Add Skills Hub — universal skill search, install, and management from online registries

Implements the Hermes Skills Hub with agentskills.io spec compliance,
multi-registry skill discovery, security scanning, and user-driven
management via CLI and /skills slash command.

Core features:
- Security scanner (tools/skills_guard.py): 120 threat patterns across
  12 categories, trust-aware install policy (builtin/trusted/community),
  structural checks, unicode injection detection, LLM audit pass
- Hub client (tools/skills_hub.py): GitHub, ClawHub, Claude Code
  marketplace, and LobeHub source adapters with shared GitHubAuth
  (PAT + gh CLI + GitHub App), lock file provenance tracking, quarantine
  flow, and unified search across all sources
- CLI interface (hermes_cli/skills_hub.py): search, install, inspect,
  list, audit, uninstall, publish (GitHub PR), snapshot export/import,
  and tap management — powers both `hermes skills` and `/skills`

Spec conformance (Phase 0):
- Upgraded frontmatter parser to yaml.safe_load with fallback
- Migrated 39 SKILL.md files: tags/related_skills to metadata.hermes.*
- Added assets/ directory support and compatibility/metadata fields
- Excluded .hub/ from skill discovery in skills_tool.py

Updated 13 config/doc files including README, AGENTS.md, .env.example,
setup wizard, doctor, status, pyproject.toml, and docs.

skills/mlops/accelerate/SKILL.md

@@ -4,8 +4,11 @@ description: Simplest distributed training API. 4 lines to add distributed suppo
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Distributed Training, HuggingFace, Accelerate, DeepSpeed, FSDP, Mixed Precision, PyTorch, DDP, Unified API, Simple]
 dependencies: [accelerate, torch, transformers]
+metadata:
+  hermes:
+    tags: [Distributed Training, HuggingFace, Accelerate, DeepSpeed, FSDP, Mixed Precision, PyTorch, DDP, Unified API, Simple]
+
 ---
 
 # HuggingFace Accelerate - Unified Distributed Training

skills/mlops/audiocraft/SKILL.md

@@ -4,8 +4,11 @@ description: PyTorch library for audio generation including text-to-music (Music
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Multimodal, Audio Generation, Text-to-Music, Text-to-Audio, MusicGen]
 dependencies: [audiocraft, torch>=2.0.0, transformers>=4.30.0]
+metadata:
+  hermes:
+    tags: [Multimodal, Audio Generation, Text-to-Music, Text-to-Audio, MusicGen]
+
 ---
 
 # AudioCraft: Audio Generation

skills/mlops/axolotl/SKILL.md

@@ -4,8 +4,11 @@ description: Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 1
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Fine-Tuning, Axolotl, LLM, LoRA, QLoRA, DPO, KTO, ORPO, GRPO, YAML, HuggingFace, DeepSpeed, Multimodal]
 dependencies: [axolotl, torch, transformers, datasets, peft, accelerate, deepspeed]
+metadata:
+  hermes:
+    tags: [Fine-Tuning, Axolotl, LLM, LoRA, QLoRA, DPO, KTO, ORPO, GRPO, YAML, HuggingFace, DeepSpeed, Multimodal]
+
 ---
 
 # Axolotl Skill

skills/mlops/chroma/SKILL.md

@@ -4,8 +4,11 @@ description: Open-source embedding database for AI applications. Store embedding
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [RAG, Chroma, Vector Database, Embeddings, Semantic Search, Open Source, Self-Hosted, Document Retrieval, Metadata Filtering]
 dependencies: [chromadb, sentence-transformers]
+metadata:
+  hermes:
+    tags: [RAG, Chroma, Vector Database, Embeddings, Semantic Search, Open Source, Self-Hosted, Document Retrieval, Metadata Filtering]
+
 ---
 
 # Chroma - Open-Source Embedding Database

skills/mlops/clip/SKILL.md

@@ -4,8 +4,11 @@ description: OpenAI's model connecting vision and language. Enables zero-shot im
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Multimodal, CLIP, Vision-Language, Zero-Shot, Image Classification, OpenAI, Image Search, Cross-Modal Retrieval, Content Moderation]
 dependencies: [transformers, torch, pillow]
+metadata:
+  hermes:
+    tags: [Multimodal, CLIP, Vision-Language, Zero-Shot, Image Classification, OpenAI, Image Search, Cross-Modal Retrieval, Content Moderation]
+
 ---
 
