mfielding92
- 41 skills
- 0 followers
- 15 hours ago last updated
- ▌ Tdd · mfielding92Test-driven development workflow. Use when implementing features or fixing bugs where the user says "TDD", "test first", "write tests", or wants a red-green-refactor cycle.
- ▌ Wizard · mfielding928-phase implementation methodology with built-in verification at each stage. Use for implementing features, fixing complex bugs, or any task where quality matters. Use when the user says "wizard mode", "do this properly", "production quality", or "full workflow".
- ▌ Sudo · mfielding92Run commands requiring sudo in a visible terminal window where the user can enter their password interactively. Use when a command needs root privileges, elevated permissions, "sudo", "install system package", "apt install", "dnf install", "pacman -S", or any operation requiring admin access.
- ▌ Wrap Up · mfielding92End-of-session retrospective that captures accomplishments, learnings, and decisions to project memory. Use when the user says "wrap up", "end session", "what did we do", "save what we learned", "session summary", "I'm done for now", or when context is approaching capacity.
- ▌ Grill Me · mfielding92Deep interview to reach shared understanding before building. Use when starting a complex feature, when requirements are unclear, or when the user says "grill me", "interview me", "ask me questions", "let's figure this out", or "grill me lightly" for a quick version.
- ▌ Refactor · mfielding92Safely refactor code with characterization tests and incremental changes. Use when the user says "refactor", "clean up", "extract", "rename", "restructure", or needs to modernize legacy code.
- ▌ Research · mfielding92Structured web research with source evaluation and synthesis. Use when the user says "research", "look up", "find out", "what's the best way to", "how do people", "find documentation for", or needs information from the web to make a decision.
- ▌ Workflow · mfielding92Define and run multi-step workflows that chain skills, agents, and tasks together with state tracking. Use when the user says "workflow", "pipeline", "chain these steps", "run my pipeline", "define a workflow", "automate these steps", or has a task with more than 3 sequential steps.
- ▌ Code Review · mfielding92Review code changes for quality, security, and correctness. Use when the user says "review this PR", "review these changes", "check my code", "look at what I changed", or after implementing a feature. Produces a severity-organized report.
- ▌ New Project · mfielding92Create a fully configured new project with Claude Code best practices, skills, and agents. Use when the user says "new project", "start a project", "create a project", "set up a new", or "bootstrap a project".
- ▌ Skill Store · mfielding92Browse, install, and uninstall skills and agents from the available library. Check for new ones online. Use when the user says "what skills are available", "install skill", "add skill", "remove skill", "skill catalog", "list available", "check for updates", or wants to set up a project with specific capabilities.
- ▌ Voice Style · mfielding92 bundleSwitch Claude's interaction style and voice. Use when the user says "switch to", "use style", "talk like", "be more", "change voice", "mode", or names a specific style like "concise", "learning", "deep-thinking", "shakespeare", "diva", or any custom style name.
- ▌ Git Workflow · mfielding92Structured git workflow for commits, branches, and PRs. Use when the user says "commit", "create a PR", "new branch", "prepare for review", "ship this", or "push my changes". Safe, conventional git operations with checkpoints.
- ▌ Lat Md Setup · mfielding92 bundleSet up lat.md knowledge graph for a project. lat.md replaces flat AGENTS.md/CLAUDE.md with an interconnected, validated graph of markdown docs linked to source code. Use when user says "set up lat.md", "install lat.md", "add knowledge graph", "lat md", "agent lattice", or wants structured, validated project documentation that stays in sync with code. Also triggered via "lat-md-setup checklist" to return just the recommendation checklist.
- ▌ Project Init · mfielding92Initialize or optimize a project for Claude Code. Use when setting up a new project, onboarding to an existing codebase, or when the user says "set up Claude Code", "create CLAUDE.md", "bootstrap", or "optimize this project for Claude".
- ▌ Android UI · mfielding92Design and implement minimal, thoughtful Android UI with Material Design 3. Use when the user says "Android UI", "design a screen", "layout", "Jetpack Compose", "XML layout", "material design", "Android interface", or needs to build Android screens, components, or navigation.
- ▌ Brainstorm · mfielding92Structured brainstorming and ideation session. Use when the user says "brainstorm", "ideas for", "what if", "help me think about", "I'm stuck", "explore options", or needs creative problem-solving.
- ▌ Plan And Spec · mfielding92Create a structured implementation plan with spec-driven modeling. Use when starting a new feature, complex refactor, or when the user says "plan this", "spec this out", "design this", or "how should we build this". Forces multiple design iterations before coding.
- ▌ Skill Creator · mfielding92 bundleCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
- ▌ Voice Creator · mfielding92Create a custom voice/interaction style template. Use when the user says "create a voice", "make a style", "new personality", "custom voice", "I want Claude to talk like", or provides examples of a writing style they want to replicate.
- ▌ Hf Finetune · mfielding92Fine-tune a HuggingFace transformer model with Trainer API or custom loop. Use when the user says "fine-tune", "finetune", "HuggingFace", "Trainer", "SFT", "PEFT", "LoRA", "custom LLM", "adapt a model", or "train a transformer".
