Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Deep Code Audit

ASecurity

Audits an entire repository, not a diff: bugs, dead code, TODOs, dummy returns, unfinished endpoints, swallowed errors, missing tests, security, performance. Use when asked to \"audit the whole repo\", \"find incomplete features\" or \"deep code audit\". One diff: code-review-and-quality.

3 stars
0 votes
0 copies
0 views
Added 10/2/2026
ai-agentstypescriptgosqlvuecode-reviewapisecurityperformance

Works with

api

Security Analysis

A100/100

Scanned 10/2/2026

$npx -y skills add Gastonchevarria/god-mode --skill deep-code-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Deep Code Audit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Deep Code Audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gastonchevarria-deep-code-audit/badge)](https://www.skillsdirectory.com/skills/gastonchevarria-deep-code-audit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: deep-code-audit
description: "Audits an entire repository, not a diff: bugs, dead code, TODOs, dummy returns, unfinished endpoints, swallowed errors, missing tests, security, performance. Use when asked to \"audit the whole repo\", \"find incomplete features\" or \"deep code audit\". One diff: code-review-and-quality."
---

# Deep Code Audit Skill

Use this skill when the user asks to "audit the entire repository", "find incomplete features", or "run deep code review".

## 12-Point Audit Methodology

When invoked, act as an expert Hybrid LLM Code Reviewer. You must audit the entire repository (not just recently modified files).

Search for and classify:
1. **Bugs funcionales y errores de lógica**: Flujos que obviamente van a fallar en runtime.
2. **Funciones declaradas pero nunca utilizadas**: Código muerto o huérfano.
3. **TODO, FIXME, HACK y placeholders**: Comentarios que indican deuda técnica.
4. **Rutas, botones o endpoints que no tienen implementación completa**: UI que no hace nada o APIs que devuelven errores 501.
5. **Funciones que retornan valores ficticios**: Funciones mockeadas (`return null`, `return []`, `return {}`, `return true/false`).
6. **Manejo de errores ausente o incompleto**: Promesas sin `catch`, `try/catch` vacíos, o errores tragados silenciosamente.
7. **Flujos que comienzan pero no terminan**: Webhooks sin procesamiento final, procesos en background que mueren.
8. **Integraciones con APIs o bases de datos parcialmente implementadas**: Llamadas de red simuladas.
9. **Variables, componentes y servicios desconectados**: Exports sin import.
10. **Tests faltantes para funcionalidades importantes**: Core business logic sin cobertura.
11. **Problemas de seguridad**: Hardcoded secrets, inyecciones (SQL/NoSQL), XSS, falta de sanitización.
12. **Problemas de rendimiento y fugas de recursos**: N+1 queries, memory leaks, bucles ineficientes, renders innecesarios.

## Format of the Audit Report

For each finding, you MUST provide:
- **Severidad**: Crítica, alta, media o baja.
- **Archivo y número de línea**: Ubicación exacta.
- **Evidencia concreta**: El bloque de código problemático.
- **Por qué es un problema**: Impacto real en la aplicación.
- **Cómo reproducirlo**: Pasos o condiciones para que falle.
- **Solución recomendada**: Código corregido o estrategia de refactor.
- **Requiere un nuevo test**: Sí/No, y por qué.

## Execution Steps for the Agent

1. **Static Analysis**: Run `npm run lint` and `npm run build` (if applicable) to catch dead code and typescript errors.
2. **Grep Scanning**: Use `grep_search` to actively hunt for "TODO", "FIXME", "HACK", "console.log", "return null", "return []", "return true".
3. **Architecture Mapping**: Use `list_dir` to map `src/app`, `src/api`, `src/components`, `src/lib` to find incomplete routes.
4. **Report Generation**: Compile all findings into a comprehensive `audit_report.md` artifact.

Attribution

GastonchevarriaGastonchevarria
View sourceSee grades on GitHubMore from Gastonchevarria →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →