Menu
SkillsMP has collected 420 skills from eightmm/codex-science. Open a skill to review its source and details.
Showing 40 of 420 collected skills.
Execute auditable quantitative research across preregistered study design, statistical inference, numerical verification, dimensional analysis, uncertainty propagation, counterexample search, and formal proof. Use when a scientific or mathematical question…
Compare finite actions under uncertainty with explicit states, loss, utility or risk-neutral payoff, priors, experiment likelihoods, and a declared decision criterion. Use for Bayes risk, expected utility or payoff, pure-action minimax, minimax regret,…
Compare finite actions under uncertainty with explicit states, loss, utility or risk-neutral payoff, priors, experiment likelihoods, and a declared decision criterion. Use for Bayes risk, expected utility or payoff, pure-action minimax, minimax regret,…
Start or continue a task-scoped scientific workbench in Codex. Invoke when the user explicitly uses $codex-science or asks to start, activate, enable, load, or enter Codex Science, including "Codex Science 시작" or "Codex Science 활성화". Also invoke automatically…
Inspect and use the local computer as a reproducible scientific workbench across shell, Python, R, Julia, Jupyter, containers, CPUs, and GPUs. Use when a scientific task needs local files, code execution, package or environment setup, data conversion,…
Audit equations, models, conversions, scales, and limiting cases with explicit dimensions and units, plus executable SI dimensional-consistency and conversion receipts. Use for physical quantities, empirical correlations, nondimensionalization, scaling laws,…
Quantify and review measurement or model-input uncertainty with explicit measurands, calibration, Type A and B components, covariance, linear sensitivities, seeded Monte Carlo propagation, nonlinear disagreement, and machine-readable uncertainty receipts.
Formalize mathematical statements and produce auditable kernel-check receipts in an existing Lean 4 workspace. Use for theorem-statement audits, proof repair, definition design, tactic or term proofs, dependency minimization, axiom inspection, and…
Run a protocol-driven, updateable literature review with exact multi-source queries, study-level deduplication, structured extraction, evidence dependency tracking, bounded synthesis, provenance, and independent review. Use for systematic, scoping, rapid,…
Drive a concrete pure or applied mathematics problem from exact statement through method selection, derivation, proof or computation, executable checks, error control, edge cases, and machine-readable evidence without promoting bounded tests to proofs.
Design and audit numerical computations by separating conditioning, stability, discretization, iteration, floating-point, sampling, and model errors, with executable refinement, residual, invariant, precision, and cross-method verification receipts.
Prove, disprove, test, or repair mathematical statements by normalizing quantifiers and assumptions, building proof obligations, searching bounded domains safely, verifying counterexamples, and assigning evidence statuses that distinguish computation from…
Run reproducible scientific workloads through an existing SSH host, Slurm/HPC cluster, cloud GPU provider, or remote object storage. Use for remote execution, job submission and monitoring, checkpointed long runs, GPU allocation, data staging, result…
Design experiments and perform defensible statistical inference with explicit estimands, experimental units, preregistration, effect sizes, intervals, multiplicity, missingness, randomization, diagnostics, and machine-readable analysis receipts.
Create or revise a traceable scientific manuscript and submission package from reviewed artifacts, a claim register, verified citations, or an existing draft. Use for research articles, methods papers, literature syntheses, journal revisions, cover letters,…
Package a scientific analysis as a reproducible artifact bundle containing the approved plan, inputs, code, commands, environment, outputs, claims, evidence links, and review findings. Use whenever Codex produces or revises scientific figures, tables,…
Independently review a scientific run by checking claims against the approved plan, saved artifacts, citations, environment, and execution record. Use after scientific analysis or writing, before presenting conclusions, and when users ask to verify…
Start or continue Codex Science. Use when the user explicitly starts, activates, enables, loads, or enters Codex Science, or when session context says it is active. This stable bootstrap always loads the task-pinned verified coordinator before scientific work.
Package scientific work as a reproducible artifact bundle with plans, inputs, commands, environments, outputs, evidence, claims, and review findings. This stable bootstrap loads the verified activation-pinned provenance workflow first.
