nanoresearch-writing
The nanoresearch-writing skill transforms research planning and experimental results into a complete LaTeX paper draft. It parses ideation outputs, experimental blueprints, and results data to automatically generate structured sections including abstract, introduction, related work, methods, experiments, and conclusion. The skill produces publication-ready figures, tables, and a compiled PDF document. Use this when you have completed research ideation, experimental planning, and data collection and need to synthesize all outputs into a formatted academic paper.
git clone --depth 1 https://github.com/OpenRaiser/NanoResearch /tmp/nanoresearch-writing && cp -r /tmp/nanoresearch-writing/skills/nanoresearch-writing ~/.claude/skills/nanoresearch-writingSKILL.md
# Writing Skill ## Purpose Take all previous outputs (ideation, planning, experiment results) and produce a complete LaTeX paper draft with figures, tables, and bibliography. ## Tools Required - `generate_latex`: Generate and assemble LaTeX source files for each paper section - `compile_pdf`: Compile the LaTeX source into a PDF document - `generate_figure`: Produce publication-quality figures from experiment results ## Input - `ideation_output`: Path to `papers/ideation_output.json` from the ideation skill - `experiment_blueprint`: Path to `papers/experiment_blueprint.json` from the planning skill - `experiment_results`: Path to `experiments/` directory containing code and results from the experiment skill ## Process 1. Parse all upstream outputs to gather hypotheses, literature, experiment design, and results 2. Generate the paper outline following a standard structure (Abstract, Introduction, Related Work, Method, Experiments, Conclusion) 3. Draft the Abstract summarizing the problem, approach, and key findings 4. Draft the Introduction motivating the research question and stating contributions 5. Draft Related Work synthesizing the surveyed literature from the ideation stage 6. Draft the Method section describing the proposed approach in detail 7. Draft the Experiments section with dataset descriptions, baseline comparisons, and ablation results 8. Generate figures (performance plots, ablation charts, architecture diagrams) using `generate_figure` 9. Generate tables summarizing quantitative results 10. Draft the Conclusion with a summary of findings and future work directions 11. Compile the bibliography from all cited papers 12. Assemble the full LaTeX document using `generate_latex` 13. Compile to PDF using `compile_pdf` and verify the output ## Output Produces `papers/draft/` directory containing: - `main.tex`: Complete LaTeX source of the paper - `references.bib`: Bibliography file with all citations - `figures/`: Generated figures in PDF or PNG format - `tables/`: LaTeX table source files - `main.pdf`: Compiled PDF of the paper draft
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.