Axiom Lldb
Axiom Lldb analyzes code execution data from LLDB to identify and diagnose issues within your AI models for faster debugging & optimization.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add axiom-lldb npx -- -y @trustedskills/axiom-lldb
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"axiom-lldb": {
"command": "npx",
"args": [
"-y",
"@trustedskills/axiom-lldb"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill enables AI agents to interactively debug applications using LLDB (Low Level Debugger). It allows for pausing application execution to inspect variables, evaluate expressions, navigate threads, and understand the root cause of issues. The skill addresses situations where a user lacks familiarity with specific LLDB commands, particularly when dealing with Swift types, framing this as a knowledge gap rather than a tool deficiency.
When to use it
This skill is helpful in scenarios such as:
- Inspecting variable values during runtime.
- Reproducing and debugging local crashes.
- Diagnosing incorrect runtime values despite seemingly correct code.
- Understanding thread state when an application hangs.
- Troubleshooting issues where
po(print object) commands return unexpected results. - Recreating crashes from crash logs to set breakpoints.
Key capabilities
- Interactive debugging with LLDB.
- Breakpoint setting and inspection of variables.
- Expression evaluation for testing fixes without rebuilding.
- Exception breakpoint configuration.
- Thread backtrace analysis during hangs.
- Provides structured output including diagnosis, commands, expected outputs, likely root causes, and next steps.
Example prompts
- "I'm seeing an unexpected value for
myVariable. Can you help me debug it using LLDB?" - "My app is crashing. I have the crash log; can you set breakpoints to reproduce it with LLDB?"
- "The application hangs sometimes. How can I use LLDB to investigate the thread state?"
Tips & gotchas
- LLDB is most effective when you need to understand what's happening at a specific moment in time, as opposed to identifying trends over longer periods (for which Instruments would be more suitable).
- The skill aims to bridge knowledge gaps regarding LLDB commands, particularly for Swift types.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.