 # CLIP - Contrastive Language-Image Pre-Training

skills/mlops/dspy/SKILL.md

@@ -4,8 +4,11 @@ description: Build complex AI systems with declarative programming, optimize pro
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Prompt Engineering, DSPy, Declarative Programming, RAG, Agents, Prompt Optimization, LM Programming, Stanford NLP, Automatic Optimization, Modular AI]
 dependencies: [dspy, openai, anthropic]
+metadata:
+  hermes:
+    tags: [Prompt Engineering, DSPy, Declarative Programming, RAG, Agents, Prompt Optimization, LM Programming, Stanford NLP, Automatic Optimization, Modular AI]
+
 ---
 
 # DSPy: Declarative Language Model Programming

skills/mlops/faiss/SKILL.md

@@ -4,8 +4,11 @@ description: Facebook's library for efficient similarity search and clustering o
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [RAG, FAISS, Similarity Search, Vector Search, Facebook AI, GPU Acceleration, Billion-Scale, K-NN, HNSW, High Performance, Large Scale]
 dependencies: [faiss-cpu, faiss-gpu, numpy]
+metadata:
+  hermes:
+    tags: [RAG, FAISS, Similarity Search, Vector Search, Facebook AI, GPU Acceleration, Billion-Scale, K-NN, HNSW, High Performance, Large Scale]
+
 ---
 
 # FAISS - Efficient Similarity Search

skills/mlops/flash-attention/SKILL.md

@@ -4,8 +4,11 @@ description: Optimizes transformer attention with Flash Attention for 2-4x speed
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Optimization, Flash Attention, Attention Optimization, Memory Efficiency, Speed Optimization, Long Context, PyTorch, SDPA, H100, FP8, Transformers]
 dependencies: [flash-attn, torch, transformers]
+metadata:
+  hermes:
+    tags: [Optimization, Flash Attention, Attention Optimization, Memory Efficiency, Speed Optimization, Long Context, PyTorch, SDPA, H100, FP8, Transformers]
+
 ---
 
 # Flash Attention - Fast Memory-Efficient Attention

skills/mlops/gguf/SKILL.md

@@ -4,8 +4,11 @@ description: GGUF format and llama.cpp quantization for efficient CPU/GPU infere
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [GGUF, Quantization, llama.cpp, CPU Inference, Apple Silicon, Model Compression, Optimization]
 dependencies: [llama-cpp-python>=0.2.0]
+metadata:
+  hermes:
+    tags: [GGUF, Quantization, llama.cpp, CPU Inference, Apple Silicon, Model Compression, Optimization]
+
 ---
 
 # GGUF - Quantization Format for llama.cpp

skills/mlops/grpo-rl-training/SKILL.md

@@ -4,8 +4,11 @@ description: Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Post-Training, Reinforcement Learning, GRPO, TRL, RLHF, Reward Modeling, Reasoning, DPO, PPO, Structured Output]
 dependencies: [transformers>=4.47.0, trl>=0.14.0, datasets>=3.2.0, peft>=0.14.0, torch]
+metadata:
+  hermes:
+    tags: [Post-Training, Reinforcement Learning, GRPO, TRL, RLHF, Reward Modeling, Reasoning, DPO, PPO, Structured Output]
+
 ---
 
 # GRPO/RL Training with TRL

skills/mlops/guidance/SKILL.md

@@ -4,8 +4,11 @@ description: Control LLM output with regex and grammars, guarantee valid JSON/XM
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Prompt Engineering, Guidance, Constrained Generation, Structured Output, JSON Validation, Grammar, Microsoft Research, Format Enforcement, Multi-Step Workflows]
 dependencies: [guidance, transformers]
+metadata:
+  hermes:
+    tags: [Prompt Engineering, Guidance, Constrained Generation, Structured Output, JSON Validation, Grammar, Microsoft Research, Format Enforcement, Multi-Step Workflows]
+
 ---
 
