debug
Scannednpx machina-cli add skill parcadei/Continuous-Claude-v3/debug --openclawDebug
You are tasked with helping debug issues during manual testing or implementation. This command allows you to investigate problems by examining logs, database state, and git history without editing files. Think of this as a way to bootstrap a debugging session without using the primary window's context.
Initial Response
When invoked WITH a plan/ticket file:
I'll help debug issues with [file name]. Let me understand the current state.
What specific problem are you encountering?
- What were you trying to test/implement?
- What went wrong?
- Any error messages?
I'll investigate the logs, database, and git state to help figure out what's happening.
When invoked WITHOUT parameters:
I'll help debug your current issue.
Please describe what's going wrong:
- What are you working on?
- What specific problem occurred?
- When did it last work?
I can investigate logs, database state, and recent changes to help identify the issue.
Environment Information
You have access to these key locations and tools:
Logs:
- Application logs (check project-specific locations)
- Common locations:
./logs/,~/.local/share/{app}/,/var/log/
Database (if applicable):
- SQLite databases can be queried with
sqlite3 - Check project config for database locations
Git State:
- Check current branch, recent commits, uncommitted changes
- Similar to how
commitanddescribe_prcommands work
Service Status:
- Check running processes:
ps aux | grep {service} - Check listening ports:
lsof -i :{port}
Process Steps
Step 1: Understand the Problem
After the user describes the issue:
-
Read any provided context (plan or ticket file):
- Understand what they're implementing/testing
- Note which phase or step they're on
- Identify expected vs actual behavior
-
Quick state check:
- Current git branch and recent commits
- Any uncommitted changes
- When the issue started occurring
Step 2: Investigate the Issue
Spawn parallel Task agents for efficient investigation:
Task 1 - Check Recent Logs:
Find and analyze the most recent logs for errors:
1. Find latest logs: ls -t ./logs/*.log | head -1 (or project-specific location)
2. Search for errors, warnings, or issues around the problem timeframe
3. Note the working directory if shown
4. Look for stack traces or repeated errors
Return: Key errors/warnings with timestamps
Task 2 - Database State (if applicable):
Check the current database state:
1. Locate database file (check project config)
2. Connect: sqlite3 {database_path}
3. Check schema: .tables and .schema for relevant tables
4. Query recent data based on the issue
5. Look for stuck states or anomalies
Return: Relevant database findings
Task 3 - Git and File State:
Understand what changed recently:
1. Check git status and current branch
2. Look at recent commits: git log --oneline -10
3. Check uncommitted changes: git diff
4. Verify expected files exist
5. Look for any file permission issues
Return: Git state and any file issues
Step 3: Present Findings
Based on the investigation, present a focused debug report:
## Debug Report
### What's Wrong
[Clear statement of the issue based on evidence]
### Evidence Found
**From Logs**:
- [Error/warning with timestamp]
- [Pattern or repeated issue]
**From Database** (if applicable):
```sql
-- Relevant query and result
[Finding from database]
From Git/Files:
- [Recent changes that might be related]
- [File state issues]
Root Cause
[Most likely explanation based on evidence]
Next Steps
-
Try This First:
[Specific command or action] -
If That Doesn't Work:
- Restart relevant services
- Check browser console for frontend errors
- Run with debug flags enabled
Can't Access?
Some issues might be outside my reach:
- Browser console errors (F12 in browser)
- MCP server internal state
- System-level issues
Would you like me to investigate something specific further?
## Important Notes
- **Focus on manual testing scenarios** - This is for debugging during implementation
- **Always require problem description** - Can't debug without knowing what's wrong
- **Read files completely** - No limit/offset when reading context
- **Think like `commit` or `describe_pr`** - Understand git state and changes
- **Guide back to user** - Some issues (browser console, MCP internals) are outside reach
- **No file editing** - Pure investigation only
## Quick Reference
**Find Latest Logs**:
```bash
ls -t ./logs/*.log | head -1
# Or check project-specific log locations
Database Queries (SQLite):
sqlite3 {database_path} ".tables"
sqlite3 {database_path} ".schema {table}"
sqlite3 {database_path} "SELECT * FROM {table} ORDER BY created_at DESC LIMIT 5;"
Service Check:
ps aux | grep {service_name}
lsof -i :{port}
Git State:
git status
git log --oneline -10
git diff
Remember: This command helps you investigate without burning the primary window's context. Perfect for when you hit an issue during manual testing and need to dig into logs, database, or git state.
Source
git clone https://github.com/parcadei/Continuous-Claude-v3/blob/main/.claude/skills/debug/SKILL.mdView on GitHub Overview
This skill helps you bootstrap debugging during manual testing or implementation by inspecting logs, database state, and git history without editing files. It guides you through understanding the problem, running targeted checks, and producing a focused Debug Report to identify root causes and actionable next steps.
How This Skill Works
It follows a structured process: understand the problem from the user input, then run parallel checks on logs, database, and git state as described in the SKILL steps. The results are compiled into a focused Debug Report with evidence, root cause, and recommended next steps.
When to Use It
- When tests fail or a feature misbehaves and you need a non-intrusive investigation
- When logs hint at errors but the root cause isn't obvious
- When the database state may be inconsistent or stale
- When recent code changes might have introduced a regression
- When you need a structured, shareable debugging report for stakeholders
Quick Start
- Step 1: Describe what's going wrong and provide any plan or ticket file if available
- Step 2: Invoke the debug tool to assess logs, DB, and git state as described
- Step 3: Review the Debug Report and follow the recommended next steps
Best Practices
- Start with a concise problem statement and reproduce steps
- Check the most recent logs for errors with timestamps
- Inspect the current git state (branch, commits, uncommitted changes)
- Verify database state and relevant tables from the latest data
- Deliver a focused Debug Report with clear root cause and next steps
Example Use Cases
- Bug in user login causes a 500 error; latest logs show a stack trace in the auth module; database lacks the user record; a recent git commit touched the authentication flow
- Checkout flow fails in staging; logs reveal a null pointer in the flow controller; database session data appears stale; a recent migration changed session schema
- Data export returns an empty file; logs show a file IO permission denied; the export table has no rows; a commit updated the export logic
- Email notifications not sent; logs show an SMTP timeout; queue table contains unsent entries; git history includes a mailer-related change
- Dashboard shows stale metrics after a cache refresh; logs indicate cache miss errors; caching layer code was recently modified