nanoresearch-ideation
The nanoresearch-ideation skill searches academic literature across arXiv and Semantic Scholar using multiple diverse queries, then analyzes retrieved papers to identify research gaps and generate novel hypotheses. Use this skill when exploring a research topic to discover unexplored areas and develop evidence-based research directions grounded in current literature.
git clone --depth 1 https://github.com/OpenRaiser/NanoResearch /tmp/nanoresearch-ideation && cp -r /tmp/nanoresearch-ideation/skills/nanoresearch-ideation ~/.claude/skills/nanoresearch-ideationSKILL.md
# Ideation Skill ## Purpose Search arXiv and Semantic Scholar for papers related to a research topic, perform gap analysis, and generate novel hypotheses. ## Tools Required - `search_arxiv`: Search arXiv for papers - `search_semantic_scholar`: Search Semantic Scholar for papers and citations ## Input - `topic`: The research topic or question to investigate ## Process 1. Generate 5-8 diverse search queries from the topic 2. Search arXiv and Semantic Scholar using each query 3. Deduplicate and rank papers by relevance 4. Analyze the collected papers to identify research gaps 5. Generate 2-4 novel hypotheses that address the identified gaps 6. Select the most promising hypothesis with justification ## Output Produces `papers/ideation_output.json` containing: - Retrieved papers with metadata - Survey summary - Gap analysis - Generated hypotheses - Selected hypothesis with rationale
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.
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.
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.
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.
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.
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.
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.
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.