A collection of Claude Code AI rules for development best practices.
Explore common use cases for Claude Code: claude-code/common-tasks.
⭐ Learn best practices for Claude Code: engineering/claude-code-best-practices.
Here is my list of practical recommendations for using Claude Code:
- Ask “think hard” to trigger deep thinking:
- "think" < "think hard" < "think harder" < "ultrathink."
- Ask Claude to brainstorm ideas and iterate on them. Later, these ideas can be used as grounding context for your prompts.
- Write a plan to an external source (e.g., file - plan.md) and use it as a checklist.
plan.prompt.md- use an external file as memory for task management and planning.plan modevsauto-accept modevsedit mode:- Verify what is about to be performed using
plan mode. - Once verified, proceed with
auto-accept mode. - Step-by-step mode is the default mode with no auto-accept.
- Verify what is about to be performed using
- Workflows:
- a. Explore, plan, code, commit.
- b. Write tests, commit; code, iterate, commit.
- c. Write code, screenshot results, iterate.
-
Use the
/initcommand to initialize theCLAUDE.mdfile. There’s no required format forCLAUDE.mdfiles. I recommend keeping it concise and human-readable. You can use it to store important information about your project, such as architecture, design decisions, and other relevant details that can help Claude understand your codebase better. -
CLAUDE.mdcan open other files like this:@path/to/import. Be careful, as this file is attached every time you submit a prompt. -
You can use
# <text>to add particular memory to theCLAUDE.mdfile. -
There are two different types:
- Project memory
./CLAUDE.md- share it with your team. - User memory
~/.claude/CLAUDE.md- personal preferences.
- Project memory
-
Use
/memoryto edit the memory file directly. It will open the file in your default editor. -
Codebase Q&A: Use Claude Code to ask questions about your codebase. It can help during onboarding or when you need to understand how something works.
-
Use hints, reference files, provide examples, mention documentation, and provide links.
- Use in “pipe” mode, as Unix philosophy utils:
claude -p ""orecho '' | claude -p "". - 🗑️
/clearand/compact <specific prompt for aggregation>can be very helpful. - 🧠 If you don’t know something about Claude Code, ask it! It’s self-aware.
- E.g., What kind of tools do you have? Can you perform a web search?
You can use MCP servers. See claude-code/mcps.
- Use
/create-prdto create a Product Requirements Document (PRD) based on user input. - Use
/generate-tasksto create a task list from the PRD. - Use
/process-task-listto manage and track task progress.
- General Prompt Engineering with Claude Models - https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview
- Interactive Tutorial for Prompt Engineering - https://github.com/anthropics/prompt-eng-interactive-tutorial
- CLI Usage - https://docs.anthropic.com/en/docs/claude-code/cli-usage
- ⭐ Tutorials - https://docs.anthropic.com/en/docs/claude-code/tutorials
- Claude Code Memory - https://docs.anthropic.com/en/docs/claude-code/memory
Inspired by: