← Back to Skills Marketplace
eaveluo

Claude Code Setup

by Eave Luo · GitHub ↗ · v1.0.1
cross-platform ✓ Security Clean
435
Downloads
0
Stars
2
Active Installs
2
Versions
Install in OpenClaw
/install claude-code-setup
Description
Setup production-grade .claude/ AI collaboration layer for projects. Use when an agent starts using Claude Code for development, enters a new project directo...
README (SKILL.md)

Claude Code Setup

Setup production-grade `.claude/` AI collaboration layer for projects.

Overview

This skill ensures projects have a proper `.claude/` configuration before agents start development work with Claude Code. It acts as a supervisor to maintain and enforce project standards.

Important: Target Project Directory

.claude/ must be created in the target project directory, NOT in your workspace root.

Example:

  • ❌ Wrong: /home/user/workspace-xiaolong/.claude/ (workspace root)
  • ✅ Correct: /home/user/eave-web/.claude/ (actual project being developed)

Always identify which project you're working on first, then check/create .claude/ in that directory.

When to Use

  • Starting a new development task with Claude Code
  • Entering a new project directory
  • User mentions "Claude Code", ".claude", "AI collaboration layer", or "project standards"

Workflow

Step 1 — Check First

Always check if `.claude/` directory already exists in the target project directory:

```bash ls -la .claude/ 2>/dev/null ```

Step 2 — If Missing → Create

If the project doesn't have `.claude/` directory, create it first before development:

```bash node ~/.openclaw/skills/claude-code-setup/index.js ```

Step 3 — If Exists → Supervise

If `.claude/` already exists:

  • DO NOT overwrite existing files
  • DO NOT recreate the structure
  • ✅ Let Claude Code naturally maintain and update during development

Step 4 — Be a Supervisor

Your role is supervisor, not executor:

  • Ensure Claude Code follows rules in `.claude/`
  • During development, let Claude Code update configs based on actual code
  • Periodically review if `.claude/` content matches the project reality

Core Principles

  1. CLAUDE.md is core — Highest priority project instructions
  2. Modular — Separate rules/skills/context
  3. Clear directives — Use MUST/ALWAYS/NEVER
  4. Project context — Must include project overview and tech stack
  5. Don't reinvent — Reuse and maintain existing configs

.claude/ Directory Structure

``` .claude/ ├── CLAUDE.md # ⭐ Project-level global instructions (most important) ├── rules/ # Team rule library │ ├── frontend.md │ ├── typescript.md │ └── commit.md ├── context/ # Project context knowledge │ ├── project.md │ └── stack.md ├── skills/ # Project-private skills │ └── generate-crud.md └── prompts/ # Reusable prompt templates └── review.md ```

Common Mistakes to Avoid

❌ Writing as requirements doc or README
❌ Vague rules ("try to", "should")
❌ Only CLAUDE.md without modularity
❌ Missing project context
❌ Overwriting existing configs
❌ Redundant recreation

Collaboration with Claude Code

When using Claude Code:

  1. Before starting: Ensure `.claude/` exists
  2. During development: Let Claude Code reference rules in `.claude/`
  3. After completion: Update `.claude/` with any new standards learned

Template Files

See `index.js` for template definitions.

Usage Guidance
This skill appears to do what it says: create a .claude/ directory and populate it with templates. Before running it: (1) ensure your shell's current working directory is the exact project directory you intend — running it in the wrong folder will create .claude/ there; (2) inspect index.js if you want to verify templates or behavior (it is included and easy to read); (3) you can run it without --force to avoid overwriting existing files (the script checks and skips existing files); (4) there are no network calls or credential requests, but treat any file-write operation carefully in sensitive repositories (consider running in a disposable test repo first).
Capability Analysis
Type: OpenClaw Skill Name: claude-code-setup Version: 1.0.1 The skill's primary purpose is to set up a `.claude/` directory structure with configuration files for an AI agent (Claude Code) in the current project directory. The `SKILL.md` instructs the OpenClaw agent to execute the `index.js` script, which then uses standard Node.js file system operations (`fs.mkdirSync`, `fs.writeFileSync`) to create the specified directories and populate them with markdown templates. These templates contain guidelines and rules for the *target* AI, including security best practices (e.g., 'No hardcoded secrets', 'Input validation present' in `prompts/review.md`). There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection against the OpenClaw agent to perform unauthorized actions. The script is transparent and avoids overwriting existing configurations by default.
Capability Assessment
Purpose & Capability
Name/description match the actual behavior: SKILL.md and index.js both set up a .claude/ directory and populate it with template files. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
Runtime instructions tell the agent to check for .claude/ and, if missing, run the bundled index.js to create templates. That is appropriate for the purpose, but the instructions and script will write files into the current working directory — the SKILL.md warns about choosing the correct project directory. Confirm you run it in the intended project to avoid accidental writes.
Install Mechanism
No install spec or remote downloads. The skill is instruction-only for install but includes a local index.js script (no obfuscated code or external fetch). This is low-risk compared with network installs.
Credentials
The skill requests no environment variables or credentials and only accesses the working directory and .claude/ path; access is proportional to its stated function.
Persistence & Privilege
always:false and default autonomous invocation are set. The skill does write files to the project but does not request persistent elevated privileges or modify other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install claude-code-setup
  3. After installation, invoke the skill by name or use /claude-code-setup
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Add important note: .claude/ must be created in target project directory, not workspace root
v1.0.0
Initial release: Setup production-grade .claude/ AI collaboration layer for projects
Metadata
Slug claude-code-setup
Version 1.0.1
License
All-time Installs 2
Active Installs 2
Total Versions 2
Frequently Asked Questions

What is Claude Code Setup?

Setup production-grade .claude/ AI collaboration layer for projects. Use when an agent starts using Claude Code for development, enters a new project directo... It is an AI Agent Skill for Claude Code / OpenClaw, with 435 downloads so far.

How do I install Claude Code Setup?

Run "/install claude-code-setup" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Claude Code Setup free?

Yes, Claude Code Setup is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Claude Code Setup support?

Claude Code Setup is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Claude Code Setup?

It is built and maintained by Eave Luo (@eaveluo); the current version is v1.0.1.

💬 Comments