#SKILL.md

#Agents42#MCP16#RAG15#Developer Tools14#YouTube14#Claude Code11#Retrieval11#AI Engineer9#MoE9#Multi-Agent Systems9#Reinforcement Learning9#Multimodal8#VLM8#Coding Agents7#Hugging Face7#On-device AI7#Open Weights7#Reasoning7#Agent Evaluation6#Agent Harness6#Agent Skills6#Agent Systems6#Benchmark6#Codex6#Context Engineering6#Embeddings6#Long Context6#Tool Use6#Agentic AI5#AI Agents5#arXiv5#Claude5#NVIDIA5#OCR5#Qwen5#Qwen35#Reranking5#Agent Memory4#Agent Workflows4#AI Safety4#Data Pipeline4#Document Intelligence4#Foundation Models4#Gemma4#GRPO4#Image Generation4#Inference Optimization4#LLM Architecture4#LLM Systems4#Open Source4#RLVR4#SKILL.md4#Synthetic Data4#Vision-Language Models4#Workflow Automation4#Agent Training3#Anthropic3#Auto Research3#Design Systems3#Edge AI3#Fine-Tuning3#KV Cache3#LLM Evaluation3#LLM Serving3#LoRA3#MLOps3#Prompt Engineering3#PyTorch3#Quantization3#Qwen3-VL3#Test-Time Scaling3#Transformer3#Vector Search3#Video Generation3#VLA3#Agent OS2#Agentic Coding2#Agentic Search2#AI for Science2#Apple Silicon2#Argilla2#Backpropagation2#Computer Vision2#Contrastive Learning2#CUDA2#Data Curation2#Data Infrastructure2#Deep Research2#DeepSeek2#Diffusion2#Distillation2#Document AI2#Gemini2#GEPA2#Hallucination2#Harness Engineering2#Information Retrieval2#Knowledge Distillation2#Knowledge Graph2#Language Modeling2#LLM Agents2#LLM Pretraining2#LLM Training2#LLMOps2#Local-First2#Mechanistic Interpretability2#Microsoft Research2#MLX2#Mobile LLM2#Model Training2#Multi-Agent2#Multimodal Agents2#Nemotron2#Observability2#Obsidian2#OpenAI2#Post-Training2#Privacy2#Product Strategy2#Quant Finance2#Reasoning Models2#Research Engineering2#RF-DETR2#Roboflow2#Robotics2#SAM2#Security2#Skill Optimization2#Small Language Models2#Sparse Models2#Structured Extraction2#Survey2#Tabular Data2#TDD2#Training Systems2#Unsloth2#Verification2#Video Understanding2#Vision Transformer2#Vision-Language Model2#vLLM2#World Model2#Accessibility1#Activation Steering1#AG-UI1#Agent Engineering1#Agent Orchestration1#Agent Protocols1#Agent Runtime1#Agent Safety1#Agent UI1#AgentBench1#Agentic Design1#Agentic Reasoning1#Agentic RL1#Agentic Security1#Agentic Self-Instruct1#AI Co-Mathematician1#AI Coding1#AI Coding Agents1#AI for Mathematics1#AI Infrastructure1#AI Pricing1#AI SaaS1#AI-Q1#Allen AI1#Alyx1#AMD1#Analog Hardware1#ANN1#Apple Intelligence1#AppWorld1#Arize1#Assistive Technology1#Associative Memory1#Attention1#Attention Supervision1#Attractor Models1#Autodata1#Autogenesis1#AutoML1#Autonomous Driving1#AutoResearchClaw1#Baidu1#Benchmarks1#BI1#Biologically Plausible Learning1#Browser Agents1#Calamari1#Camera Control1#Career1#Chain-of-Thought1#Chunking1#Claude Opus1#ClawHub1#Clinical AI1#ClinSeekAgent1#Code Evolution1#Code Generation1#Code Intelligence1#Code Models1#Codex CLI1#Cognitive Loafing1#Computer Use1#Computer Use Agent1#Consulting1#Content Moderation1#Context Compression1#Context Distillation1#Context Graphs1#Context Learning1#Continual Learning1#Continuous Generation1#CopilotKit1#Ctx2Skill1#CyberGym1#Data Annotation1#Data Sanitization1#Data Security1#Data-Centric AI1#Dataset Ops1#DCI-Agent1#Deep Search1#DeepEval1#DeepSeek-OCR1#DELEGATE-521#Delegated Work1#Delivery1#Delta-Mem1#Demand-Driven Context1#Design Research1#Design Tools1#DESIGN.md1#Desktop Apps1#Diffusion Language Models1#Diffusion LLM1#Diffusion LM1#Diffusion Transformer1#Direct Corpus Interaction1#Distilabel1#Distributed Training1#Document Editing1#DPO1#DSPy1#Dynin-Omni1#EDA1#Edge Inference1#Effect1#EHR1#Elastic1#ElevenLabs1#ELF1#Enterprise Agents1#Enterprise AI1#ERNIE 4.51#ETL1#Evaluation1#EXAONE1#ExecuTorch1#Fara-7B1#FastAPI1#FastEmbed1#Financial Time Series1#Fintech1#Fixed-point1#FlashAttention1#Flow Matching1#Forward-Forward Algorithm1#Frontend AI1#FrontierMath1#Gemma 41#Generative