/lookagain-output-format
Defines the standard output format for code review findings. Use when performing code reviews to ensure consistent, parseable output.
shell
$ npx -y skills add HartBrook/lookagain --skill lookagain-output-format --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/lookagain-output-format
Context preview
The summary Claude sees to decide when to auto-load this skill.
Defines the standard output format for code review findings. Use when performing code reviews to ensure consistent, parseable output.
SKILL.md
lookagain-output-format.SKILL.mdname: lookagain-output-format description: Defines the standard output format for code review findings. Use when performing code reviews to ensure consistent, parseable output.
Code Review Output Format
When performing code reviews, output findings in this exact JSON structure:
{
"pass_summary": "string - Brief summary of review scope and key findings",
"issues": [
{
"severity": "must_fix | should_fix | suggestion",
"title": "string - Brief title (max 100 chars)",
"description": "string - Detailed explanation of the issue",
"file": "string - Relative file path",
"line": "number | null - Line number if applicable",
"suggested_fix": "string - How to fix it"
}
]
}Severity Definitions
**must_fix**:
- Security vulnerabilities
- Bugs causing runtime errors
- Data loss/corruption risks
- Breaking API changes
**should_fix**:
- Performance issues
- Poor error handling
- Missing edge cases
- Maintainability concerns
**suggestion**:
- Minor refactoring
- Documentation gaps
- Style improvements
Rules
- Output ONLY valid JSON (no markdown wrapper)
- Include all fields for each issue
- Use `null` for optional fields (like `line`) when not applicable
- Keep titles concise and descriptive
- Make suggested_fix actionable
Ships withlookagain
Sequential code review with fresh agent contexts. Each pass runs in an independent subagent, ensuring unbiased analysis that catches issues other passes might miss.
Get the whole plugin, auto-invoked

