386 个 · 按相关度排序
Train GPT-2 scale models (~124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.
中文简介正在准备中。当前显示原文说明。
Fetches Twitter/X post and Article content — text, author, engagement metrics and embedded media — downloading images locally and generating complete Markdown with image references. Use when retrieving a tweet's text or an X Article with images, or pulling post metadata for a Markdown/PKM record. Preferred over Jina alone for X Articles with images.
中文简介正在准备中。当前显示原文说明。
Anti-slop skill for PRODUCT UI - dashboards, data tables, forms, multi-step flows, settings, list/detail, app shells. The agent reads the surface, budgets the frame first, and ships dense interfaces that are correct at every edge case (overflow, long labels, empty/error/loading states, i18n expansion, keyboard/a11y). House-system-first; maps to Carbon/Polaris/Atlaskit/Fluent/Primer/Material3/Radix-shadcn/Ant. The counterpart to taste-skill, which owns landing/portfolio/marketing.
中文简介正在准备中。当前显示原文说明。
Use for full-manuscript prose polish of an Academy of Management Journal (AMJ) manuscript — front-loading the argument, active voice, structure, and AOM house style. Polishes language and structure; it does not create the theoretical contribution (amj-contribution-framing) or fix the analysis (amj-data-analysis).
中文简介正在准备中。当前显示原文说明。
Loads, converts, and manipulates Hi-C contact matrices in cooler format (.cool/.mcool/.scool) and Juicer .hic, using cooler (Python + CLI), hic2cool, and hictk. Covers the single-resolution mcool URI (file.mcool::/resolutions/<bp>), the load-bearing divisive-vs-multiplicative weight-naming rule (KR/VC/VC_SQRT auto-divisive vs cooler's multiplicative weight), what survives .hic<->.cool conversion (FRAG matrices and norm vectors do not), raw-vs-balanced coarsening, the .pairs upper-triangle/chromsize-order contract, and chrom-naming/bin-table provenance. Use when loading a cooler, converting .hic to .mcool, selecting a resolution, building a cooler from pairs or a matrix, coarsening/zoomifying, importing Juicer norm vectors, or debugging all-NaN balanced matrices and chr1-vs-1 empty fetches.
中文简介正在准备中。当前显示原文说明。
Retrieve records from NCBI databases using Biopython Bio.Entrez (EFetch, ESummary). Use when downloading sequences, fetching GenBank/GenPept records, getting document summaries, parsing nested XML, navigating GI deprecation, choosing between rettype+retmode combinations, and parsing into Biopython SeqRecord/SwissProt objects. Covers nucleotide, protein, gene, pubmed, sra, gds, taxonomy, snp, clinvar.
中文简介正在准备中。当前显示原文说明。
Embeds and controls web content in SwiftUI with WebKit for SwiftUI, including WebView, WebPage, navigation policies, JavaScript execution, observable page state, link interception, local HTML or data loading, and custom URL schemes. Use when building iOS 26+ article/detail views, help centers, in-app documentation, or other embedded web experiences backed by HTML, CSS, and JavaScript.
中文简介正在准备中。当前显示原文说明。
Resolve Swift concurrency compiler errors, adopt approachable concurrency (SE-0466), and write data-race-safe async code. Use when fixing Sendable conformance errors, actor isolation warnings, or strict concurrency diagnostics; when adopting default MainActor isolation, @concurrent, nonisolated(nonsending), or Task.immediate; when designing actor-based architectures, structured concurrency with TaskGroup, or background work offloading; or when migrating from @preconcurrency to full Swift 6 strict concurrency.
中文简介正在准备中。当前显示原文说明。
Read and write 3-D point cloud data using Lidar Toolbox file I/O. Covers PLY, PCD, LAS/LAZ, PCAP (Velodyne/Ouster/Hesai), E57, and IDC (Ibeo) formats. Use when loading point clouds from disk, saving to disk, choosing the correct reader or writer for a file format, extracting or preserving lidar point attributes, reading Ibeo IDC sensor recordings, or converting between formats.
