菜单
SkillsMP 已收集 eightmm/codex-science 中的 420 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 420 个已收集 Skill。
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…
原文语言：英语
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,…
原文语言：英语
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,…
原文语言：英语
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…
原文语言：英语
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,…
原文语言：英语
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,…
原文语言：英语
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.
原文语言：英语
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…
原文语言：英语
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,…
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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.
原文语言：英语
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,…
原文语言：英语
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,…
原文语言：英语
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…
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
Independently review scientific claims, calculations, citations, methods, artifacts, and reproducibility. This stable bootstrap loads the verified activation-pinned review workflow before reviewing.
原文语言：英语
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,…
原文语言：英语
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,…
原文语言：英语
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.
原文语言：英语
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…
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
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…
原文语言：英语
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.
原文语言：英语
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…
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
Synthesize target, ligand, mechanism, exposure, safety, pharmacogenomic, trial, and regulatory evidence for translational pharmacology questions. Use for target-drug-indication landscapes, not prescribing.
原文语言：英语
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.
原文语言：英语
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,…
原文语言：英语
Find ontology-aware healthy wild-type gene expression context with Bgee. Use for cross-species, anatomical, developmental-stage, or baseline-expression questions.
原文语言：英语
Discover public life-science studies and associated archive records through EMBL-EBI BioStudies. Use for ArrayExpress, supplementary-data, accession, and public dataset discovery.
原文语言：英语