One-click install
npx skills add https://github.com/spyqs/nanoclaw-email-imap --skill debug-spyqs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: debug
Source: https://github.com/spyqs/nanoclaw-email-imap/tree/main/.claude/skills/debug
Command: npx skills add https://github.com/spyqs/nanoclaw-email-imap --skill debug-spyqs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The debug skill helps you diagnose why NanoClaw containerized agent runs fail or behave incorrectly, especially when authentication, mounts, environment variables, permissions, or session resumption break.

Core Features & Use Cases

  • Container architecture walkthrough: Explains the host-to-container layout, including how environment files, group mounts, IPC, and per-group Claude session directories map into the container filesystem.
  • Actionable log and filesystem triage: Points you to the exact host and per-group log files to inspect container stderr/stdout, mounts, and session behavior.
  • Common failure fixes: Covers typical breakages such as missing API credentials, root-user/permission mismatches, env vars not reaching the container, incorrect session mount paths, and MCP server startup failures.
  • Session persistence validation: Shows how to confirm that Claude session IDs stay consistent for a group and how to clear sessions safely when needed.

Quick Start

Run the debug skill and ask it to diagnose your failure by telling it which group folder you are using and pasting the relevant container log file contents from groups/{folder}/logs/container-*.log.

Frequently Asked Questions about debug

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fix Claude Code exit code 1 errors in a containerized agent?

To fix Claude Code exit code 1 errors in a containerized agent, verify the container runs as the non-root node user, confirm session mounts map to /home/node/.claude, and check that API credentials are properly propagated to the environment.

Why does my MCP server initialization fail inside a Docker sandbox?

MCP server initialization fails inside Docker sandboxes when environment variables do not reach the container or filesystem mappings are incorrect. Triage the container stderr logs and verify group mounts and IPC configurations map correctly into the container.

How do I validate Claude session persistence across container restarts?

Validate Claude session persistence by confirming the session ID stays consistent for a group and checking that per-group session directories mount correctly to /home/node/.claude. Clear sessions safely by removing the mounted session files when needed.

What is the best way to troubleshoot incorrect filesystem mappings between host and container?

Troubleshoot incorrect filesystem mappings by inspecting the host-to-container layout, verifying group mounts and environment files, and checking the exact host and per-group log files located at groups/{folder}/logs/container-*.log for mount errors.

Why are my API credentials missing inside the Docker sandbox container?

API credentials go missing inside Docker sandbox containers due to environment propagation failures or root-user permission mismatches. Verify the container runs as the non-root node user and that environment files are correctly mounted and accessible.