Results for “pattern-classification”

Guides migration of AEM Cloud Service schedulers from legacy patterns to OSGi-compliant Sling Scheduler or Sling Jobs, with classification, review checklists, and troubleshooting.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Train, evaluate, export, and run inference for pose classification models using ST-GCN on skeleton keypoint sequences.

Identifies recurring patterns across three or more domains to extract universal principles and apply them to new contexts.

Scans US equities for daily +20%/-20% movers, classifies catalysts and chart context, updates forward outcomes, and summarizes cohort patterns for research.

Pattern-Based Diagnosis

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Structure a pattern library entry with problem context, solution pattern, usage examples, and related patterns.

Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.

Your won/lost/churn pattern analyst. Connect a CRM plus a product-analytics tool, then turn retrospective data into forward-looking action. Three modes. (1) WON, win pattern recognition that feeds your ICP and lookalike search. (2) LOST, loss pattern plus competitive intel that feeds a messaging refresh. (3) CHURN, churn theme extraction plus predictive scoring (which active accounts look like recent churners?). Trigger on "why are we winning?", "why are we losing?", "closed-lost autopsy", "churn patterns", "competitive intel rollup", "who do we lose to most?", "show me lookalike candidates to {winning customer}", "predictive churn", "which active accounts look like churners?", or any portfolio-level pattern recognition.

Train, evaluate, distill, quantize, export, and run inference for PyTorch-based TAO image classification models with support for multiple backbones.

Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.

Identifies recurring patterns across three or more domains to extract universal principles and apply them to new problems.

Cardinality and model family jointly determine the encoding.

A library of reusable, production-tested prompt engineering patterns for building AI-powered features. Use when designing system prompts for apps, building AI pipelines, selecting the right prompting technique for a use case, or reviewing prompts for common failure modes. Complements the prompt-engineering skill (which covers the optimization framework); this skill covers the pattern library itself.

Adapt and integrate a specific pattern from your references into your current codebase. Use when you've identified a pattern worth adopting and need a structured plan to integrate it with minimal disruption.

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.

Compare tradeoffs and recommend architectural patterns — dependency injection, service-oriented architecture, repository, domain events, circuit breaker, and anti-corruption layer. Use when choosing between design patterns, planning microservices boundaries, evaluating system design alternatives, or asking 'which pattern should I use' for a specific coupling or resilience problem.

Provides JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.

TRAK: Attributing Model Behavior at Scale

Provides production-grade Django architecture patterns including project structure, model design, REST API design with DRF, ORM best practices, caching, signals, and middleware.

Provides production patterns and non-obvious traps for Prisma ORM in TypeScript backends, covering schema design, query optimization, transactions, pagination, and common pitfalls.

Curriculum Learning

通用分类法抽象接口。当定义分类系统、分类结构或分层分类框架时调用此技能。

Reviews parsers, deserialization, uploads, archives, YAML/JSON/XML/pickle, paths, templates, SSRF, and unsafe loaders.

Use this skill to classify tabular data end-to-end in MATLAB — load a dataset, prepare and clean it, select promising classifiers, train them, and compare accuracies with cross-validation, holdout, or hyperparameter optimization plus statistical tests. TRIGGER when: user asks to classify tabular data, pick classifiers for a dataset, compare classifier accuracy, run cross-validation or a holdout evaluation, or find the best model with statistical uncertainty. DO NOT TRIGGER when: user has non-tabular inputs (images, sequences, time series), wants a regression model, is training a specific neural network architecture (use matlab-train-network), or wants cost-sensitive learning or an arbitrary class-prior vector (this skill only supports the built-in uniform-prior toggle for imbalanced data).

Apply named refactoring transformations to improve code structure without changing behavior, guided by code smells and safe transformation sequences.

Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction design across any domain (portfolios, e-commerce, SaaS, adult content, technical showcases). This skill should be used when users need exhaustive design research, pattern recognition across large example sets, or systematic visual analysis for competitive positioning.

Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.

Testing patterns and principles. Unit, integration, mocking strategies.