Agent Skills

---

name: autoresearch

description: Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

---

name: brainstorming-research-ideas

description: Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.

---

name: creative-thinking-for-research

description: Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

---

name: evaluating-llms-harness

description: Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

---

name: huggingface-accelerate

description: 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.

---

name: ml-paper-writing

description: 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.

---

name: ml-training-recipes

description: 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.

---

name: nanoresearch-experiment

description: Generate a Python code skeleton from an experiment blueprint

---

name: nanoresearch-ideation

description: Search academic literature and generate research hypotheses

---

name: nanoresearch-planning

description: Produce an experiment blueprint from a research hypothesis

---

name: nanoresearch-writing

description: Draft a LaTeX research paper from all previous stage outputs

---

name: peft-fine-tuning

description: 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.

---

name: ray-data

description: Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

---

name: skypilot-multi-cloud-orchestration

description: 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.

---

name: unsloth

description: Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

---

name: oma-academic-writing

description: Draft and revise academic prose against a rubric, evidence, and citation requirements. Use for essays, reports, literature reviews, or academic style audits.

---

name: oma-architecture

description: Evaluate system boundaries and architectural tradeoffs. Use for architecture decisions, design reviews, and ADRs.

---

name: oma-backend

description: Implement server APIs, authentication, and application data access. Schema modeling and query tuning use oma-db.

---

name: oma-brainstorm

description: Explore goals, constraints, and alternative approaches before choosing a design. Use when the user requests ideation or design exploration.

---

name: oma-coordination

description: Coordinate assigned specialist tasks and handoffs manually. Use when supervising a multi-agent project step by step.

---

name: oma-db

description: Design schemas and migrations, tune queries, or plan vector retrieval and database operations. Application API implementation uses oma-backend.

---

name: oma-debug

description: Diagnose a reproducible failure, fix its cause, and verify the regression. Use for crashes, incorrect behavior, and failing tests.

---

name: oma-design

description: Define or review a visual system, DESIGN.md, or redesign direction. Use for typography, layout, color, motion, and interaction design decisions.

---

name: oma-dev-workflow

description: Configure development tasks, git hooks, CI/CD, or release automation. Use when creating or fixing a repository development workflow.