开始使用免费开始使用

Tightening the codebase-onboarding skill

A teammate just shared a personal skill called codebase-onboarding to help new hires get oriented in a service repo, and it's already installed at ~/.claude/skills/codebase-onboarding/SKILL.md.

There are two problems with it that waste context every time the skill loads:

  1. It leaves Claude with full edit and write permission (the skill is supposed to be read-only. New hires shouldn't get an agent that modifies code while they're just trying to look around).
  2. The body is huge because the entire architecture reference was pasted directly into SKILL.md instead of split into a separate file.

In this exercise you'll fix both: add an allowed-tools allowlist that restricts the skill to read-only discovery, and apply progressive disclosure by moving the architecture reference into its own file under references/

本练习是课程的一部分

Introduction to Agent Skills

查看课程

练习说明

  • Start Claude Code with claude.
  • Ask Claude to read ~/.claude/skills/codebase-onboarding/SKILL.md and identify any design issues.
  • Ask Claude to add an allowed-tools field to the frontmatter restricting the skill to read-only discovery tools.
  • Ask Claude to apply progressive disclosure by moving the architecture reference into references/architecture.md and replacing it with a link.
  • Type /exit to exit Claude Code.

动手互动练习

通过我们的互动练习之一,将理论转化为实践

开始练习