 技术分析、Tyler Durden); meme/叙事派 (Ansem、Murad、Cobie、各 Solana memecoin KOL); 宏观/周期派 (Raoul Pal、Lyn Alden、PlanB stock-to-flow(争议)、Benjamin Cowen 数据/周期); 量化/系统化 (各匿名量化、Hyperliquid 生态); 中文圈 (链上分析/合约 KOL、币圈大 V、播客如 '无人之境'/'Web3 佛学院'、研究机构如 Foresight/PANews/律动 BlockBeats); 反诈/安全 (ZachXBT、SlowMist 慢雾、go+ 安全); (f) 行业话术/黑话 — 现货 spot / 合约 perps 永续 / 杠杆 leverage / 多空 long-short / 爆仓 liquidation 清算 / 资金费率 funding rate / 开多开空 / 止损 SL 止盈 TP / 仓位 position sizing / 满仓梭哈 ape in / 梭 / FOMO / FUD / 钻石手 diamond hands / 纸手 paper hands / 韭菜 / 镰刀 / 庄 / 出货 / 拉盘砸盘 / 插针 wick / 针 / 上车下车 / 埋伏 / 潜伏 / 链上 on-chain / 钱包 wallet / 地址 / 聪明钱 smart money / 巨鲸 whale / 跟单 copy-trade / 老鼠仓 / 貔貅盘 honeypot / 貔貅 / rug 跑路 rug-pull / 归零 / 土狗 (memecoin/小币) / 金狗 (暴涨百倍) / meme 币 / 叙事 narrative / 赛道 / 板块轮动 / 撸毛 撸空投 airdrop / 女巫 sybil / 交互 / 解锁 unlock / 砸盘解锁 / 代币经济学 tomomics / TVL / APY APR / 无常损失 IL / 滑点 slippage / MEV / 三明治 sandwich / gas / 抢跑 frontrun / 貔貅检测 / 授权 approve / 撤销授权 revoke / 私钥 助记词 seed phrase / 冷钱包 热钱包 / 自托管 / 减半 halving / 牛熊 / 山寨季 altseason / 比特币市占率 BTC.D / 山寨 alt / 主流币 / DeFi 暑期 / GM / WAGMI / NGMI / 归零归零 / PvP / Ponzi 庞氏; (g) 争议/批
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 GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.22.0+). Covers retriever selection (VectorRetriever, HybridRetriever, VectorCypherRetriever, HybridCypherRetriever, Text2CypherRetriever, ToolsRetriever), external vector DB retrievers (Weaviate, Pinecone, Qdrant), retrieval_query Cypher fragments, query_params, filters, GraphRAG pipeline wiring (GraphRAG + LLM + prompt), all LLM providers (OpenAI, Anthropic, Gemini/VertexAI, Bedrock, Cohere, Mistral, Ollama), embedder setup, index creation, token usage tracking, Cypher 25 SEARCH clause, and LangChain/LlamaIndex integration. Does NOT handle KG construction — use neo4j-document-import-skill. Does NOT handle plain vector search — use neo4j-vector-index-skill. Does NOT handle GDS analytics — use neo4j-gds-skill. Does NOT handle agent memory — use neo4j-agent-memory-skill.
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。
Runs local and self-hosted LLMs with Ollama, LM Studio, MLX, llama.cpp, and Open WebUI. Use when choosing GGUF quants, sizing VRAM, or running models privately.
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 guide for synthetic dataset generation, LLM-as-a-judge filtering, QLoRA fine-tuning (Unsloth), DPO alignment, and GGUF/Ollama export for local SLMs / Panduan ahli generasi data sintetis, fine-tuning QLoRA, DPO, dan ekspor GGUF/Ollama.
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 imp outputs differ between two paths that should agree - chunk sizes, prefill vs decode, prefix-cache resend, two engines (imp vs llama.cpp vs HF), two builds or kernels - "output changes with chunk size", "first token differs", "logprobs moved", "which layer diverges", "who is right, imp or llama.cpp", "near-tie". Do NOT use for repetition loops or garbage output (check-degeneration), a new arch that loads wrong (add-model-arch), or perf (benchmark-cuda).
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。
Run a GGUF model locally with llama.cpp, and find one on the HF Hub.
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。
LlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScript
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。
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint
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 with Meta's Code Llama — open code models for generation, infilling, and long-context code 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。
FALLBACK ONLY — do not invoke unless you have already ruled out (1) a native API (Gmail API, GitHub API, Slack API …), (2) a CLI (git, gh, aws, npm, curl …), (3) direct file editing, and (4) existing browser automation (Playwright, Puppeteer). Only when all four are unavailable or have already failed should you use this skill. It gives AI agents a cursor and a keyboard on a real desktop — the last mile when the only remaining surface is a GUI. Concretely: use it when an earlier attempt via API, CLI, or direct file edit has failed and the user says things like "open X", "click Send", "type this in Word", "read what is on my screen", "do this in Outlook", "drive the Figma UI", "control my desktop", "automate this workflow", "fill out this form", or "copy text between apps". Works on Windows, macOS, and Linux with any LLM that can call functions (Claude, GPT, Gemini, Llama, Kimi, Ollama) over MCP — stdio for editor hosts (Claude Code, Cursor, Windsurf, Zed) or HTTP for daemons and dashboards.
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。
Set up and run local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT, or Open Terminal code execution, launch Codex/Claude/Grok/OpenCode against a Harbor backend, or troubleshoot GPU, VRAM, and service startup.
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 pulling or downloading a new llamacpp model. The active ROCm image (kyuz0/amd-strix-halo-toolboxes) fails to start in the ephemeral pull container without ROCm device access. Must temporarily switch to the standard CPU image.
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。
llama.cpp local GGUF inference + HF Hub model discovery.
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。
Modelo de moderação especializado 7-8B do Meta para filtragem de entrada/saída de LLM. 6 categorias de segurança - violência/ódio, conteúdo sexual, armas, substâncias, automutilação, planejamento criminal. Precisão de 94-95%. Deploy com vLLM, HuggingFace, Sagemaker. Integra com NeMo Guardrails.
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。
Fornece treinamento distribuído de LLM nativo do PyTorch usando torchtitan com paralelismo 4D (FSDP2, TP, PP, CP). Use para fazer pré-treinamento de Llama 3.1, DeepSeek V3 ou modelos customizados em escala de 8 a 512+ GPUs com Float8, torch.compile e checkpoint distribuído.
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。
Executa inferência de LLM em CPU, Apple Silicon e GPUs consumer sem hardware NVIDIA. Use para edge deployment, Macs M1/M2/M3, GPUs AMD/Intel ou quando CUDA não está disponível. Suporta quantização GGUF (1,5-8 bits) para redução de memória e aceleração de 4-10× vs PyTorch em CPU.
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。
Formato GGUF e quantização llama.cpp para inferência eficiente em CPU/GPU. Use ao implantar modelos em hardware de consumidor, Apple Silicon, ou quando precisar de quantização flexível de 2-8 bits sem requisitos de GPU.
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。