best-practices
Transforms vague Claude Code prompts into effective ones by applying five set constraints on scope and approach, structure complex tasks in phases, and include rich content like error logs and screenshots. Invoke with /best-practices when a prompt needs improvement before execution.
npx skills add majiayu000/claude-skill-registry --skill best-practices-platxa-platxa-skill-generat --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Best Practices -- Prompt Transformer Transform prompts by adding what Claude Code needs to succeed. ## Overview This guide transforms vague or incomplete Claude Code prompts into precise, verifiable instructions. A well-formed prompt gives Claude specific file locations, clear success criteria, explicit constraints, and supporting materials -- reducing correction cycles from 5+ iterations to a single execution. **What you will learn:** - The 5 transformation principles ranked by impact - How to choose between direct transformation and context-first workflows - Prompt patterns for common task types (bug fix, feature, refactor, test, debug, UI, exploration, migration) - An evaluation rubric to score prompt quality before execution **When to use this skill:** - Before submitting a multi-step prompt to Claude Code - When a previous prompt led to a correction spiral (2+ failed attempts) - When reviewing team prompts in shared CLAUDE.md configurations ## Mode Selection When the user provides a prompt to transform, ask using AskUserQuestion: - **Question**: "How should I improve this prompt?" - **Header**: "Mode" - **Options**: 1. **Transform directly** -- Apply the 5 principles and out
- Overview
- Mode Selection
- Learning Path
- Level 1: The Core Rule
- Level 2: The 5 Transformation Principles
- Level 3: Context-First Workflow
- Best Practices
- Do
- Do Not
- Common Questions
- Q: When should I use "Transform directly" vs "Build context first"?
- Q: How do I handle prompts that combine multiple tasks?
- Q: What if the prompt is already well-formed?
- Examples
BEFORE implement email validation AFTER write a validateEmail function. test cases: invalid -> false run the tests after implementing. fix the login bug users report login fails after session timeout. check auth flow in src/auth/, especially token refresh in refresh_token.ts. write a failing test that
What does the best-practices skill do?
Transforms vague Claude Code prompts into effective ones by applying five set constraints on scope and approach, structure complex tasks in phases, and include rich content like error logs and screenshots. Invoke with /best-practices when a prompt needs improvement before execution.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill best-practices-platxa-platxa-skill-generat --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.