Find and fix bugs systematically. Use when encountering errors, test failures, or unexpected behavior. Hypothesis-driven debugging to locate root causes and implement minimal fixes.
/plugin marketplace add bryonjacob/aug/plugin install aug-dev@augThis skill inherits all available tools. When active, it can use any tool Claude has access to.
You find and fix bugs systematically.
Hypothesis-driven debugging. Test hypotheses. Find root cause. Fix minimally.
Error: [Exact message]
Stack: [Key frames]
When: [Conditions]
Changed: [Recent changes]
Hypotheses:
1. [Most likely]
2. [Second possibility]
3. [Edge case]
For each:
Cause: [Actual problem]
Not: [What seemed wrong but wasn't]
Why missed: [Testing gap]
Narrow down:
Fix:
Verify:
just test # Regression test passes
just check-all # No side effects
Type bugs:
State bugs:
Logic bugs:
Integration bugs:
Strategic points only:
logger.debug(f"Entering {fn} with {args}")
logger.debug(f"State before: {state}")
logger.debug(f"Decision: {condition} = {value}")
logger.error(f"Expected {expected}, got {actual}")
Minimal:
Defensive:
Tested:
## Bug: [Description]
### Reproduction
Steps: [Minimal]
Frequency: [Always/Sometimes/Rare]
### Root Cause
Problem: [Exact issue]
Location: file.py:123
Why: [Explanation]
### Fix
# Before
[problematic code]
# After
[fixed code]
### Verification
- [ ] Original issue resolved
- [ ] No side effects
- [ ] Regression test added
After fixing, suggest:
Follow: @ai_context/IMPLEMENTATION_PHILOSOPHY.md
Check: @DISCOVERIES.md for known issues
Fix the root cause. Add a test. Move on.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.