Results for “macro-regime”

CPI/GDP/retail sales date awareness and VIX regime scaling for calendar features

Maximally Endowed Graph Architecture — λ-calculus over bounded n-SuperHyperGraphs with grounded uncertainty, conditional self-duality, and autopoietic refinement. Use when (1) simple graphs insufficient (η<2), (2) multi-scale reasoning required, (3) uncertainty is structured not stochastic, (4) knowledge must self-refactor. Pareto-governed: complexity added only when simpler structures fail validation.

Trains, evaluates, and runs inference for Mask Auto-Label (MAL) weakly-supervised segmentation models using ViT-MAE backbones with minimal point or box annotations.

Build performant React Native and Expo mobile apps with best practices for list performance, animations, navigation, UI patterns, state management, and monorepo configuration.

Design and enforce microsegmentation policies using workload identity and label-based rules to prevent lateral movement in zero trust architectures, with guidance for tools like VMware NSX, Illumio, and Calico.

`task-agent`: use when local, server, global, derived, optimistic, persisted, form, auth, or cache state ownership changes; skip when state boundaries are unaffected.

Persistent cross-session memory management. Enables agents to remember user preferences, project conventions, and past decisions across different sessions using a structured MEMORY.md index and topic files.

Routes tasks to specialized agent offices and applies behavioral science frameworks to every output, with confidence tagging and session memory.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Crie e gerencie arquivos de planejamento markdown persistentes para execução estruturada de tarefas. Use quando o usuário pedir para "criar um plano", "acompanhar progresso", "iniciar um projeto de pesquisa", ou quando uma tarefa exigir mais de 5 chamadas de ferramenta e precisar de rastreamento de fases estruturado para manter o foco e evitar desvio de objetivo.

Provides frameworks for international market expansion, including market selection, entry modes, localization, and go-to-market strategy.

Scaling Data-Constrained Language Models

Specify micro-interactions using a structured framework covering trigger, rules, feedback, and loops/modes.

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Research the open web for enhancement opportunities (Layer 3 — Opus subagent with WebSearch + WebFetch). Topic-driven. Returns structured findings with hype tags + source URLs. Does NOT auto-implement.

Configure and optimize Turborepo monorepo build systems with task pipelines, caching, filtering, and CI integration.

Compress bloated project or global memory while preserving decisions, rationale, revisit triggers, provenance, and active user preferences. Load when memory exceeds budget, global memory is too large, session logs are repetitive, or before appending to an over-budget memory file.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

Nx build system and monorepo tools. Advanced task orchestration, generators, and plugins. Use for complex enterprise monorepos with multiple technologies. USE WHEN: user mentions "Nx", "nx.json", "Nx monorepo", "Nx generators", asks about "Nx workspace", "affected commands", "module boundaries" DO NOT USE FOR: Turborepo (use turborepo skill), simple monorepos (Turborepo is simpler), single-package projects

International market expansion strategy. Market selection, entry modes, localization, regulatory compliance, and go-to-market by region. Use when expanding to new countries, evaluating international markets, planning localization, or building regional teams.

Design the small details—triggers, rules, feedback, loops, and modes—that separate good products from great ones, based on Dan Saffer's framework.

Implement schema.org structured data markup to help search engines understand content and enable rich results in search.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Drive mex (`mex-agent`), persistent project memory and code graphs for AI coding agents. One command scaffolds a living wiki, builds a deterministic code graph, and installs a project anchor file (CLAUDE.md, root AGENTS.md, .cursorrules, .windsurfrules, copilot-instructions.md, or .opencode/opencode.json) that your agent auto-loads as a standing rule document. Use when the user wants to `mex setup` a new project, build a symbol-grounded wiki, keep knowledge connected to implementation, route relevant context to agents, or run drift detection (`mex check`, `mex sync`). Triggers on: "mex setup", "project memory", "code graphs", "codebase documentation", "drift detection", "agent memory", "structured scaffolds", "architectural context", "living wiki", "project anchor file".

Progressively refines context retrieval in multi-agent workflows to solve the subagent context problem.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Architects, reviews, and scales backend systems with structured blueprints, trade-off analysis, and audit reports.

Produce the weekly regulatory digest — a prioritized rollup of new rules, open comment deadlines, and compliance gaps across every tracked matter.

Guides backend development across API design, authentication, databases, performance, security, scalability, and testing, with quick decision guides and defaults for production-ready systems.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Documents MariaDB-specific INSERT syntax and behavior, including RETURNING, ON DUPLICATE KEY UPDATE, INSERT IGNORE, and various forms and modifiers, to help write and review INSERT statements.

Nx smart monorepo build system reference. Covers affected commands, computation caching, project graph visualization, nx.json and project.json config, code generators for React/ Angular/Node/Next.js, module boundary enforcement, Nx Cloud remote caching, and migration from Turborepo.

AutoAugment: Learning Augmentation Strategies from Data

Design and implement Monte Carlo methods for uncertainty quantification, risk analysis, and probabilistic simulations across scientific and financial domains. Use when "monte carlo, random sampling, uncertainty quantification, risk analysis, stochastic simulation, MCMC, variance reduction, probabilistic, " mentioned.

建议在逻辑间隔处手动压缩上下文，以在任务阶段中保留上下文，而非任意的自动压缩。