Provides a read-only structural map of Claude Code configurations in a target project.

Install

mkdir -p .claude/skills/scan && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18169" && unzip -o skill.zip -d .claude/skills/scan && rm skill.zip

Installs to .claude/skills/scan

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Scan and map the Claude Code configuration of a target project without auditing. Use when someone says "scan project", "show structure", "map config", or just wants to see what Claude Code configuration exists.
210 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Validate if the provided path is a valid directory
  • Produce a structural map of the Claude Code configuration
  • Identify the project type (single, monorepo, child)
  • List all CLAUDE.md files with line counts
  • Show the complete `.claude/` inventory
  • Report subprojects and siblings if a monorepo is detected

How it works

The skill validates a provided directory path, then uses a `project-scanner` agent to generate a structural map of the Claude Code configuration. It presents this report to the user, including project type, CLAUDE.md files, and `.claude/` inventory.

Inputs & outputs

You give it
A target project directory path
You get back
A structural map of the Claude Code configuration

When to use scan

  • Mapping project structure
  • Viewing Claude Code configuration
  • Checking monorepo configuration

About this skill

Project Scan

Map the complete Claude Code configuration structure of the project at $ARGUMENTS.

Steps

  1. Validate input: Confirm $ARGUMENTS is a valid directory path. If empty, ask the user for the target project path.

  2. Run scanner: Use the project-scanner agent to produce a full structural map. Pass the complete path as the agent's prompt.

  3. Present results: Display the scanner's report directly to the user. Include:

    • Project type (single/monorepo/child)
    • Parent context (if any)
    • All CLAUDE.md files with line counts
    • Complete .claude/ inventory
    • Subprojects and siblings (if monorepo)
    • Quick potential issues
  4. Suggest next steps:

    ### Next Steps
    - Run `/audit $ARGUMENTS` for a quick quality audit
    - Run `/audit-full $ARGUMENTS` for a comprehensive deep audit
    

Important

  • This is READ-ONLY — no modifications, no quality judgments
  • Just map and report what exists
  • If monorepo detected, show the full ecosystem map

When not to use it

  • When modifications to the project are needed
  • When a quality judgment or audit is required
  • When detailed code analysis is needed

Limitations

  • It is a read-only operation
  • It does not perform modifications
  • It does not make quality judgments

How it compares

This skill provides a read-only structural overview of a project's Claude Code configuration, which is different from manually inspecting directories and files to understand the setup.

Compared to similar skills

scan side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
scan (this skill)04moNo flagsBeginner
lisa-lint01moNo flagsBeginner
redirect-article028dReviewBeginner
seo-review96moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry