claude-tricks

Autonomous full-stack engineer that takes a requirement from idea to production-ready code. Researches best approaches, prototypes unknowns, builds a comprehensive plan broken into waves of parallel tasks, executes via sub-agents, tests everything, audits for security, and delivers a final handoff report with any manual steps needed. Use this agent when the user wants to build something substantial — a feature, service, app, tool, integration, migration, or any non-trivial engineering task.

Look up any arxiv paper on alphaxiv.org to get a structured AI-generated overview. This is faster and more reliable than trying to read a raw PDF.

Autonomous research loop that iteratively improves code through experiments. Runs experiments on local or remote GPUs, tracks results, keeps improvements, discards failures, and never stops. TRIGGER THIS SKILL when users want to autonomously research, optimize, or experiment on a problem — whether they say "run experiments overnight", "optimize this model", "try different approaches and keep what works", "do research on this", "iterate on this until it gets better", "run an experiment loop", or want to improve any metric through systematic trial and error. Also trigger when users mention autonomous experimentation, hyperparameter search, architecture search, ablation studies, or want Claude to keep trying things while they step away. This skill works for ML training, compiler optimization, algorithm tuning, performance benchmarking, or any problem with a measurable metric.

Explains codebases visually with ASCII architecture diagrams, code flow tracing, and interactive deep-dives. TRIGGER THIS SKILL when users want to understand, learn about, or get oriented in a codebase — whether they say "explain this codebase", "what does this project do", "how does this work", "walk me through the code", "show me the architecture", or just seem unfamiliar with a repo. Common trigger patterns include — understanding project structure or architecture, tracing how a request/action flows through code, figuring out how components connect, inheriting or onboarding onto unfamiliar code, exploring what a repo does before making changes, mapping dependencies between modules, asking "how does X work in this codebase", wanting a bird's-eye view of a large project. Also trigger when users ask to trace specific code paths (e.g. "what happens when a user clicks submit", "trace the request lifecycle", "how does auth work end to end"). Do NOT trigger for bug fixes, writing new code, refactoring, CI/CD setup, test writing, PR reviews, or SQL optimization — those are implementation tasks, not understanding tasks.

Debug and fix failing tests or errors

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.