Development skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

1.24k repo starsObserved in 1 repos
Development

blackbox

Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

1.24k repo starsObserved in 1 repos
Development

chroma

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

1.24k repo starsObserved in 1 repos
Development

distributed-llm-pretraining-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

1.24k repo starsObserved in 1 repos
Development

faiss

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

1.24k repo starsObserved in 1 repos
Development

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

1.24k repo starsObserved in 1 repos
Development

github-pr-workflow

Full pull request lifecycle — create branches, commit changes, open PRs, monitor CI status, auto-fix failures, and merge. Works with gh CLI or falls back to git + GitHub REST API via curl.

1.24k repo starsObserved in 1 repos
Development

github-repo-management

Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

1.24k repo starsObserved in 1 repos
Development

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

1.24k repo starsObserved in 1 repos
Development

huggingface-accelerate

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

1.24k repo starsObserved in 1 repos
Development