UI1#Google I/O1#GPT-5.51#GPU Optimization1#GQA1#GraphRAG1#Grounding1#Guard Models1#Guardrail1#Guardrails1#GUI Agents1#HarnessAudit1#HeavySkill1#Hermes Agent1#Hidden-State Probing1#Historical Documents1#HNSW1#Hope1#Horizon Generalization1#Human Feedback1#Human-in-the-loop1#HumanLayer1#Hunyuan1#Hy-MT21#Hybrid SSM1#Hypernetworks1#Hyperparameter Transfer1#ICLR 20261#Image Editing1#Implicit Differentiation1#In-Context Learning1#Incremental Processing1#Inference1#Inference Providers1#Inference Scaffolding1#Inference Systems1#Inference-Time Compute1#Inference-Time Feedback1#Inpainting1#Interpretability1#Jina AI1#Kanban1#Karpathy1#Knowledge Bases1#Knowledge Graphs1#Knowledge Management1#Korean AI1#Korean LLM1#Kronos1#Lance1#Latent Reasoning1#Latent Space1#Layout Analysis1#Leaderboard1#Learning Rate Transfer1#LFM21#Life-Harness1#Liquid AI1#LiteLLM1#LiteVLA-H1#LLM Depth1#LLM Fundamentals1#LLM Infrastructure1#LLM Internals1#LLM Ops1#LLM Reasoning1#Local Agents1#Local AI1#Local LLM1#Locally AI1#Logic Synthesis1#Long-Horizon1#Long-Horizon Agents1#LongLive-2.01#LongMemEval1#Looped Transformers1#Machine Translation1#Mamba1#Matt Pocock1#MCP Apps1#MCTS1#MDASH1#Megatron-LM1#Memory Systems1#Meta AI1#Meta-Optimization1#MetaAgent-X1#Microsoft1#Microsoft Security1#Mid-Training1#MiMo1#MiniCPM-V1#MinT1#Mistral1#Mistral AI1#ML Engineering1#MMProLong1#Mobile Agents1#MobileLLM-R11#Model Adaptation1#Model Compression1#Model Pruning1#Model Studio1#Moderation1#ModernBERT1#Modular AI1#Monetization1#MongoDB1#MTEB1#Multi-Agent Debate1#Multi-LoRA1#Multimodal AI1#Multimodal Diffusion1#Multimodal Embeddings1#Multimodal LLM1#Multimodal Models1#Multimodal Retrieval1#Multimodal RL1#Multimodal Safety1#Multimodal Search1#Multimodal Training1#NanoGPT1#Native Unified Model1#Native VLM1#Natural Language Autoencoders1#NEO-unify1#Neo4j1#Nested Learning1#Netflix1#Neural Architecture Search1#Neural Networks1#NeurIPS 20251#nGPT1#NL-Refer1#Normalized Transformer1#NVFP41#NVIDIA NeMo1#Object Detection1#OCR-Memory1#Olympiad Math1#Omnimodal1#OmniShotCut1#On-policy Distillation1#OneManCompany1#OneVL1#Online Memory1#Open Models1#Open Training Recipe1#OpenAI API1#OpenCompass1#OpenSearch-VL1#Optimizers1#Ouroboros1#PageIndex1#Paper Reproduction1#Parameter-Efficient Tuning1#Pare-Bench1#PEFT1#PII Detection1#Pixel Embeddings1#Plugins1#PowerPoint1#Preparedness1#Presentation AI1#Presentation Tools1#Priming1#PriorVLA1#Proactive Agents1#Procrustes Alignment1#Product1#Productivity1#Prompt Optimization1#Prompt Tuning1#Pytest1#QAT1#Query Rewriting1#Qwen-Image-2.01#Qwen2.5-VL1#Qwen3-Next1#React1#Reasoning Model1#Recursive Reasoning1#Reinforced Agent1#Research1#Research Workflow1#Residual Stream1#Risk Assessment1#Robot Learning1#RoPE1#Routing1#Rust1#Safety1#SANA-WM1#Sandcastle1#Segmentation1#Self-Consistency1#Self-Evolution1#Self-Generated Data1#Self-Play1#Self-Speculation1#Self-Training1#Semantic Layer1#SenseNova-U11#Sentence Transformers1#Sequence Classification1#SGLang1#Shot Boundary Detection1#Skill Evolution1#Skill Governance1#Skill Retrieval1#Skill-RAG1#Skills1#SmallCode1#Sparse Attention1#Sparse Autoencoder1#Sparse MoE1#Specification First1#Speculative Decoding1#Speech1#SQL1#SRA-Bench1#State Space Model1#Stripe1#SU-011#Swarm Intelligence1#SWE-Bench1#SWIM1#Sycophancy1#TabEmbed1#TabPFN1#Talent Market1#TEDS1#Terminal-Bench1#Text Embeddings1#Text Rendering1#Text-to-SQL1#Time Series Forecasting1#TinyLoRA1#Token Classification1#Tokenizer1#Tool Calling1#Tool-Integrated Reasoning1#TorchAO1#Training Recipes1#Trajectory Audit1#Transformers1#Triton1#Tuna-21#TypeScript1#UI Engineering1#UI Inspiration1#UI over MCP1#Usage-Based Billing1#User Simulation1#Validation1#Vector Database1#Vibe Coding1#Video Editing1#Vision-Language Alignment1#Vulnerability Discovery1#Web Agents1#WorkOS1#X2SAM1#ZeroEntropy1#Zyphra1#μP1

