Skip to content

OffchainLabs/arbitrum-docs / .agents/skills/debug

Debug issues with research-first approach. Delegates to engineer. Triggers on "error", "tx failed", "bridge stuck", "retryable failed", "debug this".

FileKindSize
SKILL.mdskill md1.1 KB
---
name: debug
description: Debug issues with research-first approach. Delegates to engineer. Triggers on "error", "tx failed", "bridge stuck", "retryable failed", "debug this".
agent: engineer
---

# Debugging

Delegates to `engineer` for systematic debugging.

When working on Arbitrum projects, use `@arbitrum-best-practices` for domain-specific debugging patterns.

## Process

### 1. Documentation Research

- Search ArbitrumDocs MCP for error patterns
- Find troubleshooting solutions
- Query relevant API references

### 2. On-Chain Investigation

```bash
cast tx <hash> --rpc-url https://arb1.arbitrum.io/rpc
cast call <contract> "function()" --rpc-url <rpc>
cast logs --from-block <block> --address <contract>
```

### 3. Root Cause Classification

- **L1 issues**: Insufficient gas, failed L1 txs
- **L2 issues**: EVM compatibility, precompiles
- **Cross-chain**: Failed retryables, message delays
- **Config**: Wrong addresses, network mismatch

### 4. Solution

Production-ready fix with:

- Complete error handling
- Gas estimation with L1 data cost buffers
- Verification commands
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 321kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 321kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 321kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 197kUpdated Claude CodeCodexVerifiedInstall