1285 个 · 按相关度排序
Turn a broad research direction into ranked ideas with clear hypotheses and small experiments. Survey related papers, use another model to challenge candidates, and update priorities using pilot results when suitable computing resources are available.
中文简介正在准备中。当前显示英语简介。
Explore a broad research direction through literature searches, idea generation, novelty checks, small pilot experiments, and critical review. Receive ranked ideas plus a refined proposal and experiment plan for the leading candidate, with evidence recorded across stages.
中文简介正在准备中。当前显示英语简介。
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.
中文简介正在准备中。当前显示英语简介。
Guides experiments that inspect and modify internal values in PyTorch models to study their effects on predictions. Covers local analysis and remote experiments through NDIF for models too large for local GPUs.
中文简介正在准备中。当前显示英语简介。
Build machine learning workflows that connect data checks, training, evaluation, and deployment. The skill implements experiment tracking, model version management, and automated retraining, with reproducible environments and explicit validation thresholds before models enter production.
中文简介正在准备中。当前显示英语简介。
Test an app idea through focused experiments and collect verified findings for development. It can also suggest what to explore next based on existing experiments and package findings as a reusable project skill.
中文简介正在准备中。当前显示英语简介。
Analyze ML and AI experiment data with statistical tests, effect sizes, confidence intervals, and figures. The skill validates comparisons and produces an analysis report, statistical appendix, and figure catalog while identifying missing evidence and limitations.
中文简介正在准备中。当前显示英语简介。
Turn observations or preliminary data into competing scientific hypotheses grounded in literature. Develop explanations, assess what could disprove them, and produce testable predictions and experimental designs in a structured report with diagrams.
中文简介正在准备中。当前显示英语简介。
Build testable scientific hypotheses from observations or preliminary data. Compare competing explanations against published evidence, define measurable predictions, and propose experiments, then organize the findings into a research report with diagrams and detailed supporting material.
中文简介正在准备中。当前显示英语简介。
Design experiments and quasi-experiments before analysis. Use when choosing study design, treatment/control structure, outcomes, assumptions, validation plans after scientific experiment failure, or which of DiD, ITS, synthetic control, or regression discontinuity fits the research question. For fitting models or estimating effects on existing data, use performing-causal-analysis instead.
中文简介正在准备中。当前显示原文说明。
Add file-based observability, tracing, and run analysis to LLM/agent experiments — per-turn transcripts, tool calls and results, reasoning traces, token/cost accounting, per-episode artifacts, plus terminal viewers and a run-comparison report. Platform-agnostic: one small adapter covers OpenAI, Gemini/Vertex, Anthropic, LiteLLM, Tinker, vLLM, or any custom inference stack, and the same tooling then works unchanged. Use this skill whenever the user wants observability, tracing, logging, or run tracking for model experiments; asks why an agent failed a task or wants to replay/debug/diff an episode; wants to compare models, arms, or ablations; wants to instrument a new folder, repo, or platform ("add observability here", "do the same for Tinker/Gemini/OpenAI"); wants to import or tie in existing experiment results so old runs show up alongside new ones; or wants eval runner scripts where many models share one protocol. Reach for this even when they only say "log what the model is doing", "I can't tell what happened in this run", or "set up traces for this experiment".
中文简介正在准备中。当前显示原文说明。
Estimates the minimum biological replicates (or cells/events) for a target power at a target FDR in genomics experiments using ssizeRNA, PROPER, powsimR for scRNA-seq, and pilot-data dispersion estimation from DESeq2/edgeR. Covers the biological-versus-technical replication distinction (technical replicates do not add degrees of freedom for biological inference), replicate-number-versus-sequencing-depth budgeting, scRNA-seq sample-versus-cell allocation under a pseudobulk model, and the critique that "n=3" is a publication convention rather than a power calculation. Use when budgeting a sequencing experiment, writing the sample-size justification in a grant, estimating replicates from pilot data, allocating a fixed budget between samples and depth, or planning scRNA-seq cohort size. For clinical-trial sample size see clinical-biostatistics/power-and-sample-size; for the power-given-n direction see experimental-design/power-analysis.
中文简介正在准备中。当前显示原文说明。
Designs genomics experiments so technical nuisance variation (batch, lane, plate, flow cell, operator, reagent lot, processing day) is balanced against the biological variable of interest and therefore estimable rather than confounded, using constrained sample-to-batch assignment (designit, OSAT), the confounder/mediator/collider distinction, and the principle that no post-hoc correction recovers a fully confounded design. Covers detecting hidden batches with surrogate variable analysis, a decision table for downstream correction (ComBat-seq, RUVSeq, SVA) whose execution is deferred to differential-expression/batch-correction, and reproducibility metadata. Use when assigning samples to sequencing batches/lanes/plates, avoiding batch-condition confounding, deciding whether a design is salvageable by correction, choosing a correction method, or estimating the number of hidden batches. For the experimental unit, randomization, and blocking concepts see experimental-design/randomization-blocking.