 # Guidance: Constrained LLM Generation

skills/mlops/huggingface-tokenizers/SKILL.md

@@ -4,8 +4,11 @@ description: Fast tokenizers optimized for research and production. Rust-based i
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Tokenization, HuggingFace, BPE, WordPiece, Unigram, Fast Tokenization, Rust, Custom Tokenizer, Alignment Tracking, Production]
 dependencies: [tokenizers, transformers, datasets]
+metadata:
+  hermes:
+    tags: [Tokenization, HuggingFace, BPE, WordPiece, Unigram, Fast Tokenization, Rust, Custom Tokenizer, Alignment Tracking, Production]
+
 ---
 
 # HuggingFace Tokenizers - Fast Tokenization for NLP

skills/mlops/instructor/SKILL.md

@@ -4,8 +4,11 @@ description: Extract structured data from LLM responses with Pydantic validation
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Prompt Engineering, Instructor, Structured Output, Pydantic, Data Extraction, JSON Parsing, Type Safety, Validation, Streaming, OpenAI, Anthropic]
 dependencies: [instructor, pydantic, openai, anthropic]
+metadata:
+  hermes:
+    tags: [Prompt Engineering, Instructor, Structured Output, Pydantic, Data Extraction, JSON Parsing, Type Safety, Validation, Streaming, OpenAI, Anthropic]
+
 ---
 
 # Instructor: Structured LLM Outputs

skills/mlops/lambda-labs/SKILL.md

@@ -4,8 +4,11 @@ description: Reserved and on-demand GPU cloud instances for ML training and infe
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Infrastructure, GPU Cloud, Training, Inference, Lambda Labs]
 dependencies: [lambda-cloud-client>=1.0.0]
+metadata:
+  hermes:
+    tags: [Infrastructure, GPU Cloud, Training, Inference, Lambda Labs]
+
 ---
 
 # Lambda Labs GPU Cloud

skills/mlops/llama-cpp/SKILL.md

@@ -4,8 +4,11 @@ description: Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Inference Serving, Llama.cpp, CPU Inference, Apple Silicon, Edge Deployment, GGUF, Quantization, Non-NVIDIA, AMD GPUs, Intel GPUs, Embedded]
 dependencies: [llama-cpp-python]
+metadata:
+  hermes:
+    tags: [Inference Serving, Llama.cpp, CPU Inference, Apple Silicon, Edge Deployment, GGUF, Quantization, Non-NVIDIA, AMD GPUs, Intel GPUs, Embedded]
+
 ---
 
 # llama.cpp

skills/mlops/llava/SKILL.md

@@ -4,8 +4,11 @@ description: Large Language and Vision Assistant. Enables visual instruction tun
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [LLaVA, Vision-Language, Multimodal, Visual Question Answering, Image Chat, CLIP, Vicuna, Conversational AI, Instruction Tuning, VQA]
 dependencies: [transformers, torch, pillow]
+metadata:
+  hermes:
+    tags: [LLaVA, Vision-Language, Multimodal, Visual Question Answering, Image Chat, CLIP, Vicuna, Conversational AI, Instruction Tuning, VQA]
+
 ---
 
 # LLaVA - Large Language and Vision Assistant

skills/mlops/lm-evaluation-harness/SKILL.md

@@ -4,8 +4,11 @@ description: Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Evaluation, LM Evaluation Harness, Benchmarking, MMLU, HumanEval, GSM8K, EleutherAI, Model Quality, Academic Benchmarks, Industry Standard]
 dependencies: [lm-eval, transformers, vllm]
+metadata:
+  hermes:
+    tags: [Evaluation, LM Evaluation Harness, Benchmarking, MMLU, HumanEval, GSM8K, EleutherAI, Model Quality, Academic Benchmarks, Industry Standard]
+
 ---
 
 # lm-evaluation-harness - LLM Benchmarking

skills/mlops/ml-paper-writing/SKILL.md

@@ -4,8 +4,11 @@ description: Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL,
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Academic Writing, NeurIPS, ICML, ICLR, ACL, AAAI, COLM, LaTeX, Paper Writing, Citations, Research]
 dependencies: [semanticscholar, arxiv, habanero, requests]
+metadata:
+  hermes:
+    tags: [Academic Writing, NeurIPS, ICML, ICLR, ACL, AAAI, COLM, LaTeX, Paper Writing, Citations, Research]
+
 ---
 
