fix-board
SkillMonitoring & opsLets your agent diagnose and fix PlatformIO board compile, upload, and monitor problems automatically.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the fix-board skill
About this capability
Automatically diagnose and fix PlatformIO board upload/monitor issues. Runs three-phase device workflow (Compile, Upload, Monitor) and applies fixes.
What this skill tells your AI
The instructions your AI receives, as published by fastled/fastled in .claude/skills/fix-board/SKILL.md and read by ahel’s review.
Automatically run the three-phase device workflow (Compile, Upload, Monitor), diagnose any failures, and apply fixes.
- Compile: Run compilation using
uv run ci/debug_attached.py(compile phase only) - Upload: Execute upload with automatic port conflict resolution
- Monitor: Attach to serial monitor, capture output for 10 seconds, detect failure keywords
- Diagnose: Identify upload failures, compilation errors, runtime crashes, ESP-IDF errors
- Fix: Automatically fix code, configuration, or suggest manual hardware fixes
- Verify: Re-test after applying fixes (up to 3 attempts)
Using debug_attached.py
uv run ci/debug_attached.py esp32dev --timeout 10 --fail-on PANIC --fail-on "guru meditation"
What Gets Fixed Automatically
- Upload failures: Port detection, permission issues, bootloader problems
- Compilation errors: Missing includes, type errors, dependency issues
- Configuration issues: Wrong board settings, incorrect platformio.ini parameters
- Runtime crashes: Watchdog resets, brownout detection, stack overflows
What Requires Manual Intervention
- Hardware issues: Physical wiring problems, power supply issues
- Driver issues: Missing USB drivers, permission setup
- Severe code issues: Major architecture problems requiring human decisions
Signals
- GitHub stars
- 7k
- Forks
- 2k
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
fix-board- Source
- github.com/fastled/fastled