Data & Analytics

Reads a company's filed XBRL numbers from SEC EDGAR and plainly summarizes what changed quarter over quarter.

Acts as a French DGFIP tax inspector, auditing a company's books across 9 axes and issuing a reassessment report with legal grounds and penalty estimates.

Runs a French statutory-audit program (NEP, 7 phases) over annual accounts and issues a structured audit opinion report.

Turns Claude Code transcript tokens into a manager-readable cost report (HTML/PDF/CSV/JSON) showing cost per completed outcome and what mistakes cost.

Searches scientific literature through the BGPT MCP server and returns 25+ structured fields extracted from full-text papers.

Guides Claude to infer transcription factor–target gene networks from expression data using arboreto's GRNBoost2 and GENIE3.

Turns your full claude-mem project timeline into a narrative "Journey Into [Project]" development-history report.

Sizes queued-work ops teams with Erlang-C math: required FTE, utilization risk bands, and a 12-month ramp- and attrition-aware hiring sequence.

Runs bounded one-hop and endpoint-pinned two-hop TRAPI queries against the NCATS Translator ARAX API and returns typed, provenance-rich biomedical relationships.

A rigorous workflow skill for planning, validating, restarting, and analyzing FluidSim 0.9 pseudospectral CFD runs with explicit numerical and HPC safety gates.

Scans protein sequences for N-/O-glycosylation sites and guides glycan engineering strategies for antibodies and vaccine antigens.

Runs DiffDock/DiffDock-L to predict protein–small-molecule binding poses and interprets the confidence scores.

Runs the standard phylogenetics workflow — MAFFT alignment, IQ-TREE 2/FastTree inference, and ETE3 tree analysis and rendering.

A guided skill for using histolab to detect tissue, extract tiles, and normalize stains from whole slide pathology images.

Lets your agent query Paperzilla projects, recommendation feeds, and canonical papers via the `pz` CLI, then summarize and give feedback.

An expert skill for building, tuning, evaluating, and reporting right-censored and competing-risk survival models with scikit-survival, without data leakage.

A skill that guides you through defining single-, multi-, and many-objective problems in pymoo, computing Pareto fronts, and picking a final solution.

Guides Claude to query and analyze the 200M+ cell CZ CELLxGENE Census of public single-cell and spatial transcriptomics data without downloading full datasets.

Combines lab-animal welfare readouts into a single RELSA severity score and forecasts humane endpoints with ARIMA plus KDE-derived severity zones.

Give it a gene symbol, genomic region, or FASTA and it calls hosted DNA language models to predict promoters, splice sites, enhancer activity, chromatin state, expression, and gene annotations.