 # ML Paper Writing for Top AI Conferences

skills/mlops/modal/SKILL.md

@@ -4,8 +4,11 @@ description: Serverless GPU cloud platform for running ML workloads. Use when yo
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Infrastructure, Serverless, GPU, Cloud, Deployment, Modal]
 dependencies: [modal>=0.64.0]
+metadata:
+  hermes:
+    tags: [Infrastructure, Serverless, GPU, Cloud, Deployment, Modal]
+
 ---
 
 # Modal Serverless GPU

skills/mlops/nemo-curator/SKILL.md

@@ -4,8 +4,11 @@ description: GPU-accelerated data curation for LLM training. Supports text/image
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Data Processing, NeMo Curator, Data Curation, GPU Acceleration, Deduplication, Quality Filtering, NVIDIA, RAPIDS, PII Redaction, Multimodal, LLM Training Data]
 dependencies: [nemo-curator, cudf, dask, rapids]
+metadata:
+  hermes:
+    tags: [Data Processing, NeMo Curator, Data Curation, GPU Acceleration, Deduplication, Quality Filtering, NVIDIA, RAPIDS, PII Redaction, Multimodal, LLM Training Data]
+
 ---
 
 # NeMo Curator - GPU-Accelerated Data Curation

skills/mlops/outlines/SKILL.md

@@ -4,8 +4,11 @@ description: Guarantee valid JSON/XML/code structure during generation, use Pyda
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Prompt Engineering, Outlines, Structured Generation, JSON Schema, Pydantic, Local Models, Grammar-Based Generation, vLLM, Transformers, Type Safety]
 dependencies: [outlines, transformers, vllm, pydantic]
+metadata:
+  hermes:
+    tags: [Prompt Engineering, Outlines, Structured Generation, JSON Schema, Pydantic, Local Models, Grammar-Based Generation, vLLM, Transformers, Type Safety]
+
 ---
 
 # Outlines: Structured Text Generation

skills/mlops/peft/SKILL.md

@@ -4,8 +4,11 @@ description: Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Fine-Tuning, PEFT, LoRA, QLoRA, Parameter-Efficient, Adapters, Low-Rank, Memory Optimization, Multi-Adapter]
 dependencies: [peft>=0.13.0, transformers>=4.45.0, torch>=2.0.0, bitsandbytes>=0.43.0]
+metadata:
+  hermes:
+    tags: [Fine-Tuning, PEFT, LoRA, QLoRA, Parameter-Efficient, Adapters, Low-Rank, Memory Optimization, Multi-Adapter]
+
 ---
 
 # PEFT (Parameter-Efficient Fine-Tuning)

skills/mlops/pinecone/SKILL.md

@@ -4,8 +4,11 @@ description: Managed vector database for production AI applications. Fully manag
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [RAG, Pinecone, Vector Database, Managed Service, Serverless, Hybrid Search, Production, Auto-Scaling, Low Latency, Recommendations]
 dependencies: [pinecone-client]
+metadata:
+  hermes:
+    tags: [RAG, Pinecone, Vector Database, Managed Service, Serverless, Hybrid Search, Production, Auto-Scaling, Low Latency, Recommendations]
+
 ---
 
 # Pinecone - Managed Vector Database

skills/mlops/pytorch-fsdp/SKILL.md

@@ -4,8 +4,11 @@ description: Expert guidance for Fully Sharded Data Parallel training with PyTor
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Distributed Training, PyTorch, FSDP, Data Parallel, Sharding, Mixed Precision, CPU Offloading, FSDP2, Large-Scale Training]
 dependencies: [torch>=2.0, transformers]
+metadata:
+  hermes:
+    tags: [Distributed Training, PyTorch, FSDP, Data Parallel, Sharding, Mixed Precision, CPU Offloading, FSDP2, Large-Scale Training]
+
 ---
 
 # Pytorch-Fsdp Skill

skills/mlops/pytorch-lightning/SKILL.md

@@ -4,8 +4,11 @@ description: High-level PyTorch framework with Trainer class, automatic distribu
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [PyTorch Lightning, Training Framework, Distributed Training, DDP, FSDP, DeepSpeed, High-Level API, Callbacks, Best Practices, Scalable]
 dependencies: [lightning, torch, transformers]
+metadata:
+  hermes:
+    tags: [PyTorch Lightning, Training Framework, Distributed Training, DDP, FSDP, DeepSpeed, High-Level API, Callbacks, Best Practices, Scalable]
+
 ---
 
