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:
- 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).
- The body is huge because the entire architecture reference was pasted directly into
SKILL.mdinstead 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/
Bài tập này là một phần của khóa học
Introduction to Agent Skills
Hướng dẫn bài tập
- Start Claude Code with
claude. - Ask Claude to read
~/.claude/skills/codebase-onboarding/SKILL.mdand identify any design issues. - Ask Claude to add an
allowed-toolsfield 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.mdand replacing it with a link. - Type
/exitto exit Claude Code.
Bài tập tương tác thực hành
Biến lý thuyết thành hành động với một trong các bài tập tương tác của chúng tôi
Bắt đầu bài tập