New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Search

Research & Science · Orchestra-Research/AI-Research-SKILLs

12 skills found.
Product:

Skills

Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName

Search results
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1
1.Sparse Autoencoder Training with SAELens

Guides training and analyzing sparse autoencoders with SAELens to break neural network activations into interpretable features, including superposition and monosemanticity studies.

Orchestra-Research/AI-Research-SKILLs13k5 repos~3.2kAutomated safety check: PassMIT3 mo ago
2
2.TransformerLens Interpretability

Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis.

Orchestra-Research/AI-Research-SKILLs13k3 repos~3kAutomated safety check: PassMIT3 mo ago
3
3.Knowledge Distillation

Compress large language models using knowledge distillation from teacher to student models.

Orchestra-Research/AI-Research-SKILLs13k2 repos~3.4kAutomated safety check: PassMIT3 mo ago
4
4.Model Pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT.

Orchestra-Research/AI-Research-SKILLs13k2 repos~3.4kAutomated safety check: PassMIT3 mo ago
5
5.pyvene Causal Interventions

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/AI-Research-SKILLs13k2 repos~3.5kAutomated safety check: PassMIT3 mo ago
6
6.ML Training Recipes

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/AI-Research-SKILLs13k1 repo~2.8kAutomated safety check: PassMIT3 mo ago
7
7.Systems Paper Writing Blueprint

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/AI-Research-SKILLs13k1 repo~3.5kAutomated safety check: PassMIT3 mo ago
8
8.Research Idea Brainstorming

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/AI-Research-SKILLs13k2 repos~4.8kAutomated safety check: PassMIT3 mo ago
9
9.ARA Research Compiler

Turns papers, repositories, logs or notes into an Agent-Native Research Artifact with claims, concepts, configs, an exploration graph and grounded evidence.

Orchestra-Research/AI-Research-SKILLs13k—~3.7kAutomated safety check: PassMIT3 mo ago
10
10.Cosmos Policy Evaluation

Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling.

Orchestra-Research/AI-Research-SKILLs13k—~3.7kAutomated safety check: PassMIT3 mo ago
11
11.Conference Talk Slides from Papers

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/AI-Research-SKILLs13k—~2.5kAutomated safety check: PassMIT3 mo ago
12
12.Nemo Guardrails

NVIDIA's runtime safety framework for LLM applications. An agent skill from Orchestra-Research/AI-Research-SKILLs.

Orchestra-Research/AI-Research-SKILLs13k2 repos~1.9kAutomated safety check: WarnMIT3 mo ago

Browse