A multi-technique debugging protocol for AI agents designed to triage, investigate, and fix software defects with a mandatory cleanup guarantee.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install shadows-bug-hunter
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install shadows-bug-hunter using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Bug Hunter?
The Bug Hunter skill is a sophisticated debugging framework tailored for Openclaw Skills users who require a systematic approach to fixing broken code. Instead of relying on guesswork, this skill enforces a strict Triage phase to identify the root cause using git history and error analysis. It then deploys one of four specialized techniques—Log Injection, Screenshot Analysis, Manual Trace, or Test-Driven Fix—ensuring that every bug, from UI regressions to complex async logic errors, is resolved with technical precision.
Built for professional development environments, this skill emphasizes code integrity. It includes a non-negotiable Cleanup Guarantee, where the agent automatically scans for and removes any temporary debug artifacts like console logs or print statements before finalizing a task. By integrating directly with popular test runners like pytest, jest, and vitest, Bug Hunter provides a robust workflow for maintaining high-quality software repositories.
Bug Hunter Use Cases
- Resolving runtime exceptions, crashes, and stack traces.
- Identifying and fixing UI rendering issues or layout regressions.
- Debugging complex logic errors and algorithmic flaws.
- Preventing regressions by implementing test-driven bug fixes.
- Cleaning up accidental debug logs and print statements from the codebase.
How Bug Hunter Works
- Triage: The agent performs a mandatory 60-second analysis of the error message and recent git logs to establish context.
- Technique Selection: Based on the triage, the agent selects the optimal strategy (e.g., Log Injection for backend flow or Screenshot Analysis for UI).
- Investigation & Hypothesis: The agent investigates the source code, injecting logs or manually tracing logic to form a fix hypothesis.
- Execution & Fix: The proposed fix is applied to the codebase, often accompanied by a failing test to confirm the bug is reproducible.
- Verification & Cleanup: The agent runs the full test suite to ensure no new regressions were introduced and removes all temporary debug artifacts.
Bug Hunter Setup
To get started with Bug Hunter on Openclaw Skills, ensure you have the necessary binaries installed for your project type.
# Ensure git is available for triage
git --version
# For Python projects (Optional)
python -m pytest --version
# For JavaScript/TypeScript projects (Optional)
npx jest --version
# or
npx vitest --version
Bug Hunter Data Schema & Taxonomy
The Bug Hunter skill utilizes project metadata and version control history to organize its debugging workflow.
| Component | Description |
|---|---|
| Git Logs | Uses git log --oneline -10 to track recent changes and regression points. |
| Debug Markers | Temporary strings like [LOG] or debugger used during investigation. |
| Test Suites | Detects pytest.ini, jest.config.*, or vitest.config.* for execution. |
| Output Report | Generates a structured markdown report covering Error, Severity, Root Cause, and Fix. |
Bug Hunter Advanced Features
- Cleanup Guarantee: Mandatory automated grep-based search to ensure no debug code is ever committed.
- Multi-Runner Integration: Native support for pytest, jest, and vitest for seamless Test-Driven Fixes.
- Git-Aware Triage: Automatically correlates bugs with recent commits to speed up root cause identification.
- Heuristic-Based Technique Selection: Automatically chooses the best debugging strategy based on the error classification.
- Edge Case Verification: Encourages logic fixes that explicitly address null, undefined, or empty data states.
SKILL.md
Loading
Related Openclaw Skills
Zhihu Assistant
An automated workflow tool designed to monitor Zhihu trending topics, generate AI-powered responses, and manage review queues via Feishu.
VibeTrader
VibeTrader is an AI-driven trading platform that enables users to build, backtest, and deploy automated trading bots for stocks and crypto using natural language.
LAN Media Server
A lightweight Node.js server that enables AI agents to share media files over a local network when standard communication channels lack inline support.
Neutron Memory
A persistent memory layer for AI agents that enables semantic search and long-term context retention across multiple sessions.
Context Optimizer
Context Optimizer is a token economy protocol designed to reduce redundancy and prioritize critical context for AI agents.
Deep Research Protocol
A rigorous 4-round reasoning protocol designed to guide AI agents through exhaustive landscape mapping, risk assessment, and strategic synthesis.
METADATA
Featured*
