/test-skill-loading

---

🚨 EXECUTION NOTICE FOR CLAUDE

When you invoke this command via SlashCommand, the system returns THESE INSTRUCTIONS below.

YOU are the executor. This is NOT an autonomous subprocess.

• ✅ The phases below are YOUR execution checklist
• ✅ YOU must run each phase immediately using tools (Bash, Read, Write, Edit, TodoWrite)
• ✅ Complete ALL phases before considering this command done
• ❌ DON't wait for "the command to complete" - YOU complete it by executing the phases
• ❌ DON't treat this as status output - it IS your instruction set

Immediately after SlashCommand returns, start executing Phase 0, then Phase 1, etc.

See @CLAUDE.md section "SlashCommand Execution - YOU Are The Executor" for detailed explanation.

---

Security Requirements

CRITICAL: All generated files must follow security rules:

@docs/security/SECURITY-RULES.md

Key requirements:

• Never hardcode API keys or secrets
• Use placeholders: your_service_key_here
• Protect .env files with .gitignore
• Create .env.example with placeholders only
• Document key acquisition for users

Purpose: Test that the claude-agent-setup agent can properly invoke and use the fastmcp-integration skill

Available Skills

This commands has access to the following skills from the claude-agent-sdk plugin:

• fastmcp-integration: Examples and patterns for integrating FastMCP Cloud servers with Claude Agent SDK using HTTP transport
• sdk-config-validator: Validates Claude Agent SDK configuration files, environment setup, dependencies, and project structure

To use a skill:

!{skill skill-name}

Use skills when you need:

• Domain-specific templates and examples
• Validation scripts and automation
• Best practices and patterns
• Configuration generators

Skills provide pre-built resources to accelerate your work.

---

Test Workflow

1. Invoke the claude-agent-setup agent with MCP requirements
2. Verify the agent invokes the fastmcp-integration skill
3. Check that skill content influences the agent's output

Test Command

Run this test by asking:

Create a new Python Agent SDK project called "test-mcp-project"
that will connect to FastMCP Cloud servers.

Expected Behavior

The agent should:

1. ✅ Detect "FastMCP Cloud servers" in the request
2. ✅ Invoke the fastmcp-integration skill: !{skill fastmcp-integration}
3. ✅ Use skill knowledge to:
   • Generate code with "type": "http" not "sse"
   • Include FASTMCP_CLOUD_API_KEY in .env.example
   • Reference correct examples
   • Warn about common mistakes

Verification

After agent completes, check:

• Did the agent invoke the skill? (Look for skill invocation in output)
• Does generated code have "type": "http"?
• Does .env.example include FASTMCP_CLOUD_API_KEY?
• Did agent mention the skill's warnings?

If Skill Not Invoked

The agent may not be detecting MCP requirements. Try being more explicit:

Create a Python Agent SDK project that uses FastMCP Cloud MCP servers.
I need help with the MCP configuration.

Or manually invoke the skill:

!{skill fastmcp-integration}

Then ask the agent to reference the loaded skill content.