中文简介正在准备中。当前显示原文说明。
Import Claude Code or Codex history and move complete CCAM datasets between machines. Use when rescanning provider history, importing a copied directory, uploading JSONL or archives, exporting a backup, restoring it idempotently, or verifying that tokens, workflows, runs, rules, and pricing survived.
中文简介正在准备中。当前显示原文说明。
Use when captions, subtitles, or the spoken text of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to read, quote, or translate a video, accessibility needs, deaf/HoH use cases, content review, or language learning. Fetches timestamped caption data from any YouTube video. Not for uploading subtitles or account management.
中文简介正在准备中。当前显示原文说明。
Use when building or fixing an Unreal Engine 5 level or open world: World Partition, OFPA, Data Layers, Level Instances, Packed Level Actors, HLOD, landscape size, heightmap import or clipping, edit layers, terrain material rules, foliage and grass, a PCG forest or rock scatter, runtime GPU grass, Nanite and tessellation choices, modular kits, a river or village, streaming pop-in, cells not loading, landscape black spots, "PCG shows nothing in the editor", or a world too heavy to hand to lighting.
中文简介正在准备中。当前显示原文说明。
Use when preloading fonts, asset/network images, Lottie/Rive animations, local JSON/config, warming initial API data, or optimizing Flutter Web startup.
中文简介正在准备中。当前显示原文说明。
Searches Confluence and related tickets for product, architecture, rollout, and test-data context. Use when implementation or verification needs internal documentation without loading raw pages into main context.
中文简介正在准备中。当前显示原文说明。
Meta-skill for designing orchestrator+phases structured workflow skills. Creates SKILL.md coordinator with progressive phase loading, TodoWrite patterns, and data flow. Triggers on "design workflow skill", "create workflow skill", "workflow skill designer".
中文简介正在准备中。当前显示原文说明。
Use ML.NET to train, evaluate, or integrate machine-learning models into .NET applications with realistic data preparation, inference, and deployment expectations. USE FOR: ML.NET integration; local model training or retraining; inference pipelines, model loading, evaluation, and deployment review. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
中文简介正在准备中。当前显示原文说明。
Design, tune, or review EF Core data access with proper modeling, migrations, query translation, performance, and lifetime management for modern .NET applications. USE FOR: DbContext, migrations, model configuration, EF queries, tracking, loading, performance, transactions, and EF6 migration decisions. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
中文简介正在准备中。当前显示原文说明。
Create dynamic schema-based forms using @delon/form (SF component). Use this skill when building complex forms with validation, conditional rendering, async data loading, custom widgets, and multi-step workflows. Ensures forms follow JSON Schema standards, integrate with Angular reactive forms, support internationalization, and maintain consistent validation patterns across the application.
中文简介正在准备中。当前显示原文说明。
DepMap CRISPR gene effect (Chronos) analysis: sign convention for essentiality, per-gene NaN-safe Spearman correlation, data loading/alignment. For general NaN-safe correlation see nan-safe-correlation; for quality filtering see degenerate-input-filtering.
中文简介正在准备中。当前显示原文说明。
Schedule labor crews based on CWICR norms and project timeline. Calculate crew sizes, shifts, and labor loading curves.
中文简介正在准备中。当前显示原文说明。
Use fastMRI for MRI reconstruction data loading, MRI operators, reconstruction models, Lightning training, evaluation, and submission preparation.
中文简介正在准备中。当前显示原文说明。
Use DeepChem for molecular machine learning, data loading, featurization, model training, MoleculeNet, docking, and optional backend troubleshooting.
中文简介正在准备中。当前显示原文说明。
Route Chinese-BERT-wwm model loading, model selection, benchmark data, and troubleshooting workflows for HFL Chinese BERT-family resources.
中文简介正在准备中。当前显示原文说明。
Route BEIR repository tasks for benchmark data loading, retrieval evaluation, reranking, generation, and training workflows.
中文简介正在准备中。当前显示原文说明。