majiayu000/claude-skill-registry - 第 40 页

using-ai-engineering

Route AI/ML tasks to correct Yzmir pack - frameworks, training, RL, LLMs, architectures, production

原文语言：英语

using-deep-rl

Routes to appropriate deep-RL skills based on problem type and algorithm family

原文语言：英语

using-dynamic-architectures

Use when building networks that grow, prune, or adapt topology during training. Routes to continual learning, gradient isolation, modular composition, and lifecycle orchestration skills.

原文语言：英语

using-ml-production

Router skill directing to deployment, optimization, MLOps, and monitoring guides.

原文语言：英语

using-neural-architectures

The architecture selection router for CNNs, Transformers, RNNs, GANs, GNNs by data modality and constraints

原文语言：英语

using-pytorch-engineering

Routes to appropriate PyTorch specialist skill based on symptoms and problem type

原文语言：英语

using-training-optimization

Router to training optimization skills based on symptoms and training problems

原文语言：英语

vector-database-ops

Deploy, manage, and optimize vector databases for AI applications. Covers Qdrant, Weaviate, pgvector, and Pinecone — collection management, indexing strategies, backup, and performance tuning for production RAG and semantic search workloads.

原文语言：英语

vector-databases

Design vector database ingestion and retrieval pipelines (points + payloads, filtered similarity search, multi-stage hybrid retrieval, index maintenance). Use when building RAG/vector search flows or debugging retrieval quality; triggers: vector database,…

原文语言：英语

vector-databases

Vector database selection, embedding storage, approximate nearest neighbor (ANN) algorithms, and vector search optimization. Use when choosing vector stores, designing semantic search, or optimizing similarity search performance.

原文语言：英语

vector-index-tuning

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

原文语言：英语

vector-search-alternatives

SQLiteプロジェクト向けのベクトル検索代替戦略スキル。 SQLite VSS、外部ベクトルDB、RAGパイプラインの実装を提供します。 Anchors: - The Pragmatic Programmer（Andrew Hunt）/ 適用: 実践的ソリューション選定 / 目的: 適材適所の技術選択 - Designing Data-Intensive Applications（Martin Kleppmann）/ 適用: データシステム設計 / 目的: スケーラブルなアーキテクチャ - Building…

原文语言：日语

vector-search-patterns

Implementing semantic search and similarity search using vector embeddings and vector databases.

原文语言：英语

vector-search

Implement vector search for knowledge retrieval. Use when adding RAG, semantic search, knowledge base features, or context building for the agent.

原文语言：英语

vector-store

Transient vector store service for fast similarity search (FAISS)

原文语言：英语

vector-store

Vector store schema protection and migration management

原文语言：英语

verify-training-pipeline

Verify a CVlization training pipeline example is properly structured, can build, trains successfully, and logs appropriate metrics. Use when validating example implementations or debugging training issues.

原文语言：英语

vexor

Vector-powered CLI for semantic file search with a Claude/Codex skill

原文语言：英语

vision-utilities

Guide for using vision utilities in speedy_utils, including fast GPU image loading, memory-mapped datasets, and notebook visualization.

原文语言：英语

wandb-plot

Shared skill entrypoint for Claude Code. See the canonical skill file at: wandb-plot/SKILL.md

原文语言：英语

ward-identity-checker

Ward Identity Checker

原文语言：英语

wedding-immortalist

Transform thousands of wedding photos and hours of footage into an immersive 3D Gaussian Splatting experience with theatre mode replay, face-clustered guest roster, and AI-curated best photos per person. Expert in 3DGS pipelines, face clustering, aesthetic…

原文语言：英语

whole-brain-emulation-core-simulation

Simulate whole-brain emulation core processes.

原文语言：英语

workflow-kaltstart-und-routing

Kaltstart und Routing im Plugin produktrecht: führt vom ersten Satz oder Dokument in den passenden Arbeitsweg, erkennt Rolle, Ziel, Risiko und Anschluss-Skills.

原文语言：德语

xai-check

Explainability (XAI) audit for products containing AI components. Five-stage tier-scaled check: risk classification, stakeholder×question matrix, fidelity audit, system card, recourse path. Honest about what was validated functionally vs what needs user…

原文语言：英语

zx-calculus

Coecke's ZX-calculus for quantum circuit reasoning via string diagrams with Z-spiders (green) and X-spiders (red)

原文语言：英语

functional-enrichment

Perform GO and KEGG functional enrichment using HOMER from genomic regions (BED/narrowPeak/broadPeak) or gene lists, and produce R-based barplot/dotplot visualizations. Use this skill when you want to perform GO and KEGG functional enrichment using HOMER from…

原文语言：英语

known-motif-enrichment

This skill should be used when users need to perform known motif enrichment analysis on ChIP-seq, ATAC-seq, or other genomic peak files using HOMER (Hypergeometric Optimization of Motif EnRichment). It identifies enrichment of known transcription factor…

原文语言：英语

chromatin-state-inference

This skill should be used when users need to infer chromatin states from histone modification ChIP-seq data using chromHMM. It provides workflows for chromatin state segmentation, model training, state annotation.

原文语言：英语

162-java-profiling-analyze

Use when you need to analyze Java profiling data collected during the detection phase — including interpreting flamegraphs, memory allocation patterns, CPU hotspots, threading issues, systematic problem categorization, evidence documentation with…

原文语言：英语

1k-sentry-analysis

Analyze and fix production errors from Sentry crash reports. Use when investigating AppHang, ANR, crashes, or production errors. Includes complete workflow from JSON analysis to bug fix implementation with evidence-based methodology. Triggers on sentry,…

原文语言：英语

identify

Identify friction points, bottlenecks, bugs, and technical debt. Use for audits, debugging sessions, when something feels wrong, or before major work to surface hidden issues. This is the second system in the 5-system framework.

原文语言：英语

21-understand-research-150

[21] UNDERSTAND. Deep research workflow for this project using 150% scope (100% core + 50% boundary), evidence-based reasoning, and structured investigation notes. Use when the task requires investigation, root-cause analysis, or mapping unknown areas. Always…

原文语言：英语

peak-calling

Perform peak calling for ChIP-seq or ATAC-seq data using MACS2, with intelligent parameter detection from user feedback. Use it when you want to call peaks for ChIP-seq data or ATAC-seq data.

原文语言：英语

30-analyze-impact-150

[30] ANALYZE. Understand how changes impact the system — what's the core, what's affected, what depends on what. Use when planning changes, analyzing systems, debugging issues, or anytime you need to see the full picture of cause and effect. Triggers on…

原文语言：英语

31-analyze-think-150

[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, planning, reviewing, or anytime you need thorough thinking instead of surface-level…

原文语言：英语

a

Trigger: /a. Never auto-trigger on think, scan, consider, or examine.

原文语言：英语

a3criticalthinking

Toyota-style A3 problem solving with embedded priority hierarchy: Safety First, then Customer Value, then Shareholder Value. Structured thinking framework for manufacturing decisions, root cause analysis, and countermeasure development. USE WHEN user says…

原文语言：英语

a3criticalthinking

Toyota-style A3 problem solving with embedded priority hierarchy: Safety First, then Customer Value, then Shareholder Value. Structured thinking framework for manufacturing decisions, root cause analysis, and countermeasure development. USE WHEN user says…

原文语言：英语

aads-status-triage

Triage AADS-ULoRA requests by capturing repository state, mapping impacted files and modules, and selecting the smallest safe validation surface before coding. Use when scope is unclear, when asked what to change or test first, or before implementation and…

原文语言：英语