Menu
Structured code quality assessment with severity ratings
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Generate and apply structured code changes to a file
Fix agents that read stale production data instead of classifying direct benchmark prompts — add format detection at top of instructions
Diagnose and fix sub-agent configuration issues in YAML + instruction files that cause timeouts, tool failures, or degraded performance
Fallback persistence paths when primary tools (store_memory, create_note, write_file) are unavailable — memory blocks, task resolution fields, CRM notes, and reporting, in priority order.
Compose and send an email — using native GWS tools (never gog CLI for replies)
Create, advance, and resolve CRM tasks correctly — respecting status transitions, handling retries, and avoiding common API pitfalls.
| name | code-review |
| description | Structured code quality assessment with severity ratings |
| tags | ["quality","review"] |
| tools_required | ["read_file","list_directory"] |
| parameters | [{"name":"target","type":"string","description":"File or directory to review","required":true},{"name":"focus","type":"string","description":"Review focus area (security, performance, readability, all)","default":"all"}] |
| output_format | json |
Perform a structured code quality review of a file or directory, producing actionable findings with severity ratings.
Discover files: If {target} is a directory, use list_directory to enumerate source files (skip binary, vendored, and generated files). If it is a single file, proceed directly.
Read and analyze: For each file, use read_file to load the contents. Analyze based on the focus area ({focus}):
Rate each finding: Assign a severity:
critical -- security vulnerability or data loss risk, must fix before mergehigh -- bug or significant performance issuemedium -- code smell or maintainability concernlow -- style nit or minor improvement suggestionProduce findings: For each issue, record the file path, line number(s) or function name, category, severity, a one-line summary, and a suggested fix.
Summarize: Return a JSON object:
{
"target": "{target}",
"focus": "{focus}",
"files_reviewed": <int>,
"findings": [
{
"file": "...",
"line": "...",
"category": "security|performance|readability",
"severity": "critical|high|medium|low",
"summary": "...",
"suggestion": "..."
}
],
"summary": "Brief overall assessment"
}