3b128ba3bd
This commit adds comprehensive integration of three major AI agent platforms: ## MCP Servers (3) - Prometheus MCP: Knowledge graph code reasoning with AST analysis - Every Code MCP: Fast terminal-based coding agent with Auto Drive - Dexto MCP: Agent harness with orchestration and session management ## Claude Code Skills (6) - /agent-plan: Generate implementation plans - /agent-fix-bug: Fix bugs end-to-end - /agent-solve: Solve complex problems - /agent-review: Review code quality - /agent-context: Get code context - /agent-orchestrate: Orchestrate workflows ## Ralph Auto-Integration - Pattern-based auto-trigger for all three platforms - Intelligent backend selection - Multi-platform coordination - Configuration in ralph/ralph.yml ## Documentation - Complete integration guides - Ralph auto-integration documentation - Setup scripts - Usage examples Co-Authored-By: Claude <noreply@anthropic.com>
2.5 KiB
2.5 KiB
Agent: Fix Bug
End-to-end bug fixing with reproduction, patch generation, and verification.
Usage
/agent-fix-bug "Login fails after password reset"
Description
The /agent-fix-bug skill fixes bugs through a systematic process:
- Classify the issue type (bug/feature/question/doc)
- Reproduce the bug in isolated environment
- Retrieve relevant code context via knowledge graph
- Generate and apply patch
- Verify fix with regression tests
Examples
Fix a reported bug
/agent-fix-bug "Users with special characters in names cannot sign up"
Fix with specific error
/agent-fix-bug "NullPointerException in UserService.updateProfile
Error: java.lang.NullPointerException: Cannot invoke \"String.length()\" because the return value of \"User.getName()\" is null"
Fix with reproduction steps
/agent-fix-bug "Shopping cart loses items when user switches tabs
Steps:
1. Add item to cart
2. Open new tab
3. Cart appears empty
4. Return to original tab
5. Cart still shows items"
Backends
- Primary: Prometheus (bug pipeline with LangGraph agents)
- Verification: Every Code Auto Review
- Testing: Prometheus (Docker container execution)
Workflow
1. Issue Classification
- Analyze issue description
- Classify as bug/feature/question/documentation
- Identify affected components
2. Bug Reproduction
- Create minimal reproduction case
- Execute in Docker container
- Capture error logs and stack traces
3. Context Retrieval
- Search knowledge graph for related code
- Analyze AST for function call chains
- Identify similar bug fixes
4. Patch Generation
- Generate fix using AI reasoning
- Apply patch with git
- Test in isolated environment
5. Verification
- Run regression tests
- Verify reproduction case is fixed
- Generate test coverage report
Output
✓ Issue classified as: bug
✓ Bug reproduced: UserService.updateProfile throws NPE for null names
✓ Context retrieved: 5 related files, 12 similar issues
✓ Patch generated: Added null check in UserService.updateProfile
✓ Tests passed: 15/15
✓ Regression verified: No existing tests broken
Fix applied: prometheus-backend/src/main/java/com/prometheus/service/UserService.java:47
Follow-up
After fixing:
/agent-review- Review the changes/agent-test- Run specific tests/agent-context- Understand the fix context