Practical prompt patterns and techniques for effective Claude Code usage. Reference when crafting prompts, planning workflows, or debugging interactions.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Instead of writing a spec yourself, let Claude interview you:
Start with a minimal description of what I want to build, then interview me
using AskUserQuestion tool. Ask one question at a time until you have enough
information to write a complete specification. Then create the spec document.
Creates better specs than writing them manually. Claude asks questions you wouldn't think of.
Read the entire codebase and explain the architecture to me as if I'm a new
team member. Focus on: data flow, key abstractions, and non-obvious design decisions.
After implementation, challenge Claude to prove correctness:
Grill me on these changes and don't make a PR until I pass your test.
or
Prove to me this works. Diff between main and this branch, explain every change,
and identify any edge cases we missed.
When a fix works but feels hacky:
Knowing everything you know now, scrap this and implement the elegant solution.
Claude's second attempt is almost always better because it has full context of the problem.
Review the code you just wrote as a senior engineer. Be harsh.
What would you change if this was going into a production system
serving 10 million users?
When context is getting heavy:
Use subagents to investigate [topic]. Keep the main context clean.
Explicitly telling Claude to use subagents prevents context pollution.
Process these 5 files in parallel using subagents. Each subagent handles one file.
Collect all results and present a unified summary.
For complex design and architecture decisions:
Before implementing, compare alternative designs and their trade-offs.
Here's the bug: [paste error/screenshot]. Fix it.
Claude fixes most bugs by itself. Don't prescribe the solution.
Paste a screenshot of the issue, then:
Look at this screenshot. The layout is broken. Fix it.
Create a phase-wise plan for this feature. Each phase must have:
1. Clear deliverable
2. Test criteria (unit, integration, or manual verification)
3. Rollback plan if verification fails
Do not proceed to the next phase until the current phase passes all tests.
Before starting a new task in the same session:
/clear
After heavy investigation:
/compact Preserve the key findings about [topic] and the implementation plan
Name important sessions for easy retrieval:
/rename [feature-name implementation v2]
Later: claude --resume to pick up where you left off.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
The English summary is being prepared. Showing the original description.
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
The English summary is being prepared. Showing the original description.
日本語の業務文書を作成・修正するときに使用する共通品質基準。事実性、確度、論理、簡潔さ、自然な日本語を守る。提案書、報告、技術説明、議事録、メール、Slack、要約、レビューに適用する。創作、広告コピー、コードや構造化データだけの生成には使用しない。
The English summary is being prepared. Showing the original description.
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
The English summary is being prepared. Showing the original description.
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.
The English summary is being prepared. Showing the original description.
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
The English summary is being prepared. Showing the original description.