Use when adding new error messages to React, or seeing "unknown error code" warnings.
npx skills add TaylorHuston/local-life-manager --skill "troubleshoot"
Install specific skill from multi-skill repository
# Description
Systematic debugging with 5-step loop for issues in spaces/[project]/. Use when encountering bugs, test failures, or unexpected behavior.
# SKILL.md
name: troubleshoot
description: "Systematic debugging with 5-step loop for issues in spaces/[project]/. Use when encountering bugs, test failures, or unexpected behavior."
model: claude-sonnet-4-20250514
allowed-tools: Read, Write, Edit, Glob, Grep, Bash
/troubleshoot
Systematic debugging using a 5-step loop: Research β Hypothesize β Implement β Test β Document.
Usage
/troubleshoot yourbench "tests failing after auth changes"
/troubleshoot yourbench 001 # Debug in context of issue
/troubleshoot coordinatr # General debugging session
The 5-Step Loop
βββββββββββββββββββββββββββββββββββββββββββββββ
β β
β 1. Research β 2. Hypothesize β 3. Implementβ
β β β β
β β β β
β βββββββββ 5. Document β 4. Test βββββββ
β β β
β β β
β (if not fixed, repeat) β
β β
βββββββββββββββββββββββββββββββββββββββββββββββ
Step Details
Step 1: Research
Before guessing, understand:
# Check existing research
Glob: resources/research/*.md
Glob: ideas/[project]/notes/research/*.md
# Search for similar issues in codebase
Grep: spaces/[project]/ for error message
# Check library docs via Context7
# WebSearch for error messages, known issues
Spawn research-specialist agent for:
- Unfamiliar error messages
- Library/framework behavior
- Best practices for the pattern
Step 2: Hypothesize
Form ONE hypothesis:
Hypothesis: Query fires before auth state is set
Evidence:
- isLoading is true when query executes
- Error occurs only on initial load
- Works after manual refresh
Debug Plan:
1. Add console.log before query
2. Check auth state timing
3. Verify order of operations
Only one hypothesis at a time. Multiple theories = confusion.
Step 3: Implement
Apply fix + add debugging:
// Add liberal debug logging
console.log('[Auth] State before query:', authState);
console.log('[Query] Executing with user:', user?.id);
// Implement the fix
if (!authState.isReady) {
console.log('[Query] Waiting for auth...');
return;
}
Step 4: Test
Validate the fix:
cd spaces/[project]
# Run specific tests
npm test -- --grep "auth"
# Run full suite
npm test
# Manual verification if needed
npm run dev
NEVER claim "fixed" without tests passing.
Step 5: Document
Update WORKLOG with findings:
## YYYY-MM-DD - Troubleshooting Loop 1
**Hypothesis**: Query fires before auth state is set
**Debug findings**:
- isLoading was true when query executed
- Auth state not propagating to component
- Race condition between auth init and query
**Implementation**: Added auth state check before query
**Result**: β Fixed - 47/47 tests passing
**Gotcha**: Auth state needs explicit ready check, not just truthy
If Not Fixed
- Rollback changes:
git checkout -- . - Document what you learned
- Return to Step 1 with new information
Execution Modes
Mode 1: During TASK Implementation
/troubleshoot yourbench 001 "tests failing"
- Read: TASK.md, PLAN.md, WORKLOG.md for context
- Execute 5-step loop
- Document in issue's WORKLOG.md
- Continue with
/implementwhen fixed
Mode 2: Standalone Debugging
/troubleshoot yourbench "login broken on Safari"
- Investigate without issue context
- Document findings
- Suggest creating BUG issue if significant
Key Rules
- Research BEFORE guessing
- ONE hypothesis at a time
- Liberal debug logging -
console.log('[Component] State:', data) - NEVER claim "fixed" without tests passing
- Rollback on failure before next attempt
- Document everything for future reference
Workflow
/implement β (issue occurs) β /troubleshoot β /worklog β /implement
After fixing:
- Add WORKLOG entry with findings
- Continue implementation
- Or create BUG issue if recurring problem
# 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.