Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
deep-reference
Use when validating deep references
agent-sh/agnix 169
-
with-context-agent
Use when testing valid context and agent configuration
agent-sh/agnix 169
-
with-model
Use when testing valid model configuration
agent-sh/agnix 169
-
code-review
Use when user asks to review code for quality and security issues.
agent-sh/agnix 169
-
with-argument-hint
Use when greeting users
agent-sh/agnix 169
-
with-custom-agent
Use when testing custom agent validation
agent-sh/agnix 169
-
fork-with-instructions
Use when analyzing code quality
agent-sh/agnix 169
-
deploy-prod
Use when deploying to production environment
agent-sh/agnix 169
-
with-hooks
Use when testing valid hooks
agent-sh/agnix 169
-
autocontext
Iterative strategy generation and evaluation system. Use when the user wants to evaluate agent output quality, run improvement loops, queue tasks for background evaluation, check run status, or discover available scenarios. Provides LLM-based judging with rubric-driven scoring.
greyhaven-ai/autocontext 729
-
grid-ctf-ops
Operational knowledge for the grid_ctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging grid_ctf strategies.
greyhaven-ai/autocontext 729
-
agentfield-multi-reasoner-builder
Architect and ship a complete multi-agent backend system on AgentField from a one-line user request. Use when the user asks to build, scaffold, design, or ship an agent system, multi-agent pipeline, reasoner network, AgentField project, financial reviewer, research agent, compliance agent, or any LLM composition that should outperform LangChain/CrewAI/AutoGen — especially when they want a runnable Docker-compose stack and a working curl smoke test.
Agent-Field/agentfield 1,413
-
agentfield-multi-reasoner-builder
Architect and ship a complete multi-agent backend system on AgentField from a one-line user request. Use when the user asks to build, scaffold, design, or ship an agent system, multi-agent pipeline, reasoner network, AgentField project, financial reviewer, research agent, compliance agent, or any LLM composition that should outperform LangChain/CrewAI/AutoGen — especially when they want a runnable Docker-compose stack and a working curl smoke test.
Agent-Field/agentfield 1,413
-
swe-af
Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.
Agent-Field/SWE-AF 697
-
nanoresearch-experiment
Generate a Python code skeleton from an experiment blueprint
OpenRaiser/NanoResearch 689
-
nanoresearch-planning
Produce an experiment blueprint from a research hypothesis
OpenRaiser/NanoResearch 689
-
nanoresearch-ideation
Search academic literature and generate research hypotheses
OpenRaiser/NanoResearch 689
-
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
OpenRaiser/NanoResearch 689
-
peft-fine-tuning
Parameter-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.
OpenRaiser/NanoResearch 689
-
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
OpenRaiser/NanoResearch 689
-
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, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
OpenRaiser/NanoResearch 689
-
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
OpenRaiser/NanoResearch 689
-
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.
OpenRaiser/NanoResearch 689
-
ml-paper-writing
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. 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.
OpenRaiser/NanoResearch 689