하나의 Skill, 완전히 새로운 가능성. 다음 워크플로를 찾아보세요.
moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing,…
smart-routing
Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.
bio-causal-genomics-pleiotropy-detection
Detect and adjust for horizontal pleiotropy in two-sample Mendelian randomization by distinguishing uncorrelated (UHP) from correlated (CHP) pleiotropy and choosing among Egger, MR-PRESSO, MR-RAPS, CAUSE, LHC-MR, LCV, MR-Clust, MR-Mix, and contamination-mixture methods. Use when validating an MR causal claim, running the STROBE-MR sensitivity battery, suspe…
bio-molecular-standardization
Standardizes molecular structures using the ChEMBL structure pipeline for normalization and parent selection plus RDKit rdMolStandardize for explicit custom steps such as tautomer canonicalization, salt/solvent stripping, charge handling, stereochemistry handling, mixture selection, and isotope normalization. Explicitly compares ChEMBL, canSARchem, RDKit, a…
bio-clinical-biostatistics-bayesian-trials
Designs Bayesian clinical trials including Phase I dose-finding (BOIN, CRM, EWOC, mTPI-2), meta-analytic-predictive (MAP) priors with robust mixtures for external data borrowing, EXNEX for basket trials, hierarchical models for safety AE (Berry-Berry), Bayesian platform trials (I-SPY 2, GBM AGILE, REMAP-CAP), and posterior probability stopping rules. Covers…
bio-clinical-biostatistics-missing-data
Implements missing-data sensitivity analyses for confirmatory clinical trials including MMRM under MAR (with Kenward-Roger correction), reference-based multiple imputation (J2R, CR, CIR, LMCF per Carpenter-Roger 2013), Permutt delta-adjustment / tipping-point analysis, pattern-mixture identifying restrictions (CCMV, NCMV, ACMV), and the Cro vs Bartlett vari…
bio-comparative-genomics-introgression-detection
Detect introgression and admixture between species or populations using Dsuite (Malinsky 2021 fast D-statistics), Patterson's D / ABBA-BABA test (Green 2010; Durand 2011), f4-ratio and f-branch statistic (Malinsky 2018), TreeMix (Pickrell & Pritchard 2012), HyDe (Blischak 2018), QuIBL (Edelman 2019), sprime (Browning 2018), Twisst (Martin 2017), PhyloNet (T…
bio-imaging-mass-cytometry-quality-metrics
Quality control for IMC/MIBI data across pixel, channel, image, slide, and batch levels, covering Poisson-count SNR (cell-level Gaussian-mixture and empty-channel comparison), spillover-matrix QC (the three physical sources), drift and the missing EQ-bead analog, acquisition artifacts, and sample-of-origin batch effects. Use when deciding whether to keep or…
bio-methylation-based-detection
Detects cancer and infers tissue-of-origin from cfDNA methylation by choosing conversion chemistry (bisulfite vs EM-seq vs TAPS vs cfMeDIP), calling read-level methylation haplotypes rather than averaged beta values, and deconvolving a hematopoietic-dominated cfDNA mixture against a methylation atlas via NNLS/quadratic programming. Encodes the GRAIL/CCGA th…
bio-single-cell-perturb-seq
Analyze Perturb-seq / CROP-seq single-cell CRISPR screens. Use when assigning guides as a mixture problem, removing non-perturbed escaper cells with Mixscape, choosing a calibrated test (SCEPTRE conditional resampling) over naive DE, quantifying effect size with E-distance, separating compositional shifts from within-state expression change, or judging whet…
bio-spatial-transcriptomics-high-resolution-binning
Reconstructs single cells from sub-cellular spatial capture units (Visium HD 2um bins, Stereo-seq DNB spots, Slide-seqV2 beads) by aggregating bins UP into cells rather than deconvolving a mixture DOWN. Use when choosing a bin size and recognizing the sparsity-vs-mixture dilemma (2um bins are too sparse to cluster, but binning to 8/16um re-creates the multi…
bio-spatial-transcriptomics-spatial-deconvolution
Estimates per-spot cell type composition of spatial transcriptomics mixtures (Visium, Slide-seq, Stereo-seq) from an scRNA-seq reference with cell2location, RCTD, SPOTlight, stereoscope, SpatialDWLS, or reference-free STdeconvolve. Use when deciding whether a platform even needs deconvolution (the resolution fork -- a 55um Visium spot is a 1-10-cell MIXTURE…
genome-compare
Compare your genome to George Church (PGP-1) and estimate ancestry composition via IBS and EM admixture
scienceclaw-benchmark-for36
Use when a task asks to separate stereo music mixtures into four stems (vocals, drums, bass, other) and deliver the estimated stems, optionally with training mixtures plus reference stems, judged by BSSEval-v4 source-to-distortion ratio (SDR, dB), as in MUSDB18 music source separation (FoR36 of the companion ScienceClaw-Eval benchmark).
ai-hive-gap-068-moe-routing
当用户搜索或需要MoE,稀疏模型,Mixture of Experts,模型路由时使用。帮助开发者、AI产品经理、技术负责人、模型采购和成本管理团队完成理解MoE模型的有效参数、速度和成本差异并设计路由，通过AI-HIVE MCP实时核验模型并交付概念说明、任务评测、模型候选、成本表和路由规则。不适用于超出以下边界的请求：不得仅按总参数量判断质量与费用。
block-ffn-sparse-mixture-experts
Deploy efficient MoE models on resource-constrained edge devices by learning chunk-level activation sparsity that achieves 3.67× speedup. Use when you need to compress LLMs for on-device inference while maintaining reasoning quality and supporting speculative decoding acceleration.
cli-and-configs
Build and debug TRL CLI commands, YAML configs, dataset mixture configs, accelerate-launch argument patterns, env configs, and bundled TRL skills commands.
data-integration
Integrate LeRobot-format StarVLA datasets, modality schemas, robot DataConfig classes, mixtures, and registry discovery.
An independently imported catalog with original authors, licenses and source links. Classification is not a security audit.
Sources and import coverage