From workflows
Use BEFORE reading multiple files to understand code. Reminds you to use codebase-analyzer agent instead of manual file reading.
How this skill is triggered — by the user, by Claude, or both
Slash command
/workflows:skills/before-code-analysisThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**STOP**: You're about to read multiple files to understand how something works.
STOP: You're about to read multiple files to understand how something works.
The codebase-analyzer agent is specifically designed for understanding code implementation. It will read files in context and explain how systems work.
Read(file_path="src/auth/handler.js")
Read(file_path="src/auth/service.js")
Read(file_path="src/auth/middleware.js")
[manually piecing together how auth works]
Task(
subagent_type="codebase-analyzer",
prompt="Analyze how the authentication system works, including handlers, services, and middleware",
description="Analyze auth system"
)
Only read files manually when:
For understanding systems or flows, use codebase-analyzer.
npx claudepluginhub eveld/claude --plugin workflowsReads every source file in full to build deep understanding of a new or unfamiliar codebase. Invoke when onboarding or asked to 'learn the codebase'.
Explores codebase areas: maps files, traces data flows, identifies patterns and dependencies. For 'how does X work', architecture queries, or pre-change analysis.
Guides systematic codebase exploration through collaborative dialogue, starting with clarifying questions before investigating architecture, patterns, and implementation details.