Audit LiveView socket assigns — memory estimates, missing temporary_assigns, unused assigns, unbounded lists needing streams. Use when investigating LiveView memory bloat.

PyTorch-native Graph Neural Network framework for molecules and proteins. Suitable for building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, and retrosynthesis. If you need pretrained models and diverse feature extractors, use deepchem; if you need benchmark datasets, use pytdc.

Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries.

Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches.

Adversarial Quarto vs Beamer QA. Critic finds issues, fixer applies fixes, loops until APPROVED (max 5 rounds).

Julia-based econometric and structural estimation for computationally intensive tasks. Use for structural models, maximum likelihood, GMM, numerical optimization, simulations, and high-performance computing. Covers DataFrames.jl, FixedEffectModels.jl, Optim.jl, and performance optimization.

Walk the user through setup using AskUserQuestion menus wherever possible. Collect all answers, then write config files in one pass.

>-

hud

diverga-memory

>-

Use this skill when the user discusses experiment design, ablations, training runs, evaluation, baselines, metrics, failures, or result interpretation that should be logged into Obsidian experiment and result notes.

This skill should be used when the user asks to start a new research project, import an existing code-plus-Markdown repository into Obsidian, or bind the current repository to a compact research knowledge base for future syncing.

Use this skill when the user wants to detach, archive, purge, or otherwise change the lifecycle state of an Obsidian project knowledge base.

This skill should be used when the user asks to maintain an Obsidian knowledge base for a research project, import an existing research repository into Obsidian, keep project memory or daily notes synchronized, summarize project context into durable notes, or update experiments, results, papers, writing, and plans in an Obsidian vault without requiring MCP.

Use this skill when the user is discussing daily research work, TODOs, plans, standups, meetings, milestones, or general project progress that should be reflected in Obsidian daily notes, plan notes, and hub updates.

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

27 ai & machine learning skills. Trigger: ML experiments, model training, deep learning, NLP, computer vision. Design: covers frameworks, benchmarks, paper reproduction, and AI research workflows.

Benchmark AI models across 60+ academic evaluation suites and metrics

Evaluate and benchmark large language models for research applications

TensorFlow best practices for tf.function, GPU memory, and deployment

Vectorized multi-agent reinforcement learning simulator

Innovation metrics, R&D management research, and technology forecasting

Distributed systems design patterns and analysis for CS research

Post-labor economies with automation, UBI, and wealth distribution

Legal case law database with PACER data and judge profiles

Look up researcher profiles and academic identities via the ORCID registry

Set up and leverage ORCID for researcher identification and profiles

Ethical Google Scholar data collection techniques and best practices

'Evaluate hook security, performance, and SDK compliance. Use for audits.'

Next.js 15 애플리케이션을 위한 프론트엔드 개발 가이드라인. React 19, TypeScript, Shadcn/ui, Tailwind CSS를 사용한 모던 패턴. Server Components, Client Components, App Router, 파일 구조, Shadcn/ui 컴포넌트, 성능 최적화, TypeScript 모범 사례 포함. 컴포넌트, 페이지, 기능 생성, 데이터 페칭, 스타일링, 라우팅, 프론트엔드 코드 작업 시 사용.

Provides Zig patterns for type-first development with tagged unions, explicit error sets, comptime validation, and memory management. Must use when reading or writing Zig files.

Persistent project documentation system that maintains context across sessions. Creates structured Memory Bank files to preserve project knowledge, decisions, and progress.

Python library for scraping Twitter/X data using GraphQL API with account rotation and session management. Use when extracting tweets, user profiles, followers, trends, or building social media monitoring tools.

PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and context BEFORE starting new work. Your memory is valuable - use it.

Implement caching strategies using @delon/cache. Use this skill when adding memory cache, LocalStorage cache, SessionStorage cache, or cache interceptors for HTTP requests. Supports TTL-based expiration, cache invalidation, cache grouping, and persistent storage. Optimizes performance by reducing redundant API calls and database queries.

Expert prompt optimization for LLMs and AI systems. Use when building

Analyzes backlink profiles to understand link authority, identify toxic links, discover link building opportunities, and monitor competitor link acquisition. Essential for off-page SEO strategy.

Create SEO-optimized MDX blog posts with proper frontmatter

Manage SEO, sitemaps, and metadata for optimal search engine visibility

Creates detailed character profiles including backstory, personality traits, motivations, relationships, and character arcs. Use when the user needs help developing compelling, multi-dimensional characters for their story.

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.

>

Full-stack performance analysis, optimization patterns, and monitoring strategies

Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.

operating-k8s-local

Optimize Next.js 15 applications for performance, Core Web Vitals, and production best practices using App Router patterns

react-component

tailwind-css

Save current progress to memory-keeper to prevent work loss.