---

name: "testing_protocol" version: "1.0.0" description: "Testing workflow tools following Modified-Code Protocol for intelligent test selection." routing_keywords: [ "testing protocol", "smart test", "modified code", "test selection", "what to test", "test strategy", "which tests", ] authors: ["omni-dev-fusion"] intents:

• "Determine what tests to run"
• "Create test strategy"
• "Select relevant tests for changes"
• "Plan testing approach"

---

Testing Protocol Skill System Prompts

When using the Testing Protocol skill, follow these patterns for effective test execution.

Modified-Code Protocol

Step 1: Identify Modified Files

The smart_test_runner automatically detects:

• Staged files (git diff --cached --name-only)
• Unstaged files (git diff --name-only)
• Untracked files (git ls-files --others)

Step 2: Categorize Changes

Step 3: Execute Appropriate Tests

• Skip: Return immediately with rationale
• MCP only: Run just test-mcp-only
• Full: Run just test

When to Use Each Tool

smart_test_runner (Most Common)

Copyawait smart_test_runner()

Automatically determines what to test.

smart_test_runner with focus

Copyawait smart_test_runner(focus_file="src/agent/tests/test_phase13.py")

When you know exactly what to test.

run_test_command

Copyawait run_test_command(command="just test-mcp-only")

When you need to run a specific test command.

get_test_protocol

Copyawait get_test_protocol()

To remind yourself of the protocol rules.

Test Command Reference

Common Scenarios

After making a documentation change

Copyawait smart_test_runner()
# Returns: {"strategy": "skip", "reason": "Docs only - skipping tests"}

After changing MCP server code

Copyawait smart_test_runner()
# Returns: {"strategy": "mcp_only", "command": "just test-mcp-only"}

After changing Nix configuration

Copyawait smart_test_runner()
# Returns: {"strategy": "full", "command": "just test"}

After a bug fix in Python code

Copyawait smart_test_runner()
# Returns: {"strategy": "full", "command": "just test"}