中文简介正在准备中。当前显示原文说明。
Calculates statistical power for high-dimensional genomics experiments (bulk RNA-seq, scRNA-seq, ATAC-seq, ChIP-seq, methylation, proteomics) under negative-binomial count models using RNASeqPower, PROPER, and simulation via powsimR, distinguishing per-gene from marginal (transcriptome-wide) power, the role of mean expression and dispersion, and the sequencing-depth-versus-replicate tradeoff. Covers simulation as the honest default for overdispersed counts, FDR-aware average power versus single-test power, observed/post-hoc power as an anti-pattern, and the winner's-curse / Type-S / Type-M consequences of underpowering. Use when planning replicate number for a sequencing experiment, deciding whether to add depth or samples, choosing closed-form versus simulation power, estimating power from pilot dispersions, or justifying replication in a grant. For clinical-trial power see clinical-biostatistics/power-and-sample-size; for the inverse sample-size question see experimental-design/sample-size.
中文简介正在准备中。当前显示原文说明。
This package provides a client for the Bioconductor ExperimentHub web resource. ExperimentHub provides a central location where curated data from experiments, publications or training courses can be accessed. Each resource has associated me
中文简介正在准备中。当前显示原文说明。
Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, sample size calculation, test duration, multivariate testing, or conversion experiments. Trigger phrases include "A/B test", "split test", "experiment", "statistical significance", "sample size", "test duration", "which version wins", "conversion experiment", "hypothesis test", "variant testing".
中文简介正在准备中。当前显示原文说明。
Design and validate bounded product experiments with falsifiable hypotheses, precommitted thresholds, guardrail metrics, ethical eligibility, and stop rules; use for product hypothesis validation / product experiment design. (triggers: `product hypothesis validation`, `product experiment design`)
中文简介正在准备中。当前显示原文说明。
Design, audit, and strengthen experimental validation for IEEE manuscripts using routed claim-evidence checks. Use when planning experiments, selecting baselines, designing ablations, choosing metrics, checking fairness, adding robustness tests, explaining results, analyzing complexity, building claim-to-evidence matrices, or responding to reviewer concerns about insufficient experiments.
中文简介正在准备中。当前显示原文说明。
Create consistent nn_cfd W&B experiment comparison reports from selected run IDs using wandb and wandb_workspaces. Use this whenever the user asks to report experiment results, create a W&B Report, compare CFD training/eval runs, document baseline-vs-variant outcomes, reproduce the project experiment report template, or publish a leaderboard-style report for milieu/nn_cfd.
中文简介正在准备中。当前显示原文说明。
Use when building, migrating, or debugging Agent Evals on Inngest: scoring AI agent or workflow outcomes, deferred scorers, sessions, traces, step experiments, experiment variant attribution, Insights queries, or production eval loops for prompts, models, tools, providers, and agent behavior. Covers TypeScript SDK v4 scoring beta APIs, `scoreMiddleware`, `step.score`, `inngest.score`, `createScorer`, `defer`, `group.experiment`, `experimentRef`, `meta.sessions`, and when to use durable workflow primitives for outcome-based evaluation.
中文简介正在准备中。当前显示原文说明。
Design statistically rigorous experiments to test data science hypotheses. Use when the user says "design an A/B test", "run an experiment", "test this hypothesis", "is this difference significant", "how many samples do I need", "randomized controlled trial", "causal inference", "uplift test", "holdout group", "significance test", "power calculation", "avoid p-hacking", or needs to determine whether an observed effect is real before making a product or model decision. For lean build-measure-learn product experiments without the statistics, use experiment-design instead.
中文简介正在准备中。当前显示原文说明。
Track ENCODE experiments locally with publications, citations, and provenance. Use when the user wants to build a collection of experiments, manage citations, compare experiments, or track data provenance.
中文简介正在准备中。当前显示原文说明。
Design and evaluate paid-ad experiments with hypotheses, randomization units, sample-size and duration assumptions, guardrails, platform experiment tools, analysis, and decision rules. Use for A/B test, split test, experiment design, hypothesis, statistical significance, sample size, test duration, or experiment readout.
中文简介正在准备中。当前显示原文说明。
Launch Marcus multi-agent experiments with independent CLI agents in tmux panes. Use when the user says "build X with Marcus", "run a Marcus experiment", "spawn N agents with Marcus", "/marcus", or references the Marcus multi-agent framework. This skill handles experiment setup, config generation, and spawning independent agent CLI processes that coordinate via the Marcus MCP server. Each agent runs in its own tmux pane with full autonomy. NOT for ClawTeam — this is specifically for the Marcus MCP-based multi-agent system. NOTE: "Marcus" is also the name of the MCP server that agents use for coordination. The /marcus skill launches experiments that USE the Marcus MCP server — they are complementary, not competing. The MCP server must be running before invoking this skill. The Marcus MCP server is agent-agnostic; this skill supports Anthropic's claude CLI, OpenAI's codex CLI, and Google's gemini CLI as agent harnesses (selected via --harness).
中文简介正在准备中。当前显示原文说明。