Search
Research & Science · By Orchestra-Research
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Guides training and analyzing sparse autoencoders with SAELens to break neural network activations into interpretable features, including superposition and monosemanticity studies. | Orchestra-Research/ | 13k | 5 repos | ~3.2k | Automated safety check: Pass | MIT | 3 mo ago |
| 2 | Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis. | Orchestra-Research/ | 13k | 3 repos | ~3k | Automated safety check: Pass | MIT | 3 mo ago |
| 3 | Compress large language models using knowledge distillation from teacher to student models. | Orchestra-Research/ | 13k | 2 repos | ~3.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 4 | Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. | Orchestra-Research/ | 13k | 2 repos | ~3.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 5 | Guides causal experiments on PyTorch models with pyvene, such as causal tracing, activation patching and interchange intervention training, to test how a model works. | Orchestra-Research/ | 13k | 2 repos | ~3.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 6 | PyTorch training reference: architecture choice by data type, scaling rules, a training loop, optimizer and learning-rate choices, and fixes for loss spikes or OOM. | Orchestra-Research/ | 13k | 1 repo | ~2.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 7 | Paragraph-level blueprint for 10-12 page systems papers aimed at OSDI, SOSP, ASPLOS, NSDI and EuroSys, with page budgets, writing patterns, checklists and templates. | Orchestra-Research/ | 13k | 1 repo | ~3.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 8 | Offers ten ideation frameworks for exploring new research directions, stress-testing half-formed ideas and finding gaps when you are stuck or changing fields. | Orchestra-Research/ | 13k | 2 repos | ~4.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 9 | Turns papers, repositories, logs or notes into an Agent-Native Research Artifact with claims, concepts, configs, an exploration graph and grounded evidence. | Orchestra-Research/ | 13k | — | ~3.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 10 | Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling. | Orchestra-Research/ | 13k | — | ~3.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 11 | Generates Beamer LaTeX PDF and editable PPTX slides from a compiled paper, with speaker notes and an optional talk script, sized to four talk lengths. | Orchestra-Research/ | 13k | — | ~2.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 12 | NVIDIA's runtime safety framework for LLM applications. An agent skill from Orchestra-Research/AI-Research-SKILLs. | Orchestra-Research/ | 13k | 2 repos | ~1.9k | Automated safety check: Warn | MIT | 3 mo ago |
