triton-kernel-writing
triton-kernel-writing
【开发与工程】Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation.
THE SKILLS DIRECTORY
探索全部技能.
一个技能，一个新的可能。找到适合你的 AI 工作流。
genomic-coordinates
genomic-coordinates
【数据与研究】Converts genomic intervals between coordinate conventions, normalises and compares variant representations, and detects assembly or contig-naming mismatches before they corrupt an analysis. Used whenever coordinates cross a format, tool, or assembly boundary - converting between BED, GFF/GTF, VCF, SAM/BAM, WIG, PSL, genePred, Picard interval_list, or…
pathway-enrichment
pathway-enrichment
【数据与研究】Performs pathway and gene-set enrichment analysis on gene lists or ranked gene data and interprets the results. Used when the user has a set of genes (differentially expressed genes from PyDESeq2/Scanpy, CRISPR-screen hits, cluster marker genes, proteomics hits) and wants to know which biological pathways, GO terms, or gene sets are over-represented …
torchdrug
torchdrug
【数据与研究】Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
sql-optimization-patterns
sql-optimization-patterns
【数据与研究】Diagnose slow SQL with query plans, preserve query results, and verify indexing or query changes against representative data.
voice-agents
voice-agents
【效率与协作】Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems.
poka-yoke
poka-yoke
【设计与创意】Mistake-proof code so misuse cannot be expressed, rather than warning against it. Use when designing an interface, schema, or state machine and the user wants it hard to get wrong ("make invalid states unrepresentable", "so callers cannot screw it up", "type-safe API", "pit of success"); when auditing existing code for footguns ("what could bite us h…
sparse-autoencoder-training
sparse-autoencoder-training
【开发与工程】Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
scgpt
scgpt
【数据与研究】Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For probabilistic single-cell models (scVI etc…
algorithm-visualizer
algorithm-visualizer
【设计与创意】Generate visual representations of algorithm execution
graph-modeler
graph-modeler
【效率与协作】Convert problem descriptions into graph representations
decision-visualization
decision-visualization
【设计与创意】Decision-specific visualization skill for creating clear, actionable visual representations of analyses
supply-chain-digital-twin
supply-chain-digital-twin
【开发与工程】Digital twin representation of supply chain for real-time monitoring and simulation
stakeholder-facilitation
stakeholder-facilitation
【效率与协作】Facilitate meetings, workshops, and community consultations with diverse stakeholders including artists, board members, funders, and community representatives
tooluniverse-microbial-genome-characterization
tooluniverse-microbial-genome-characterization
【数据与研究】Genome-ASSEMBLY discovery, QC, and replicon mapping for any organism (bacteria, archaea, fungi, and beyond) using NCBI Datasets. Resolves an organism name or taxid to assemblies, picks the reference/representative or best-quality assembly, pulls assembly QC metrics (total length, contig/scaffold N50, contig count, GC%, assembly level, RefSeq category…
tooluniverse-microbial-genome-characterization
tooluniverse-microbial-genome-characterization
【数据与研究】Genome-ASSEMBLY discovery, QC, and replicon mapping for any organism (bacteria, archaea, fungi, and beyond) using NCBI Datasets. Resolves an organism name or taxid to assemblies, picks the reference/representative or best-quality assembly, pulls assembly QC metrics (total length, contig/scaffold N50, contig count, GC%, assembly level, RefSeq category…
tooluniverse-neurosynth-meta-analysis
tooluniverse-neurosynth-meta-analysis
【数据与研究】Meta-analytic decoding of human fMRI coordinates using the Neurosynth coordinate database (14,371 studies, ~3,228 cognitive/neuroscience terms) — given an MNI brain coordinate, statistically identify which cognitive terms are over-represented in studies reporting activation there ("reverse inference"); given a term, find the studies and coordinates m…
tooluniverse-fastq-qc
tooluniverse-fastq-qc
【数据与研究】FASTQ quality control and adapter/quality-trimming decisions with local NGS tools — run FastQC on raw reads, summarize a project with MultiQC, interpret per-base sequence quality, per-base N content, adapter content, overrepresented sequences, sequence duplication and GC content, and decide whether (and how) to trim with fastp / Cutadapt before downs…
18 / 475