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.

skills.sh installs: 531
GitHub stars: 1.2K
last updated: May 5, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Best Practices — Prompt Transformer

Transform prompts by adding what Claude needs to succeed.

Start Here

Based on user's request:

User provides a prompt to transform: → Ask using AskUserQuestion:

Question: "How should I improve this prompt?"
Header: "Mode"
Options:
1. Transform directly — "I'll apply best practices and output an improved version"
2. Build context first — "I'll gather codebase context and intent analysis first"

User asks to learn/understand: → Show the 5 Transformation Principles section

User asks for examples: → Link to references/before-after-examples.md

User asks to evaluate a prompt: → Use the Success Criteria eval rubric at the end of this document

If "Transform directly"

Apply the 5 principles below and output the improved prompt immediately.

If "Build context first"

Launch 3 parallel agents to gather context:

Run these agents IN PARALLEL using the Task tool:

- Task task-intent-analyzer("[user's prompt]")
- Task best-practices-referencer("[user's prompt]")
- Task codebase-context-builder("[user's prompt]")