claude-code-debug

Solid

Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.

AI & Automation 422 stars 44 forks Updated today

Install

View on GitHub

Quality Score: 86/100

Stars 20%
87
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
0
Description 5%
100

Skill Content

# Claude Code Debug Troubleshoot extensions, hooks, and unexpected behavior. ## Quick Diagnostics ```bash # Enable debug mode claude --debug # Check loaded extensions /hooks # View registered hooks /agents # View available agents /memory # View loaded memory files /config # View current configuration ``` ## Common Issues | Symptom | Quick Check | |---------|-------------| | Skill not activating | Verify description has trigger keywords | | Hook not running | Check `chmod +x`, run `/hooks` | | Agent not delegating | Add "Use proactively" to description | | MCP connection fails | Test server manually with `npx` | | Permission denied | Check settings.json allow rules | ## Debug Mode Output ```bash claude --debug # Shows: # - Hook execution and errors # - Skill loading status # - Subagent invocations # - Tool permission decisions # - MCP server connections ``` ## Quick Fixes ### Skill Not Loading ```bash # Check structure ls -la .claude/skills/my-skill/ # Must have: SKILL.md # Verify YAML frontmatter head -10 .claude/skills/my-skill/SKILL.md # Must start/end with --- # Check name matches directory grep "^name:" .claude/skills/my-skill/SKILL.md ``` ### Hook Not Executing ```bash # Make executable chmod +x .claude/hooks/my-hook.sh # Test manually echo '{"tool_name":"Bash"}' | .claude/hooks/my-hook.sh echo $? # Check exit code # Verify JSON syntax jq '.' ~/.claude/settings.json ``` ### Agent Not Being Used ```bash # Check file location ls...

Details

Author
aiskillstore
Repository
aiskillstore/marketplace
Created
8 months ago
Last Updated
today
Language
Python
License
None

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

claude-code-extension-engineering

Building, debugging, or reasoning about the limits of a Claude Code extension: CLAUDE.md, rules, skills, hooks and hook events incl. Stop and Notification, subagents, dynamic workflows, agent teams, MCP servers, output styles, themes, status lines, monitors, channels, plugins, the Agent SDK, permission rules, the OS sandbox, settings files and environment variables, auto memory, and what survives a session ending (transcripts, resume, /rewind). Use when choosing between these mechanisms, writing one, or diagnosing one that will not load, fire, or behave. ALSO capability and scope: whether an event can block or refuse, whether a key is honored at project scope or only user/managed/CLI scope, which tools a path rule is consulted for, what a subagent receives, whether it exists on an older build. ALSO for IMPERATIVE build requests, not only questions: "wire up a hook that...", "make it stop when X", "put our sandbox config in settings.json". They presuppose it can, and often it cannot. ALSO for a BARE SYMPTOM or

0 Updated today
TranDenyDFW
AI & Automation Listed

claude-codehook

Configure, create, or troubleshoot Claude Code hooks (PreToolUse, PostToolUse, UserPromptSubmit), debug hook failures, or set up any automation within Claude Code. Examples include "I want to run tests before every file edit", "My hook isn't firing", "1 out of 2 hooks ran", or "How do I create a hook that formats JSON output with jq?"

16 Updated today
bendrucker
AI & Automation Listed

claude-code-guide

Use when configuring Claude Code hooks, plugins, skills, settings, or managed configuration. Triggers on SessionStart, UserPromptSubmit, PreToolUse, PermissionRequest, PostToolUse, compaction, command/prompt/agent/HTTP/MCP-tool handlers, parallel hook behavior, allowManagedHooksOnly, or onboarding and testing Claude Code automation, even when the user doesn't say 'harness adapter'.

5 Updated 4 days ago
xonovex