Claude Skills by frank-luongt

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: prompt-engineer description: Expert prompt engineer specializing in advanced prompting tags: [ai, prompt-engineering] ---

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Prompt Guard is an 86M parameter classifier that detects prompt injections and jailbreak attempts in LLM applications.

Create Pydantic models following the multi-model pattern for clean API contracts.

You are a Python project architecture expert specializing in scaffolding production-ready Python applications. Generate complete project structures with modern tooling (uv, FastAPI, Django), type hints, testing setup, and configuration following current best practices.

Comprehensive guide to creating, structuring, and distributing Python packages using modern packaging tools, pyproject.toml, and publishing to PyPI.

> Python development principles and decision-making for 2025. > **Learn to THINK, not memorize patterns.**

Comprehensive guide to profiling, analyzing, and optimizing Python code for better performance, including CPU profiling, memory optimization, and implementation best practices.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: python-pro description: Master Python 3.12+ with modern features, async programming, tags: [backend, python] --- You are a Python expert specializing in modern Python 3.12+ development with cutting-edge tools and practices from the 2024/2025 ecosystem.

Comprehensive guide to implementing robust testing strategies in Python using pytest, fixtures, mocking, parameterization, and test-driven development practices.

This skill teaches a coding agent how to **add PyTorch FSDP2** to a training loop with correct initialization, sharding, mixed precision/offload configuration, and checkpointing. > FSDP2 in PyTorch is exposed primarily via `torch.distributed.fsdp.fully_shard` and the `FSDPModule` methods it adds in-place to modules. See: `references/pytorch_fully_shard_api.md`, `references/pytorch_fsdp2_tutorial.md`. ---

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: pytorch-lightning description: PyTorch Lightning high-level training framework. Use when building structured ML training loops with distributed training, callbacks, and logging. tags: [pytorch-lightning, distributed-training, scaling] ---

pyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-based framework for activation patching, causal tracing, and interchange intervention training - making intervention experiments reproducible and shareable. **GitHub**: [stanfordnlp/pyvene](https://github.com/stanfordnlp/pyvene) (840+ stars) **Paper**: [pyvene: A Library for Understanding and Improving PyTorch Models via Interventions](https://aclanthology.org/2024.naacl-dem...

Comprehensive QA engineering toolkit for creating test plans, generating manual test cases, building regression suites, validating designs, and documenting bugs.

High-performance vector database written in Rust for production RAG and semantic search.

Master Retrieval-Augmented Generation (RAG) to build LLM applications that provide accurate, grounded responses using external knowledge sources.

Distributed data processing library for ML and AI workloads.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: ray-train description: Ray Train distributed training framework. Use when orchestrating distributed training across heterogeneous compute with fault tolerance. tags: [ray-train, distributed-training, scaling] ---

Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 57 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.

You are a frontend engineer focused on transforming designs into clean React code. You follow a modular approach and use automated tools to ensure code quality.

Create React Flow node components following established patterns with proper TypeScript types and store integration.

Master React version upgrades, class to hooks migration, concurrent features adoption, and codemods for automated transformation.

Production-ready patterns for React Native development with Expo, including navigation, state management, native modules, and offline-first architecture.

Comprehensive guide to modern React state management patterns, from local component state to global stores and server state synchronization.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: react-ui-patterns description: React UI patterns for loading states, error handling, button states, empty states, and form submissions. Use when building UI components that handle async data, managing loading/error/empty states, or implementing optimistic updates. tags: [react, ui, state-management] ---

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: reference-builder description: Creates exhaustive technical references and API documentation. tags: [documentation, reference] ---

Transform technical changelogs, PRs, and tickets into clear, user-facing release notes that communicate **what changed and why it matters** — in language customers understand. ---

You are a video production specialist focused on creating engaging walkthrough videos from app designs. You combine Stitch's screen retrieval capabilities with Remotion's programmatic video generation to produce smooth, professional presentations.

Transform vague requirements into actionable PRDs through systematic clarification with a 100-point scoring system.

End-to-end RevOps framework for pipeline analytics, revenue forecasting, quota management, and cross-functional alignment between Sales, Marketing, and Customer Success.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: risk-manager description: Monitor portfolio risk, R-multiples, and position limits. Creates tags: [business, risk] ---

Test React Native mobile applications using Maestro, Detox, or Appium frameworks.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: rwkv description: RWKV linear-attention RNN-Transformer hybrid architecture. Use when needing efficient inference with linear time complexity for long sequences. tags: [rwkv, model-architecture, training] ---

Patterns for using S3 as the document and artifact layer for AI agent workflows.

SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity. **GitHub**: [jbloomAus/SAELens](https://github.com/jbloomAus/SAELens) (1,100+ stars)

Patterns for managing distributed transactions and long-running business processes.

Build AI agents that connect to Salesforce CRM using Agentforce skills, the Einstein Trust Layer, Data Cloud grounding, and MuleSoft connectors.

Automate Salesforce CRM operations through Composio's Salesforce toolkit via Rube MCP.

Build AI agents that connect to SAP enterprise systems using SAP AI Core's Generative AI Hub (multi-LLM), SAP BTP integration, and the ABAP SDK for Google Cloud.

Static Application Security Testing (SAST) tool setup, configuration, and custom rule creation for comprehensive security scanning across multiple programming languages.

Secure secrets management practices for CI/CD pipelines using Vault, AWS Secrets Manager, and other tools.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: security-auditor description: Expert security auditor specializing in DevSecOps, comprehensive tags: [security] --- You are a security auditor specializing in DevSecOps, application security, and comprehensive cybersecurity practices.

You are a compliance expert specializing in regulatory requirements for software systems including GDPR, HIPAA, SOC2, PCI-DSS, and other industry standards. Perform comprehensive compliance audits and provide implementation guidance for achieving and maintaining compliance.

You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and supply chain security. Scan project dependencies across multiple ecosystems to identify vulnerabilities, assess risks, and provide automated remediation strategies.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: security-scanning-security-hardening description: Coordinate multi-layer security scanning and hardening across application, infrastructure, and compliance controls. tags: [security] --- Implement comprehensive security hardening with defense-in-depth strategy through coordinated multi-agent orchestration: [Extended thinking: This workflow implements a defense-in-depth security strategy across all application layers. It coord...

Static Application Security Testing (SAST) for comprehensive code vulnerability detection across multiple languages, frameworks, and security patterns.

Comprehensive guide to using Meta AI's Segment Anything Model for zero-shot image segmentation.

Automate SendGrid email delivery workflows including marketing campaigns (Single Sends), contact and list management, sender identity setup, and email analytics through Composio's SendGrid toolkit.

Python framework for sentence and text embeddings using transformers.

Unsupervised tokenizer that works on raw text without language-specific preprocessing.