2,894 件 ・ 関連度順
概要と使いどころ
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.
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。
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
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。
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
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。
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.
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。
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
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。
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
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。
MNN CPU 后端性能归因分支（`skills/cpu/` 下，另一分支是 `cpu/kernel` kernel 开发）。按五层（Runtime 线程 / Executor 调度 / Layout 内存 / Dispatch 函数表 / Kernel ISA）定位瓶颈，含 bound 类型判定、op 级实验回路、跨框架 op 对 op 对比、跨层不一致的事后定位，以及 ARM / x86_64 / RISC-V 三侧「我到底跑在哪条 ISA 路径上」的诊断面。CPU 上算子或 LLM prefill/decode 慢、线程数或内存占用异常、出现性能回归、要与外部推理框架逐算子对比时使用。
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 MNN tests / benchmarks on host or real devices. Covers two parallel tracks — (1) the regression / CI suite (static checks, host-side tests, on-device Android arm64 matrix via ./test.sh + test_stages.json) and (2) one-command iOS real-device LLM benchmarking (prefill/decode tok/s, branch comparison). Use when the user asks to run the tests, run CI, smoke-test a build, verify a change on a device, benchmark on-device (Android or iPhone/iPad), or add / select / retune a test stage.
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。
This skill should be used when the user asks to "test the harness", "run integration tests", "validate features with real API", "test with real model calls", "run agent loop tests", "verify end-to-end", or needs to verify OpenHarness features on a real codebase with actual LLM calls.
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 the current worktree as a production-shaped local dev instance with web, Slack, or both, on a real LLM + Postgres. Each developer uses their own set of Slack apps from their own machine's pool store, so many worktrees (yours and a teammate's) can run reachable at once without colliding. Use when asked to /dev-instance, "spin this up so I can QA it in Slack", or "let me test your branch end to end".
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。
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.
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。
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
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。
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
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。
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
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。
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
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。
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
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。
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
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。
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
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。
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
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 guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
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。
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
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。
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 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。