aristoteleo

Skills for rare disease case support: ontology-first normalization/retrieval and the clinical genetics consult report format contract (structure + theme). Load the relevant skill file when performing the matching task.

Scenario router for paper-writing tasks. Use after root triage to select paper submission, journal article, conference paper, grant proposal, lab report, group report, talk/workshop, or revision-response behavior.

Routing and workflow skill family for paper-writing tasks. Covers manuscript drafting, journal and conference papers, grant proposals, lab reports, group-meeting reports, talks, workshop notes, reviewer rebuttals, academic HTML/PDF/LaTeX output with editable-block contracts, citation grounding, evidence checking, and pre-submission quality gates.

Workflow phases for paper-writing tasks: triage, material inventory, research question, literature review, paper outline, data analysis summary, figure storyline, reader testing, and finalize packet. Each phase is a short contract — read the relevant rows for the current task only.

Section-level writing skill for evidence-bound academic prose: IMRaD papers, grants, reports, talks, and response letters. Indexes section-specific templates (abstract, introduction, method, results, discussion) and pre-submission quality protocols (claim-evidence, reviewer rubric, response letter).

Skills for opening and driving agent-controllable visualization components in the Pantheon UI sidebar — interactive viewers the agent can open, control, and read back. Viewers: Vitessce (spatial / single- cell omics), Viv (bioimage / microscopy), plus agent-generated apps.

Skills for querying and downloading data from genomic, transcriptomic, 3D-genome, and cancer-genomics databases. Covers programmatic access to public repositories, gene annotation, sequence retrieval, processed functional-genomics tracks, Hi-C / Micro-C contact matrices, TCGA-style cohorts, and large-scale single-cell data.

Skills for single-cell and spatial omics data analysis. Best practices, code snippets, and workflows for the scverse ecosystem.

Perform in silico gene perturbation on a dynamo vector-field AnnData to predict cell fate diversion after single or multi-gene activation or suppression, then visualize the results with streamline or quiver plots. Use when running dyn.pd.perturbation, predicting transcription factor perturbation effects, simulating gene knockdown or overexpression in scRNA-seq data, reproducing 502_perturbation_tutorial.ipynb, or choosing among pertubation_method, perturb_mode, and emb_basis branches.

Compute least action paths (LAP) between hematopoietic or general cell types in a dynamo vector-field AnnData, then rank transcription factors by MSD along each path and evaluate predictions via ROC analysis. Use when running dyn.pd.compute_cell_type_transitions, predicting optimal cell fate conversion trajectories, prioritizing transcription factor cocktails for cell reprogramming, or reproducing the 501_lap_tutorial.ipynb workflow on scNT-seq or metabolic-labeling data.

Run or adapt a conventional spliced/unspliced RNA velocity workflow in `dynamo`, including `Preprocessor` preprocessing, `dynamics`, low-dimensional `cell_velocities`, `VectorField`, topology / potential analysis, confidence-based correction, fate prediction, and optional animation. Use when analyzing conventional scRNA-seq `AnnData`, reproducing or adapting tutorial notebooks such as `200_zebrafish.ipynb`, or selecting between preprocessing, kinetics, vector-field, and fate stages for a reusable velocity pipeline.

Run downstream differential-geometry analysis on a `dynamo` vector-field `AnnData`, including velocity, acceleration, curvature, Jacobian, regulatory-network, ddhodge pseudotime, and state-graph branches. Use when adapting the `403_Differential_geometry.ipynb` tutorial, extending a conventional spliced/unspliced RNA velocity workflow into vector calculus, or choosing among `method`, `mode`, `sampling`, `formula`, `adjmethod`, or `gene_order_method` branches.

Convert Ensembl-style gene IDs to gene symbols in `dynamo` with `dynamo.preprocessing.convert2gene_symbol` or `dynamo.preprocessing.convert2symbol`, including human and zebrafish IDs, version-suffix stripping, `AnnData.var_names` updates, and optional preprocessing handoff. Use when adapting `docs/tutorials/notebooks/110_geneid_convert_tutorial.ipynb`, standardizing `adata.var_names`, mapping Ensembl IDs to symbols, or doing identifier cleanup before a `Preprocessor` recipe.

Compare lineage appearance timing and its regulators on a precomputed `dynamo` vector-field `AnnData` using topography, graph potentials, Jacobian, and vector-calculus outputs. Use when checking whether one lineage appears earlier than its peers, curating fixed points, analyzing regulator pairs on a downstream-ready vector field, or adapting `400_tutorial_hsc_dynamo_megakaryocytes_appearance.ipynb`.

Run or adapt a one-shot total RNA velocity workflow in `dynamo` for metabolic-labeling or scNT-seq `AnnData`, including monocle preprocessing with an optional curated gene list, grouped moments by labeling time, Model-2 `dynamics`, `calculate_velocity_alpha_minus_gamma_s`, low-dimensional projection with `cell_velocities`, and optional streamline or phase-portrait plotting. Use when converting tutorials such as `301_tutorial_hsc_velocity.ipynb`, or when choosing between `one_shot_method` branches like `sci_fate` and `combined` and projection `method` branches like `cosine` and `pearson`.

Convert pseudotime into reusable `dynamo` RNA velocity outputs on an `AnnData` object, then optionally continue into vector field, topology / potential, fate, and animation without relying on measured spliced/unspliced kinetics. Use when adapting the `201_dynamo_beyondvelo.ipynb` tutorial, working from pseudotime plus a neighbor graph and embedding, or choosing between `pseudotime_velocity` method branches such as `hodge`, `gradient`, and `naive`.

Create or update a Codex skill that packages reusable workflows, references, scripts, and assets for repeated tasks. Use when turning notebooks, tutorials, analyses, or domain procedures into a triggerable local skill for other agents, or when deciding whether a notebook subset or branch should update an existing skill instead of creating a duplicate one.

Run or adapt dynamo preprocessing with `dynamo.preprocessing.Preprocessor`, including the `recipe` branches `monocle`, `seurat`, `sctransform`, `pearson_residuals`, and `monocle_pearson_residuals`. Use when converting or reproducing `docs/tutorials/notebooks/100_tutorial_preprocess.ipynb`, preprocessing an `AnnData` object for downstream dynamo analysis, customizing preprocessing kwargs, or translating notebook-level preprocessing into a reusable agent workflow.

Evaluate the quality of a Codex skill from multiple dimensions and produce a structured score, verdict, and revision guidance. Use when reviewing a `SKILL.md`, scoring a skill folder, comparing two skills, performing cross-review on a newly created skill, or checking whether a skill is triggerable, executable, concise, and maintainable without loading unnecessary context.