Search
AI & LLM Engineering · Luciole-Studio/Misaka-Agent
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Evolve prompts/regex/SQL/code with Imbue's evolution loop. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 2 repos | ~2.1k | Automated safety check: Warn | MIT | 3 days ago |
| 2 | vLLM: high-throughput LLM serving, OpenAI API, quantization. | Luciole-Studio/ | 171 | 2 repos | ~2.3k | Automated safety check: Pass | MIT | 3 days ago |
| 3 | lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.). An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 2 repos | ~3.1k | Automated safety check: Pass | MIT | 3 days ago |
| 4 | HeartMuLa: Suno-like song generation from lyrics + tags. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 2 repos | ~1.6k | Automated safety check: Pass | MIT | 3 days ago |
| 5 | Delegate coding to OpenHands CLI (model-agnostic, LiteLLM). An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 2 repos | ~2.1k | Automated safety check: Pass | MIT | 3 days ago |
| 6 | Agent RAG and long-term memory with Pinecone. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~763 | Automated safety check: Pass | MIT | 3 days ago |
| 7 | Run PyTorch training across GPUs with minimal changes. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~2.3k | Automated safety check: Pass | MIT | 3 days ago |
| 8 | Speed up long-sequence transformer training and inference. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~2.7k | Automated safety check: Pass | MIT | 3 days ago |
| 9 | 9.Guidance Constrain LLM output with grammars; guarantee valid JSON. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~3.8k | Automated safety check: Pass | MIT | 3 days ago |
| 10 | 10.Pinecone Managed vector DB for production RAG and search. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~2.1k | Automated safety check: Pass | MIT | 3 days ago |
| 11 | 11.Pytorch Fsdp Fully sharded data-parallel training for large models. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~619 | Automated safety check: Pass | MIT | 3 days ago |
| 12 | 12.Qdrant Vector search engine for production RAG systems. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~3.4k | Automated safety check: Pass | MIT | 3 days ago |
| 13 | 13.Saelens Train sparse autoencoders to interpret model features. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~3.7k | Automated safety check: Pass | MIT | 3 days ago |
| 14 | 14.Simpo Reference-free preference alignment, simpler than DPO. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 15 | 15.Slime RL post-training for LLMs with Megatron and SGLang. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~2.7k | Automated safety check: Pass | MIT | 3 days ago |
| 16 | Text-to-image generation, inpainting, and img2img. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~3.2k | Automated safety check: Pass | MIT | 3 days ago |
| 17 | 17.Tensorrt LLM High-throughput LLM inference on NVIDIA GPUs. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~1.3k | Automated safety check: Pass | MIT | 3 days ago |
| 18 | 18.Torchtitan Pretrain LLMs at scale with PyTorch 4D parallelism. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~2.6k | Automated safety check: Pass | MIT | 3 days ago |
| 19 | TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~3.4k | Automated safety check: Pass | MIT | 3 days ago |
| 20 | 20.Peft Fine-tune large LLMs with LoRA on limited GPU memory. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~3k | Automated safety check: Pass | MIT | 3 days ago |
| 21 | 21.Blackbox Delegate coding tasks to the Blackbox AI multi-model CLI. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 22 | 22.Lambda Labs On-demand GPU cloud instances for ML training. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~3k | Automated safety check: Warn | MIT | 3 days ago |