 # PyTorch Lightning - High-Level Training Framework

skills/mlops/qdrant/SKILL.md

@@ -4,8 +4,11 @@ description: High-performance vector similarity search engine for RAG and semant
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [RAG, Vector Search, Qdrant, Semantic Search, Embeddings, Similarity Search, HNSW, Production, Distributed]
 dependencies: [qdrant-client>=1.12.0]
+metadata:
+  hermes:
+    tags: [RAG, Vector Search, Qdrant, Semantic Search, Embeddings, Similarity Search, HNSW, Production, Distributed]
+
 ---
 
 # Qdrant - Vector Similarity Search Engine

skills/mlops/saelens/SKILL.md

@@ -4,8 +4,11 @@ description: Provides guidance for training and analyzing Sparse Autoencoders (S
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Sparse Autoencoders, SAE, Mechanistic Interpretability, Feature Discovery, Superposition]
 dependencies: [sae-lens>=6.0.0, transformer-lens>=2.0.0, torch>=2.0.0]
+metadata:
+  hermes:
+    tags: [Sparse Autoencoders, SAE, Mechanistic Interpretability, Feature Discovery, Superposition]
+
 ---
 
 # SAELens: Sparse Autoencoders for Mechanistic Interpretability

skills/mlops/segment-anything/SKILL.md

@@ -4,8 +4,11 @@ description: Foundation model for image segmentation with zero-shot transfer. Us
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Multimodal, Image Segmentation, Computer Vision, SAM, Zero-Shot]
 dependencies: [segment-anything, transformers>=4.30.0, torch>=1.7.0]
+metadata:
+  hermes:
+    tags: [Multimodal, Image Segmentation, Computer Vision, SAM, Zero-Shot]
+
 ---
 
 # Segment Anything Model (SAM)

skills/mlops/simpo/SKILL.md

@@ -4,8 +4,11 @@ description: Simple Preference Optimization for LLM alignment. Reference-free al
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Post-Training, SimPO, Preference Optimization, Alignment, DPO Alternative, Reference-Free, LLM Alignment, Efficient Training]
 dependencies: [torch, transformers, datasets, trl, accelerate]
+metadata:
+  hermes:
+    tags: [Post-Training, SimPO, Preference Optimization, Alignment, DPO Alternative, Reference-Free, LLM Alignment, Efficient Training]
+
 ---
 
 # SimPO - Simple Preference Optimization

skills/mlops/slime/SKILL.md

@@ -4,8 +4,11 @@ description: Provides guidance for LLM post-training with RL using slime, a Mega
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Reinforcement Learning, Megatron-LM, SGLang, GRPO, Post-Training, GLM]
 dependencies: [sglang-router>=0.2.3, ray, torch>=2.0.0, transformers>=4.40.0]
+metadata:
+  hermes:
+    tags: [Reinforcement Learning, Megatron-LM, SGLang, GRPO, Post-Training, GLM]
+
 ---
 
 # slime: LLM Post-Training Framework for RL Scaling

skills/mlops/stable-diffusion/SKILL.md

@@ -4,8 +4,11 @@ description: State-of-the-art text-to-image generation with Stable Diffusion mod
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Image Generation, Stable Diffusion, Diffusers, Text-to-Image, Multimodal, Computer Vision]
 dependencies: [diffusers>=0.30.0, transformers>=4.41.0, accelerate>=0.31.0, torch>=2.0.0]
+metadata:
+  hermes:
+    tags: [Image Generation, Stable Diffusion, Diffusers, Text-to-Image, Multimodal, Computer Vision]
+
 ---
 
 # Stable Diffusion Image Generation

skills/mlops/tensorrt-llm/SKILL.md

@@ -4,8 +4,11 @@ description: Optimizes LLM inference with NVIDIA TensorRT for maximum throughput
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Inference Serving, TensorRT-LLM, NVIDIA, Inference Optimization, High Throughput, Low Latency, Production, FP8, INT4, In-Flight Batching, Multi-GPU]
 dependencies: [tensorrt-llm, torch]
+metadata:
+  hermes:
+    tags: [Inference Serving, TensorRT-LLM, NVIDIA, Inference Optimization, High Throughput, Low Latency, Production, FP8, INT4, In-Flight Batching, Multi-GPU]
+
 ---
 
