Skill Claude CodeCodex
Bioinformatics workflows — RNA-seq and scRNA-seq analysis pipelines, enrichment analysis (GO/KEGG/GSEA), variant interpretation, protein structure analysis, and key database queries. Use when analyzing genomic, transcriptomic, or proteomic data.
Skill Claude CodeCodex
Experimental and ecological biology — experimental design with controls/replicates, biology-specific statistical tests, diversity indices, cell biology assays (IC50, ELISA, flow cytometry), imaging analysis, and survival analysis. Use when working with biological experimental data.
Skill Claude CodeCodex
Causal inference methods — DAG-based causal thinking, distinguishing observational from experimental data, IV, DiD, RDD, propensity score matching, and sensitivity analysis. Use when making causal claims from data.
Skill Claude CodeCodex
Cheminformatics and computational chemistry — SMILES/InChI parsing, molecular property prediction, spectroscopy interpretation, DFT workflow, materials characterization (XRD, SAXS), and key chemistry databases. Use when analyzing chemical or materials data.
Skill Claude CodeCodex
CS theory for research — algorithm complexity analysis, data structure selection, rigorous benchmarking discipline, distributed systems fundamentals, and formal verification concepts. Use when reasoning about algorithmic correctness, efficiency, or system design.
Skill Claude CodeCodex
Computer vision workflows — image data characterization, preprocessing and augmentation, architecture selection (CNN vs ViT), and evaluation metrics (mAP, IoU, FID, SSIM). Use when working with image or video data.
Skill Claude CodeCodex
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5…
Skill Claude CodeCodex
Engineering systems analysis — control theory (PID, transfer functions, Bode plots), signal processing, reliability engineering, engineering optimization (LP/MIP), sensor data processing, and FEA concepts. Use when working with engineering, control, or sensor data.
Skill Claude CodeCodex
Controlled experiment design — hypothesis formation, statistical power and sample size estimation, confound control, ablation structure, baseline selection, and reproducibility requirements. Use when designing research experiments to ensure valid, reproducible results.
Skill Claude CodeCodex
Comprehensive EDA on scientific data files — structure, content, quality, and characteristics analysis across 200+ formats. Use when analyzing any data file to understand its structure, quality, and downstream analysis recommendations.
Skill Claude CodeCodex
Find pretrained models on HuggingFace Hub by task, keyword, size, or downloads. Use when you need a base checkpoint for fine-tuning (LoRA/PEFT/AFT) or a zero-shot baseline. Returns model IDs ready for AutoModel.frompretrained(...).
Skill Claude CodeCodex
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), build a BibTeX file, and draft Introduction +…
Skill Claude CodeCodex
Materials science analysis — crystal structure, phase diagrams, mechanical and electronic properties, characterization techniques (XRD, SEM/TEM, AFM, XPS), and high-throughput computational workflows with pymatgen. Use when working with materials data.
Skill Claude CodeCodex
Formal mathematics for scientific computing — symbolic computation (sympy), numerical linear algebra, optimization (convex/non-convex), information theory, and numerical precision issues. Use when working with mathematical derivations, proofs, or rigorous numerical analysis.
Skill Claude CodeCodex
Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, novel plot types, or publication-quality PNG/PDF/SVG export. For quick statistical plots use seaborn.
Skill Claude CodeCodex
Model evaluation framework — cross-validation strategies, metric selection by task type, baseline requirements, ablation design, and train/val/test discipline. Use for all ML experiments before reporting results.
Skill Claude CodeCodex
Graph and network analysis — graph construction, centrality measures, community detection, graph ML basics, and visualization. Use when data has relational/network structure.
Skill Claude CodeCodex
Text data analysis for NLP research — dataset characterization, preprocessing decision guide, tokenization choices, embedding selection, and evaluation metrics (BLEU, ROUGE, BERTScore, perplexity). Use when analyzing or processing text datasets.
Skill Claude CodeCodex
Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimentallog.md, template.tex, conferenceguidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator…
Skill Claude CodeCodex
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper…
Skill Claude CodeCodex
Physics simulation and computational analysis — ODE/PDE solvers, molecular dynamics, Monte Carlo methods, signal processing, error propagation, and unit management. Use when working with physical simulation data or running computational physics experiments.
Skill Claude CodeCodex
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimentallog.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER…
Skill Claude CodeCodex
Creative research ideation and exploration for open-ended brainstorming, interdisciplinary connections, challenging assumptions, and identifying research gaps. Best for early-stage research planning without specific observations yet.
Skill Claude CodeCodex
Evaluate scientific claims and evidence quality, assess experimental design validity, identify biases and confounders, and apply evidence grading frameworks (GRADE, Cochrane Risk of Bias).