NeVibeCode · 676 items
Skills for Science and research
Skills for Science and research: what each one does, an install command and example prompts.
literature-search-biorxiv skill Search bioRxiv and medRxiv preprints by DOI or date range. Use it to filter papers by category, author, or keywords.
CX Codex +1
2,500installs
nanogpt skill This skill guides work with a small PyTorch GPT implementation. Use it to study transformers, train on Shakespeare, or adapt the model to your own text.
CX Codex +1
956installs
transformer-lens-interpretability skill This skill guides TransformerLens research on transformer internals, from activation caching and attention analysis to activation patching experiments.
CX Codex +1
954installs
pyvene-interventions skill This skill guides causal intervention experiments on PyTorch models using pyvene. It covers causal tracing and activation patching on neural architectures.
CX Codex +1
952installs
sparse-autoencoder-training skill Provides patterns to train and analyze Sparse Autoencoders using SAELens. Useful for finding interpretable features in transformer activations.
CX Codex +1
950installs
citation-verification skill A skill that sets rules for verifying citations in academic writing, so you don't ship invented or mismatched references.
CX Codex +1
1,400installs
torchforge-rl-training skill This skill guides PyTorch-native agentic RL with torchforge. Use it for SFT, GRPO, custom loss functions, and distributed training experiments.
CX Codex +1
946installs
nnsight-remote-interpretability skill Guides neural network interpretability and intervention using nnsight locally or remotely via NDIF. Useful for experimenting with 70B+ models without local GPU clusters.
CX Codex +1
945installs
presenting-conference-talks skill Generates Beamer LaTeX and PPTX presentation slides from a compiled research paper with speaker notes. Useful when preparing oral, spotlight, or invited conference talks.
CX Codex +1
913installs
academic-pptx skill Guides content structure and visual standards for academic slide decks, from thesis defenses to conference talks.
CX Codex +1
1,100installs
ml-training-recipes skill PyTorch training recipes for neural networks, covering training loops, Muon and AdamW optimizer setups, mixed precision, and scaling laws.
CX Codex +1
912installs
systems-paper-writing skill Paragraph-level structural blueprint for writing 10–12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Organizes page budgets and section flows.
CX Codex +1
908installs
clinical-trials-database skill Queries ClinicalTrials.gov via REST API v2 to search studies by condition, drug, status, or phase. Saves filtered study data directly to JSON.
CX Codex +1
2,400installs
deeppapernote skill DeepPaperNote reads scientific papers and turns them into structured Markdown research notes for Obsidian vaults with evidence checks and figure plans.
CX Codex +1
1,500installs
fine-tuning-serving-openpi skill Workflows for fine-tuning and serving Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5). Guides setup, norm stats calculation, and policy inference servers.
CX Codex +1
861installs
fine-tuning-openvla-oft skill Guides fine-tuning and evaluation of OpenVLA-OFT robot action policies. Use it for LIBERO or ALOHA workflows with continuous action heads.
CX Codex +1
861installs
paper-polish skill Polishes an existing academic draft: grammar, flow, tone, and Chinese-to-English rewriting. The author's meaning stays intact.
CX Codex +1
532installs
blog-notebooklm skill Queries your Gemini Notebook documents via a browser session and returns source-grounded answers. Useful when you need cited research from your notebook library inside the agent.
CX Codex +1
2,500installs
human-protein-atlas-database skill Retrieves semi-quantitative protein expression levels and subcellular localisation data from the Human Protein Atlas. Useful for validating human protein presence across tissues.
CX Codex +1
2,200installs
opentargets-database skill This skill gives your agent GraphQL access to the Open Targets Platform: target-disease associations, drug data and tractability scores.
CX Codex +1
2,200installs
ensembl-database skill Resolves gene symbols into ENSG, ENST and ENSP IDs, pulls sequences and predicts variant effects with VEP. Useful when genomic data lives in your terminal.
CX Codex +1
2,200installs
clinvar-database skill Queries ClinVar for clinical significance, review status, and pathogenicity of genomic variants. Useful for variant interpretation and benchmark controls.
CX Codex +1
2,200installs
chembl-database skill A skill that lets your agent pull molecules, targets, bioactivity, approved drugs and structure matches from ChEMBL.
CX Codex +1
2,200installs
alphagenome-single-variant-analysis skill A skill that runs one genetic variant in chr:pos:ref>alt form through the AlphaGenome API and reports expression, chromatin and histone effects.
CX Codex +1
2,200installs
uniprot-database skill Retrieves protein metadata, function annotations, and sequences from UniProtKB, UniParc, and UniRef. Useful for mapping database identifiers and streaming entries.
CX Codex +1
2,200installs
openfda-database skill Queries, counts and downloads records from the openFDA API. Use it for FDA safety events, recalls, labels, NDC lookups and regulatory data searches.
CX Codex +1
2,200installs
pymol skill A PyMOL skill that renders protein and molecular structures, runs alignments, and measures distances or contacts. Useful when you already have a structure file and need an image or a number.
CX Codex +1
2,200installs
ncbi-sequence-fetch skill Fetches protein and nucleotide sequences from NCBI databases via E-utilities. It queries records by accession, gene name, locus tag, PubMed ID, or patent.
CX Codex +1
2,200installs
pubchem-database skill A skill that wires your agent into PubChem: resolves compounds by name, CID or SMILES and pulls properties, hazard data and bioactivity.
CX Codex +1
2,200installs
alphafold-database-fetch-and-analyze skill Pulls AlphaFold predicted structures by UniProt ID and works out what they mean: pLDDT confidence, disordered regions, rigid domain boundaries.
CX Codex +1
2,200installs
pdb-database skill Searches and downloads experimental 3D structures of biomolecules from RCSB PDB using sequence similarity, structure comparisons, or chemical attributes.
CX Codex +1
2,200installs
paper-writer skill A skill that writes paper prose from the author's own notes, results and drafts, for a paragraph or a whole manuscript. Every claim has to trace to a source.
CX Codex +1
500installs
deep-research skill Runs a topic investigation in the shape of a survey paper: pins the questions, searches from several angles, checks every reference and answers each question in the final report. Useful before you commit to a topic.
CX Codex +1
496installs
unibind-database skill This skill queries UniBind for experimentally validated transcription-factor binding sites and downloads BED or FASTA coordinates for local analysis.
CX Codex +1
2,100installs
ucsc-conservation-and-tfbs skill Pulls evolutionary conservation scores (phyloP, phastCons) and transcription factor binding sites out of the UCSC Genome Browser. Handy when you are reading non-coding variants.
CX Codex +1
2,100installs
encode-ccres-database skill Queries the ENCODE Registry of cis-regulatory elements using the SCREEN GraphQL API and REST API. It identifies promoters or enhancers across cell types.
CX Codex +1
2,100installs
gnomad-database skill This skill queries gnomAD for variant frequencies, gene constraint metrics, and regional variant searches. Use it for genetics research workflows.
CX Codex +1
2,100installs
quickgo-database skill Queries the QuickGO and ECO REST API to link genes to biological processes, molecular functions and cellular components. Useful when working through gene annotations.
CX Codex +1
2,100installs
jaspar-database skill Queries the JASPAR database for transcription factor binding profiles. Useful when fetching PFM or PWM matrices and converting gene names into stable matrix IDs.
CX Codex +1
2,100installs
gtex-database skill Retrieves RNA expression and eQTL data from GTEx across 54 non-diseased human tissue sites. Use it to query genes, variants, or tissue-specific expression.
CX Codex +1
2,100installs
241–280 of 676
