Find awesome Agent Skills

recipe-finding

Use when user wants to find recipes or resize recipe portions - provides systematic workflow for searching recipes, scaling ingredients by serving size, handling fractional amounts, and formatting output

whatsapp-message-management

Use when user wants to capture tasks, send briefings, or manage life via WhatsApp - leverages existing WhatsApp MCP for mobile-first workflow

using-life-os

Entry point skill - introduces available Life OS skills, provides command reference, and guides users through the system

grocery-shopping

Use when user needs to create grocery list from recipes - consolidates ingredients across recipes, checks pantry inventory, converts to purchasable quantities, and provides automation options for Costco/Instacart

Fluxwing Component Creator

Create uxscii components with ASCII art and structured metadata when user wants to create, build, or design UI components. Use when working with .uxm files, when user mentions .uxm components, or when creating buttons, inputs, cards, forms, modals, or navigation.

Fluxwing Screen Scaffolder

Build complete UI screens by composing multiple uxscii components. Use when working with .uxm files, when user wants to create, scaffold, or build .uxm screens like login, dashboard, profile, settings, or checkout pages.

fluxwing-validator

Validate uxscii components and screens against schema with interactive menu or direct script calls

Fluxwing Library Browser

Browse and view all available uxscii components including bundled templates, user components, and screens. Use when working with .uxm files, when user wants to see, list, browse, or search .uxm components or screens.

Fluxwing Component Viewer

View detailed information about a specific uxscii component including metadata, states, props, and ASCII preview. Use when working with .uxm files, when user wants to see, view, inspect, or get details about a .uxm component.

Fluxwing Enhancer

Enhance uxscii components from sketch to production fidelity. Use when working with .uxm files marked as "fidelity: sketch" or when user wants to add detail and polish to components.

Fluxwing Component Expander

Add interaction states like hover, focus, disabled, active, error to existing uxscii components. Use when working with .uxm files, when user wants to expand, enhance, or add states to .uxm components.

Fluxwing Screenshot Importer

Import UI screenshots and generate uxscii components automatically using vision analysis. Use when user wants to import, convert, or generate .uxm components from screenshots or images.

claude-code-agent-patterns

Activate when creating or modifying Claude Code agents with proper architecture patterns, tool selection, and extended context integration

technical-documentation

Activate when creating comprehensive documentation including README files, API docs, user guides, and developer guides

claude-code-command-patterns

Activate when creating or modifying Claude Code slash commands with proper frontmatter, Task invocation patterns, and TodoWrite integration

code-quality-assessment

Activate when analyzing code quality through linting, formatting, testing, coverage analysis, and maintainability metrics

requirements-engineering

Activate when creating Product Requirements Documents (PRDs) with business objectives, functional requirements, success criteria, and implementation planning

research-methodology

Activate when conducting topic research with complexity assessment, thinking mode selection, and comprehensive documentation generation

project-discovery

Activate when analyzing codebases to understand project structure, technology stack, dependencies, and development workflows

implementation-planning

Activate when creating detailed implementation plans with phases, tasks, dependencies, and resource allocation for software projects

task-breakdown

Activate when breaking down implementation plans into detailed task lists with agent contexts, acceptance criteria, and status tracking

security-stride-methodology

Activate when conducting security analysis using STRIDE threat modeling, vulnerability assessment, and security architecture evaluation

file-organizer

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

marcusrbrown

research-tools

External research via Context7 (docs), Grep.app (code examples), Tavily (web search, extract, crawl), and Exa (web search). Loads MCPs on-demand via skill_mcp.

marcusrbrown

content-research-writer

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

marcusrbrown

iosdev-cn

通用 iOS App 开发、构建、签名、测试与 App Store 上架流程（中国区）指南。用于当用户询问 iOS 开发/上架/审核/签名/TestFlight/App Store Connect/隐私合规/订阅配置，或输入触发词 iosdev 时。

kuangre123

pytorch

Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.

qlora

Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.

mlx

Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.

prompt-engineering

Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.

rlhf

Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.

transformers

Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text, vision, audio, and multimodal tasks.

lora

Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.

agents

Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.

context-engineering

Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.

V3 Core Implementation

Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.

V3 CLI Modernization

CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.

Swarm Orchestration

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

swarm-advanced

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

stream-chain

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

sparc-methodology

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration

Skill Builder

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.

ReasoningBank Intelligence

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.