Top Rated
The most starred skills loved by the community. Quality guaranteed!
dotnet-core-expert
by Jeffallan
Use when building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. Invoke for Entity Framework Core, CQRS with MediatR, JWT authentication, AOT compilation.
architecture-designer
by Jeffallan
Use when designing new system architecture, reviewing existing designs, or making architectural decisions. Invoke for system design, architecture review, design patterns, ADRs, scalability planning.
fine-tuning-expert
by Jeffallan
Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parameter-efficient methods, dataset preparation, or model adaptation.
graphql-architect
by Jeffallan
Use when designing GraphQL schemas, implementing Apollo Federation, or building real-time subscriptions. Invoke for schema design, resolvers with DataLoader, query optimization, federation directives.
monitoring-expert
by Jeffallan
Use when setting up monitoring systems, logging, metrics, tracing, or alerting. Invoke for dashboards, Prometheus/Grafana, load testing, profiling, capacity planning.
embedded-systems
by Jeffallan
Use when developing firmware for microcontrollers, implementing RTOS applications, or optimizing power consumption. Invoke for STM32, ESP32, FreeRTOS, bare-metal, power optimization, real-time systems.
django-expert
by Jeffallan
Use when building Django web applications or REST APIs with Django REST Framework. Invoke for Django models, ORM optimization, DRF serializers, viewsets, authentication with JWT.
simpo-training
by Orchestra-Research
Simple 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.
cli-developer
by Jeffallan
Use when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for CLI design, argument parsing, interactive prompts, progress indicators, shell completions.
database-optimizer
by Jeffallan
Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites, configuration tuning, partitioning strategies, lock contention resolution.
kotlin-specialist
by Jeffallan
Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose. Invoke for Flow API, KMP projects, Ktor servers, DSL design, sealed classes.
fullstack-guardian
by Jeffallan
Use when implementing features across frontend and backend, building APIs with UI, or creating end-to-end data flows. Invoke for feature implementation, API development, UI building, cross-stack work.
secure-code-guardian
by Jeffallan
Use when implementing authentication/authorization, securing user input, or preventing OWASP Top 10 vulnerabilities. Invoke for authentication, authorization, input validation, encryption, OWASP Top 10 prevention.
angular-architect
by Jeffallan
Use when building Angular 17+ applications with standalone components or signals. Invoke for enterprise apps, RxJS patterns, NgRx state management, performance optimization, advanced routing.
devops-engineer
by Jeffallan
Use when setting up CI/CD pipelines, containerizing applications, or managing infrastructure as code. Invoke for pipelines, Docker, Kubernetes, cloud platforms, GitOps.
ml-paper-writing
by Orchestra-Research
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
miles-rl-training
by Orchestra-Research
Provides 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.
quantizing-models-bitsandbytes
by Orchestra-Research
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
nemo-evaluator-sdk
by Orchestra-Research
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
unsloth
by Orchestra-Research
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
fine-tuning-with-trl
by Orchestra-Research
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.
sglang
by Orchestra-Research
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
pytorch-lightning
by Orchestra-Research
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
prompt-engineer
by Jeffallan
Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.