Independently review scientific claims, calculations, citations, methods, artifacts, and reproducibility. This stable bootstrap loads the verified activation-pinned review workflow before reviewing.
Create or revise a traceable scientific manuscript and submission package from reviewed artifacts, a claim register, verified citations, or an existing draft. Use for research articles, methods papers, literature syntheses, journal revisions, cover letters,…
Audit equations, models, conversions, scales, and limiting cases with explicit dimensions and units, plus executable SI dimensional-consistency and conversion receipts. Use for physical quantities, empirical correlations, nondimensionalization, scaling laws,…
Quantify and review measurement or model-input uncertainty with explicit measurands, calibration, Type A and B components, covariance, linear sensitivities, seeded Monte Carlo propagation, nonlinear disagreement, and machine-readable uncertainty receipts.
Formalize mathematical statements and produce auditable kernel-check receipts in an existing Lean 4 workspace. Use for theorem-statement audits, proof repair, definition design, tactic or term proofs, dependency minimization, axiom inspection, and…
Drive a concrete pure or applied mathematics problem from exact statement through method selection, derivation, proof or computation, executable checks, error control, edge cases, and machine-readable evidence without promoting bounded tests to proofs.
Design and audit numerical computations by separating conditioning, stability, discretization, iteration, floating-point, sampling, and model errors, with executable refinement, residual, invariant, precision, and cross-method verification receipts.
Prove, disprove, test, or repair mathematical statements by normalizing quantifiers and assumptions, building proof obligations, searching bounded domains safely, verifying counterexamples, and assigning evidence statuses that distinguish computation from…
Execute auditable quantitative research across preregistered study design, statistical inference, numerical verification, dimensional analysis, uncertainty propagation, counterexample search, and formal proof. Use when a scientific or mathematical question…
Design experiments and perform defensible statistical inference with explicit estimands, experimental units, preregistration, effect sizes, intervals, multiplicity, missingness, randomization, diagnostics, and machine-readable analysis receipts.
Validate docking, pose-prediction, rescoring, and virtual-screening workflows with leakage-aware controls and prespecified metrics. Use before interpreting AutoDock Vina, GNINA, DiffDock, or related docking outputs.
Normalize genes, proteins, variants, diseases, phenotypes, compounds, reactions, tissues, cell types, organisms, studies, and accessions before multi-source biomedical research. Use whenever aliases, assemblies, releases, or identifier namespaces could change…
Reconcile conflicting multi-source biomedical evidence with explicit entity, release, cohort, assay, independence, and claim semantics. Use before final conclusions from multiple databases or evidence lanes.
Route broad or multi-step life-science questions into normalized entities, the smallest independent evidence lanes, reproducible retrieval, conflict reconciliation, and review. Use for target, variant, disease, omics, structure, pharmacology, clinical, or…
Prioritize candidate genes at human genetic loci using curated association, credible-set/L2G, colocalization, eQTL, coding, burden, expression, and pathway evidence. Use for GWAS follow-up and target prioritization.
Discover and triage reusable public transcriptomics, proteomics, metabolomics, microbiome, and supplementary-study datasets. Use when a research question needs external data rather than only literature.
Synthesize target, ligand, mechanism, exposure, safety, pharmacogenomic, trial, and regulatory evidence for translational pharmacology questions. Use for target-drug-indication landscapes, not prescribing.
Synthesize population, clinical, functional, regulatory, expression, and cohort evidence for a genomic variant. Use for research interpretation of rsIDs or genomic alleles, not patient-specific diagnosis or treatment.
Run a protocol-driven, updateable literature review with exact multi-source queries, study-level deduplication, structured extraction, evidence dependency tracking, bounded synthesis, provenance, and independent review. Use for systematic, scoping, rapid,…
Find ontology-aware healthy wild-type gene expression context with Bgee. Use for cross-species, anatomical, developmental-stage, or baseline-expression questions.
Discover public life-science studies and associated archive records through EMBL-EBI BioStudies. Use for ArrayExpress, supplementary-data, accession, and public dataset discovery.