「科研」分类共 289 个 Skill，按仓库 star 排序。分类自动生成，仅供参考。
phuryn/pm-skills27kIdentify the Ideal Customer Profile (ICP) from research data with demographics, behaviors, JTBD, and needs. Use when defining your ICP, analyzing PMF survey data, or understanding who your best customers are.
teng-lin/notebooklm-py20kInstall, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API. Do not use for the generic Gemini API or unrelated content creation.
Orchestra-Research/AI-Research-SKILLs13kExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Orchestra-Research/AI-Research-SKILLs13kAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Orchestra-Research/AI-Research-SKILLs13kProvides 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.
Orchestra-Research/AI-Research-SKILLs13kFine-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.
Orchestra-Research/AI-Research-SKILLs13kExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Orchestra-Research/AI-Research-SKILLs13kFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Orchestra-Research/AI-Research-SKILLs13kExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
Orchestra-Research/AI-Research-SKILLs13kProvides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
Orchestra-Research/AI-Research-SKILLs13kNVIDIA'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.
Orchestra-Research/AI-Research-SKILLs13kParameter-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.
Orchestra-Research/AI-Research-SKILLs13kScalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
Orchestra-Research/AI-Research-SKILLs13kLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
Orchestra-Research/AI-Research-SKILLs13kSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
Orchestra-Research/AI-Research-SKILLs13kProvides 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.
Orchestra-Research/AI-Research-SKILLs13kProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Orchestra-Research/AI-Research-SKILLs13kProvides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Orchestra-Research/AI-Research-SKILLs13kProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
Orchestra-Research/AI-Research-SKILLs13kExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
AgriciDaniel/claude-ads9.8kResearch competitor paid-ad presence, messaging, creative, formats, landing pages, keyword and auction signals, transparent ad libraries, and strategic gaps across supported platforms. Use for competitor ads, ad libraries, ad spy, competitive PPC analysis, competitor creative, Google Ads Transparency, Meta Ad Library, or paid-media competitor research.
anbeime/skill7.7k内容创作者、技术写作员在撰写博客、深度文章或技术文档时，使用此技能可开启全流程写作协作。它能帮你研究资料、构建大纲、逐段打磨并自动添加引用，快速优化Hook，让你高效产出高质量内容，告别孤军奋战！
deanpeters/Product-Manager-Skills7.2kThe protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs.
deanpeters/Product-Manager-Skills7.2kResearch and draft a competitive battle card from public evidence — every claim labeled and sourced. Use when a rep needs a field-action card, not a research report.