Skill
btw
Helps you use the /btw (or /qq) side-conversation workflow. Use when you want to think in parallel, ask side questions without…
Agent Orchestration
Skill
/debug-helper
Debug assistant for error analysis, log interpretation, and performance profiling. Use when user
Install
$ npx -y skills add ifiokjr/monopi --skill debug-helper --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/debug-helper
Context preview
The summary Claude sees to decide when to auto-load this skill.
Debug assistant for error analysis, log interpretation, and performance profiling. Use when user
SKILL.md
debug-helper.SKILL.mdname: debug-helper description: Debug assistant for error analysis, log interpretation, and performance profiling. Use when user encounters errors, crashes, or performance issues.
Debug Helper
Systematic debugging workflow.
Error Analysis
1. **Read the error**: full stack trace and error message 2. **Locate**: find the source file and line
# Search for the error origin grep -rn "ErrorClass\|error_function" src/
3. **Context**: read surrounding code (±30 lines) 4. **Reproduce**: identify minimal reproduction steps 5. **Root cause**: trace the data flow to find where it goes wrong 6. **Fix**: minimal change that addresses the root cause 7. **Verify**: run the failing case to confirm the fix
Log Analysis
1. Read the log file or output 2. Identify patterns: timestamps, error levels, request IDs 3. Correlate events across log lines 4. Summarize: what happened, when, and why
Performance Profiling
1. **Measure**: get baseline numbers first
time <command>
2. **Profile**: use language-appropriate tools:
- Node.js: `--prof`, `clinic.js`
- Python: `cProfile`, `py-spy`
- Go: `pprof`
3. **Identify**: find the hotspot (usually 1-2 functions) 4. **Optimize**: fix the bottleneck 5. **Verify**: measure again, compare with baseline
Ships withmonopi
One command to install and configure pi-coding-agent. Like oh-my-zsh for pi.
Get the whole plugin
Stats
160
Stars
21
Forks
Active
Maintenance
TypeScript
Language
MIT
License
1d ago
Last commit
7mo ago
Created
2h ago
Added