Agent Systems

SkillsVote는 에이전트 스킬을 추천에서 진화까지 거버넌스한다

SkillsVote는 100만 규모의 SKILL.md 생태계에서 어떤 스킬을 노출하고, 실행 결과를 어떻게 귀속하며, 어떤 경험만 라이브러리에 반영할지를 하나의 수명주기 문제로 다루는 에이전트 스킬 거버넌스 프레...

Sangmin Lee2026.05.20

Agent Systems

Agent Skills는 코딩 에이전트에 시니어 엔지니어링 절차를 주입한다

addyosmani/agent-skills는 22개 SKILL.md, 7개 slash command, 3개 전문 persona를 묶어 AI 코딩 에이전트가 spec→plan→build→test→review→shi...

Sangmin Lee2026.05.13

Agent Systems

SSL은 에이전트 스킬을 문서에서 구조로 끌어낸다

Peking University의 SSL 논문은 SKILL.md 중심의 텍스트 스킬을 스케줄링·구조·논리 3계층 표현으로 정규화해, 스킬 검색과 사전 위험 검토를 더 기계 친화적으로 만들 수 있음을 보여준다.

Sangmin Lee2026.05.07

Agent Systems

SkillsMP는 흩어진 SKILL.md 생태계를 검색 가능한 마켓플레이스로 바...

SkillsMP는 GitHub 전역에 흩어진 SKILL.md 기반 에이전트 스킬을 수집해 의미 검색, 직군 분류, 카테고리 탐색, API 접근, 설치 가이드까지 한 화면으로 묶어 Claude Code·Codex·...

Sangmin Lee2026.05.06