 # TensorRT-LLM

skills/mlops/torchtitan/SKILL.md

@@ -4,8 +4,11 @@ description: Provides PyTorch-native distributed LLM pretraining using torchtita
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Model Architecture, Distributed Training, TorchTitan, FSDP2, Tensor Parallel, Pipeline Parallel, Context Parallel, Float8, Llama, Pretraining]
 dependencies: [torch>=2.6.0, torchtitan>=0.2.0, torchao>=0.5.0]
+metadata:
+  hermes:
+    tags: [Model Architecture, Distributed Training, TorchTitan, FSDP2, Tensor Parallel, Pipeline Parallel, Context Parallel, Float8, Llama, Pretraining]
+
 ---
 
 # TorchTitan - PyTorch Native Distributed LLM Pretraining

skills/mlops/trl-fine-tuning/SKILL.md

@@ -4,8 +4,11 @@ description: Fine-tune LLMs using reinforcement learning with TRL - SFT for inst
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Post-Training, TRL, Reinforcement Learning, Fine-Tuning, SFT, DPO, PPO, GRPO, RLHF, Preference Alignment, HuggingFace]
 dependencies: [trl, transformers, datasets, peft, accelerate, torch]
+metadata:
+  hermes:
+    tags: [Post-Training, TRL, Reinforcement Learning, Fine-Tuning, SFT, DPO, PPO, GRPO, RLHF, Preference Alignment, HuggingFace]
+
 ---
 
 # TRL - Transformer Reinforcement Learning

skills/mlops/unsloth/SKILL.md

@@ -4,8 +4,11 @@ description: Expert guidance for fast fine-tuning with Unsloth - 2-5x faster tra
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Fine-Tuning, Unsloth, Fast Training, LoRA, QLoRA, Memory-Efficient, Optimization, Llama, Mistral, Gemma, Qwen]
 dependencies: [unsloth, torch, transformers, trl, datasets, peft]
+metadata:
+  hermes:
+    tags: [Fine-Tuning, Unsloth, Fast Training, LoRA, QLoRA, Memory-Efficient, Optimization, Llama, Mistral, Gemma, Qwen]
+
 ---
 
 # Unsloth Skill

skills/mlops/vllm/SKILL.md

@@ -4,8 +4,11 @@ description: Serves LLMs with high throughput using vLLM's PagedAttention and co
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [vLLM, Inference Serving, PagedAttention, Continuous Batching, High Throughput, Production, OpenAI API, Quantization, Tensor Parallelism]
 dependencies: [vllm, torch, transformers]
+metadata:
+  hermes:
+    tags: [vLLM, Inference Serving, PagedAttention, Continuous Batching, High Throughput, Production, OpenAI API, Quantization, Tensor Parallelism]
+
 ---
 
 # vLLM - High-Performance LLM Serving

skills/mlops/weights-and-biases/SKILL.md

@@ -4,8 +4,11 @@ description: Track ML experiments with automatic logging, visualize training in
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [MLOps, Weights And Biases, WandB, Experiment Tracking, Hyperparameter Tuning, Model Registry, Collaboration, Real-Time Visualization, PyTorch, TensorFlow, HuggingFace]
 dependencies: [wandb]
+metadata:
+  hermes:
+    tags: [MLOps, Weights And Biases, WandB, Experiment Tracking, Hyperparameter Tuning, Model Registry, Collaboration, Real-Time Visualization, PyTorch, TensorFlow, HuggingFace]
+
 ---
 
 # Weights & Biases: ML Experiment Tracking & MLOps

skills/mlops/whisper/SKILL.md

@@ -4,8 +4,11 @@ description: OpenAI's general-purpose speech recognition model. Supports 99 lang
 version: 1.0.0
 author: Orchestra Research
 license: MIT
-tags: [Whisper, Speech Recognition, ASR, Multimodal, Multilingual, OpenAI, Speech-To-Text, Transcription, Translation, Audio Processing]
 dependencies: [openai-whisper, transformers, torch]
+metadata:
+  hermes:
+    tags: [Whisper, Speech Recognition, ASR, Multimodal, Multilingual, OpenAI, Speech-To-Text, Transcription, Translation, Audio Processing]
+
 ---
 
 # Whisper - Robust Speech Recognition