Marketplace
Everything your AI needs, in one place.
Ready-made agents, skills, personas, prompts, templates and tools. Each one is checked before it goes live, works with any model, and installs in a click. Rate what you use so the best rises to the top.
- 146.7K
- listings
- 1
- installs
- 0
- reviews
- 40.4K
- publishers
A service that does a whole job for you - research, coding, support - and reports back.
Step-by-step instructions an AI follows for one kind of task. Install once, reuse everywhere.
A voice and set of rules layered onto any model: tone, audience, do's and don'ts.
A ready-to-use prompt with fill-in-the-blank variables and notes on when it works best.
A complete routing setup - models, rules and settings - in one file you can apply in a minute.
A single function an AI can call: a calculator, a search, a database lookup.
A language model endpoint with its price, speed and quality declared so the router can compare it.
optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory iss
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU re
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or
hqq-quantization
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deployin
tao-run-automl
Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), Wa
tilegym-improve-cutile-kernel-perf
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints
PostgreSQL Database Administration
Comprehensive PostgreSQL database administration skill for customer support tech enablement, covering database design, optimization, performance tuning, backup/recovery, and advanced query techniques
r8-analyzer
Analyzes Android build files and R8 keep rules to identify redundancies, broad package-wide rules, and rules that subsume library consumer keep rules. Use when developers want to optimize their app's
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
awq-quantization
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference
quantizing-models-bitsandbytes
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 fo
optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory iss
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU re
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or
hqq-quantization
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deployin
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, M
Asset Manager
Organize design assets, optimize images and fonts, maintain brand asset libraries, implement version control for assets, and enforce naming conventions. Keep design assets organized and production-rea
context-optimization
Improve context efficiency through context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity
performance-expert
Backend, database, and infrastructure performance expert covering API response times, query and index optimization, N+1 elimination, caching and background jobs, server profiling, and build/asset deli
prompt-engineering
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, debug agent behavior, or design content ge
build-optimization
Build system optimization covering compilation, caching, incremental builds, and developer tooling. Use when improving build times, configuring CI pipelines, or designing developer tools.
evaluator-optimizer
Iterative refinement workflow for polishing code, documentation, or designs through systematic evaluation and improvement cycles. Use when refining drafts into production-grade quality.
python-performance-optimization
Python performance optimization patterns using profiling, algorithmic improvements, and acceleration techniques. Use when optimizing slow Python code, reducing memory usage, or improving application t
Find
Search or browse by kind. Every card shows who made it, how many people installed it and what they think.
Install
One click. You get a manifest the router understands, plus copy-paste snippets for the CLI, Python and YAML.
Rate and publish
Leave a star rating after you have used it. Made something useful? Publish it - free listings go live immediately.
Prefer the terminal? osr stack apply registry://starter installs the starter template.