Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component...
npx skills add Syncause/debug-skill --skill "syncause-debugger"
Install specific skill from multi-skill repository
# Description
Diagnose and fix bugs using runtime execution traces. Use when debugging errors, analyzing failures, or finding root causes in Python, Node.js, or Java applications.
# SKILL.md
name: syncause-debugger
description: Diagnose and fix bugs using runtime execution traces. Use when debugging errors, analyzing failures, or finding root causes in Python, Node.js, or Java applications.
Syncause Debugger
Use runtime traces to enhance bug fixing: collect runtime data with the SDK, then analyze with MCP tools.
Before fix, create a detailed plan to ensure no details are missed, always include 3 phases: Setup β Analyze β Teardown.
Phase 1: Setup
Pre-check
- MCP Server: This skill depends on
debug-mcp-serverMCP server. If it is not present, STOP and request the user to install the MCP server (Installation Guide). - Authentication: If any MCP Tool returns a
Unauthorizederror, STOP and request the user to configure theAPI_KEY(Installation Guide).
Verify SDK NOT already installed by checking dependency files:
- Java: pom.xml or build.gradle
- Node.js: package.json
- Python: requirements.txt or pyproject.toml
WARNING: .syncause folder is NOT a reliable indicator.
Steps
- Get credentials:
get_project_id(projectPath)β returnsprojectId,apiKey,appName - WARNING: If tool not found or returns
Unauthorized, STOP and follow Pre-check. - Install SDK: Follow language guide:
- Java
- Node.js
- Python
- Verify install: Re-read dependency file to confirm SDK added
- Restart service: Prefer starting new instance on different port over killing process
- Reproduce bug: Trigger the issue to generate trace data
Phase 2: Analyze & Fix
# Step 1: Find trace
search_debug_traces(query="<symptom>") β pick traceId
# Step 2: Get call tree
get_trace_insight(traceId) β find [ERROR] node
# Step 3: Inspect method
inspect_method_snapshot(traceId, methodName) β check args/return/logs
# Step 4 (optional): Compare traces
diff_trace_execution(baseTraceId) β compare fail vs success
Fix: Edit code based on findings, re-run to verify. After fix is confirmed, ALWAYS proceed to Phase 3: Teardown.
WARNING: No traces? β Return to Phase 1, ensure SDK active and bug reproduced.
Phase 3: Teardown
REQUIRED after debugging to restore performance.
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.