claude-ide-bridge: Skill for Claude Code

IDE Debug Workflow

Prerequisites

1. Check if the getToolCapabilities MCP tool is available to you.

   • Not available (no MCP tool by that name): stop and tell the user: "This skill requires the Claude IDE Bridge with a connected VS Code extension. It uses debug tools (breakpoints, debugger evaluation, debug state) that have no CLI equivalent.

     To use this skill:

     1. Start the bridge: npm run start-all (in claude-ide-bridge/)
     2. Ensure the Claude IDE Bridge extension is installed in your IDE
     3. Use the claude --ide session (not remote-control)

     Alternative: run tests directly via npm test to identify failures."

   • Available: call it. If extensionConnected is false: show the same message. If true: proceed.

Run a complete debug cycle using the IDE bridge's debug and test tools. This workflow automates what would normally require switching between terminal, editor, and debugger.

Workflow

Phase 1: Identify the failure

1. Run tests using runTests with the provided filter argument: $ARGUMENTS
   • If no argument provided, run the full test suite
2. If all tests pass, report success and stop
3. For each failure, note the file, line, test name, and error message

Phase 2: Set up debugging

1. For the first failing test, use goToDefinition or openFile to navigate to the failing code
2. Use getDocumentSymbols on the test file to understand the test structure
3. Use setDebugBreakpoints to set a breakpoint at the assertion line or the line referenced in the error
   • Use conditional breakpoints when the error message suggests a specific condition

Phase 3: Inspect runtime state

1. Use startDebugging with the appropriate debug configuration
   • For vitest/jest: look for "Vitest" or "Jest" debug configs
   • For pytest: look for "Python" debug configs
2. When the breakpoint hits, use evaluateInDebugger to inspect:
   • The variables mentioned in the error message
   • The expected vs actual values
   • Any intermediate computation results
3. Use getDebugState to examine the full call stack and scope variables
4. Use stopDebugging once you've identified the root cause