Reuse for Claude Codes
Reuse in Claude Code means packaging instructions and behaviour so they can be invoked repeatedly. Skills bundle instructions and files that load when relevant, custom slash commands save common prompts, output styles change how the agent responds, and model selection balances speed, cost and capability for each task.
Stage: Customisation · Part of the Claude Code roadmap · Last reviewed 19 November 2026
What to learn in Reuse
- Create a custom slash command for a prompt you repeat often
- Write a skill with a description that triggers it at the right time
- Switch models for quick edits versus hard reasoning tasks
- Change the output style to suit teaching or terse work
- Share commands and skills with a team through the repository
Reuse interview questions
What is the difference between a skill and a slash command?
A slash command is a saved prompt you invoke by name. A skill is a folder of instructions and optional scripts that the agent can load automatically when a task matches its description, so it can carry more structure and supporting files.
Why would you switch models during a project?
Smaller, faster models are cheaper for simple edits and searches, while a more capable model handles design, debugging and multi-file reasoning better. Matching the model to the task controls cost and latency without losing quality where it matters.
Where Reuse fits in the Claude Code roadmap
Reuse belongs to the Customisation stage (beginner level), which takes about 8 hours. Make it yours.
Other units in this stage
Back to the full Claude Code roadmap