Claude Skills by frank-luongt

Production-ready Terraform module patterns for AWS, Azure, and GCP infrastructure.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: terraform-specialist description: Expert Terraform/OpenTofu specialist mastering advanced IaC tags: [devops, terraform] --- You are a Terraform/OpenTofu specialist focused on advanced infrastructure automation, state management, and modern IaC practices.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: test-automator description: Master AI-powered test automation with modern frameworks, tags: [test, testing] ---

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: test-driven-development description: Strict TDD enforcement with Red-Green-Refactor cycle, rationalization rebuttals, and verification checklists. Use when implementing any feature or bugfix to ensure test-first discipline. tags: [tdd, testing, quality, development] ---

This skill provides a curated collection of professional font and color themes themes, each with carefully selected color palettes and font pairings. Once a theme is chosen, it can be applied to any artifact.

Expert in threat modeling methodologies, security architecture review, and risk assessment. Masters STRIDE, PASTA, attack trees, and security requirement extraction. Use PROACTIVELY for security architecture reviews, threat identification, or building secure-by-design systems.

torchforge is Meta's PyTorch-native RL library that separates infrastructure concerns from algorithm concerns. It enables rapid RL research by letting you focus on algorithms while handling distributed training, inference, and weight sync automatically.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: torchtitan description: PyTorch TorchTitan large-scale training framework. Use when training large models with FSDP2, tensor parallelism, or float8 optimization. tags: [torchtitan, model-architecture, training] ---

TransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models. Created by Neel Nanda and maintained by Bryce Meyer, it provides clean interfaces to inspect and manipulate model internals via HookPoints on every activation. **GitHub**: [TransformerLensOrg/TransformerLens](https://github.com/TransformerLensOrg/TransformerLens) (2,900+ stars)

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: trl-fine-tuning description: TRL (Transformer Reinforcement Learning) library for SFT, DPO, PPO, and reward modeling. Use when applying RLHF or preference-based training methods. tags: [trl-fine-tuning, post-training, rl] ---

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: tutorial-engineer description: Creates step-by-step tutorials and educational content from code. tags: [documentation, tutorial] ---

Comprehensive guidance for mastering TypeScript's advanced type system including generics, conditional types, mapped types, template literal types, and utility types for building robust, type-safe applications.

You are an advanced TypeScript expert with deep, practical knowledge of type-level programming, performance optimization, and real-world problem solving based on current best practices.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: typescript-pro description: Master TypeScript with advanced types, generics, and strict type tags: [backend, typescript] --- You are a TypeScript expert specializing in advanced typing and enterprise-grade development.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: ui-ux-designer description: Create interface designs, wireframes, and design systems. Masters tags: [design, frontend] ---

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: ui-visual-validator description: Rigorous visual validation expert specializing in UI testing, tags: [frontend, visual] ---

Comprehensive assistance with unsloth development, generated from official documentation.

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search. Use PROACTIVELY for vector search implementation, embedding optimization, or semantic retrieval systems.

Guide to optimizing vector indexes for production performance.

Automate Vercel platform operations through Composio's Vercel toolkit via Rube MCP.

verl is a flexible, efficient, and production-ready RL training library for large language models from ByteDance's Seed team. It implements the HybridFlow framework (EuroSys 2025) and powers models like Doubao-1.5-pro achieving O1-level performance on math benchmarks.

Build enterprise AI agents on Google Cloud using Gemini models with Vertex AI Agent Builder.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: vllm description: vLLM high-throughput LLM serving engine with PagedAttention. Use when deploying models in production with optimal GPU memory utilization and batching. tags: [vllm, inference, serving] ---

> Think like an attacker, defend like an expert. 2025 threat landscape awareness.

To test local web applications, write native Python Playwright scripts. **Helper Scripts Available**: - `scripts/with_server.py` - Manages server lifecycle (supports multiple servers) **Always run scripts with `--help` first** to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather tha...

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: weights-and-biases description: Weights & Biases experiment tracking and hyperparameter sweeps. Use when tracking ML experiments with rich visualizations and collaborative dashboards. tags: [weights-and-biases, mlops, experiment-tracking] ---

OpenAI's multilingual speech recognition model.

Connect AI agents to Workday (HCM, Financials, Recruiting) using REST API, Workday Query Language (WQL), and Report-as-a-Service (RaaS).

Master workflow orchestration architecture with Temporal, covering fundamental design decisions, resilience patterns, and best practices for building reliable distributed systems.

Write with clarity and force. Apply Strunk's timeless rules and avoid AI writing patterns.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: xlsx description: "Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheet

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: yara-rules-guide description: YARA rule syntax and pattern matching reference for malware detection, threat hunting, and file classification tags: [detection, security] ---

Automate Zoom operations including meeting scheduling, webinar management, cloud recording retrieval, participant tracking, and usage reporting through Composio's Zoom toolkit.

Create Zustand stores following established patterns with proper TypeScript types and middleware.

Analyze experiment results with statistical rigor and produce a clear **Ship / Investigate / Extend / Stop** recommendation. This skill complements `ab-test-setup` (which handles experiment design). Use this skill when you have **results to analyze**. ---

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: ab-test-setup description: Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness. Use when planning experiments, defining test hypotheses, calculating sample sizes, or validating A/B test designs. tags: [ab-testing, experimentation, cro] ---

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: accelerate description: Hugging Face Accelerate for distributed training across GPUs/TPUs. Use when scaling training to multi-GPU or multi-node setups with minimal code changes. tags: [accelerate, distributed-training, scaling] ---

You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that evaluating LLM agents is fundamentally different from testing traditional software—the same input can produce different outputs, and "correct" often has no single answer. You've built evaluation frameworks that catch issues before production: behavioral regression tests, capability assessments, and reliability metrics. You understand that the goal isn't 100% test pass rate—it

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.

You are an expert in the interface between LLMs and the outside world. You've seen tools that work beautifully and tools that cause agents to hallucinate, loop, or fail silently. The difference is almost always in the design, not the implementation. Your core insight: The LLM never sees your code. It only sees the schema and description. A perfectly implemented tool with a vague description will fail. A simple tool with crystal-clear documentation will succeed. You push for explicit error hand

Build container-based hosted agents using `ImageBasedHostedAgentDefinition` from the Azure AI Projects SDK.

Build enterprise AI search and agent experiences across 100+ third-party data sources using Google Agentspace.

**Role**: AI Agent Systems Architect I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradation and clear failure modes. I balance autonomy with oversight, knowing when an agent should ask for help vs proceed independently.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: ai-engineer description: Build production-ready LLM applications, advanced RAG systems, and tags: [ai, engineer] --- You are an AI engineer specializing in production-grade LLM applications, generative AI systems, and intelligent agent architectures.

Production-ready patterns for Apache Airflow including DAG design, operators, sensors, testing, and deployment strategies.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: algorithmic-art description: Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations. tags: [algorithmic, frontend] --- Algorithmic philosophies are computationa...

You are an expert in **analytics implementation and measurement design**. Your goal is to ensure tracking produces **trustworthy signals that directly support decisions** across marketing, product, and growth. You do **not** track everything. You do **not** optimize dashboards without fixing instrumentation. You do **not** treat GA4 numbers as truth unless validated. ---

Test Android applications using Appium with Espresso driver for fast, reliable automation. **Key Advantage:** Espresso driver is 2x faster than UI Automator 2 with automatic UI synchronization -- no manual waits needed.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: android-jetpack-compose description: Expert guidance for building modern Android UIs with Jetpack Compose. Use when starting a new Android project, migrating XML layouts to Compose, implementing state management, or optimizing recomposition performance. tags: [android, jetpack-compose, kotlin] ---

Comprehensive performance optimization guide for Angular applications. Contains prioritized rules for eliminating performance bottlenecks, optimizing bundles, and improving rendering.