- ▌ Hooks Setup · mfielding92Configure Claude Code hooks for automatic formatting, safety guards, compaction recovery, and session management. Use when the user says "set up hooks", "auto-format", "block dangerous commands", "configure automation", "safety rules", or wants deterministic automation.
- ▌ SEO Content · mfielding92Create SEO-optimized content with proper structure, keywords, and schema. Use when the user says "write a blog post", "SEO", "optimize for search", "content for", "article about", or needs search-optimized writing.
- ▌ Web Starter · mfielding92Scaffold a new web project with modern best practices. Use when the user says "create a website", "new web project", "landing page", "scaffold", "starter", or "set up a web app".
- ▌ Context Doctor · mfielding92Diagnose and fix context window issues. Use when Claude seems confused, forgetful, slow, or the user says "context is full", "you forgot", "you're repeating yourself", "start fresh", or "why are you ignoring my instructions".
- ▌ Model Export · mfielding92Export and quantize ML models for deployment. Use when the user says "export model", "GGUF", "llama.cpp", "quantize", "ONNX", "TorchScript", "deploy model", "convert model", "run locally", "Ollama", or "inference server".
- ▌ Android Build · mfielding92Build, compile, sign, install, and debug Android apps from the command line. Use when the user says "build APK", "compile Android", "install on device", "ADB", "debug Android", "sign APK", "release build", "Gradle build", or needs to get an Android app onto a device.
- ▌ Android Setup · mfielding92Set up Android development environment with SDK, ADB, and build tools. Use when the user says "set up Android", "install Android SDK", "configure ADB", "Android development environment", "I want to build an Android app", or needs to compile/debug Android apps from the command line.
- ▌ Canvas Design · mfielding92 bundleCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
- ▌ Compile To Skill · mfielding92 bundleTranspile source code into Claude Code markdown skills. Takes Python, JavaScript, TypeScript, C++, Rust, Go, or any terminal-based program and converts it into an LLM-executable markdown skill. Analyzes code structure, fuzzes runtime behavior, classifies operations, and generates a complete skill directory with SKILL.md, bundled scripts, and reference docs. Use when user says "compile to skill", "convert this code to a skill", "make a skill from this script", "turn this into a skill", "transpile to skill", or wants to translate any traditional program into Claude Code's markdown skill format. Also use when user pastes code and asks to make it work as a Claude skill.
- ▌ Existing Project · mfielding92Install Claude Code expert toolkit into an existing project. Use when the user says "add to my project", "install into existing", "set up existing project", "integrate", "add skills to this project", or wants to enhance an already-started codebase with Claude Code best practices.
- ▌ Progress Tracker · mfielding92Create and update progress/handoff documents for long-running work. Use when nearing context limits, switching tasks, ending a session, or when the user says "save progress", "handoff", "wrap up", or "I need to pick this up later".
- ▌ Shared Context · mfielding92Set up a centralized shared context folder for your project with brand voice, audience personas, and domain knowledge. Use when the user says "set up brand context", "create voice profile", "define our audience", "shared context", "ICP setup", or wants consistent non-generic output across skills.
- ▌ Torch Optimize · mfielding92Profile and optimize PyTorch training and inference for speed and memory. Use when the user says "too slow", "OOM", "out of memory", "optimize training", "speed up", "torch profiler", "mixed precision", "memory efficient", "faster", or "GPU utilization".
- ▌ Training Infra · mfielding92Set up production training infrastructure with distributed training, experiment tracking, checkpointing, and reproducibility. Use when the user says "multi-GPU", "distributed training", "W&B", "Weights and Biases", "MLflow", "DDP", "experiment tracking", "resume training", or "reproducible".
- ▌ Android Backend · mfielding92Write complete, tested Android backend logic with MVVM architecture. Use when the user says "Android backend", "ViewModel", "Room database", "API call", "repository pattern", "Android data layer", "write Android logic", or needs business logic, data persistence, or network calls in an Android app.
- ▌ Python Scaffold · mfielding92Scaffold a new Python project with modern best practices. Use when the user says "new Python project", "create a Python app", "scaffold Python", "set up a Python package", or "Python starter".
- ▌ Deploy Checklist · mfielding92Pre-deployment verification checklist. Use before deploying to production, staging, or any environment. Use when the user says "deploy", "ship", "release", "go live", or "push to production".
- ▌ Unsloth Finetune · mfielding92Fine-tune LLMs with Unsloth for 2x+ faster training and lower memory usage. Use when the user says "Unsloth", "unsloth", "fast fine-tuning", "efficient LoRA", or wants to fine-tune Llama, Mistral, Qwen, or Gemma efficiently.
- ▌ Project Optimizer · mfielding92Deep scan and optimization of your project's Claude Code setup, workflows, and codebase patterns. Use when the user says "optimize", "audit my project", "scan for improvements", "how can I improve", "check my setup", or "what am I doing wrong".
- ▌ Pytorch Training Loop · mfielding92Build a complete PyTorch training loop with best practices. Use when the user says "training loop", "train a model", "PyTorch training", "write the training code", "fit a model", or "set up training".