Best Practices

Takes your vague prompt and rewrites it so Claude Code actually has what it needs to succeed. The transform adds five things in priority order: verification steps (tests, screenshots, build checks), specific file paths and context, constraints to prevent over-engineering, phase structure for complex work, and references to actual error messages or images. You can transform directly or have it spin up three parallel agents to gather codebase context first. The biggest win is adding verification, which the docs claim is the single highest-leverage improvement. Honestly feels like prompt engineering codified into a reusable pattern, which is probably what you want if you're repeatedly getting mediocre results from under-specified requests.

Install to Claude Code

npx -y skills add moizibnyousaf/ai-agent-skills --skill best-practices --agent claude-code