deepseek-skills: Skill for Claude Code

.agents/.skills/skills/deepseek-review/SKILL.md

deepseek-review is a skill for Claude Code, Codex from gonzi-stack/deepseek-skills. It costs 96 tokens per session (2,584 once invoked), scanned A, original, MIT.

A code-review guide for checking changes systematically before delivery or when reviewing someone else’s code. It asks the reviewer to understand the context, read the complete change, and identify specific problems.

In plain words
What is it for?
Use it to review pull requests, audit existing modules, assess changes, and decide whether code is ready to approve.
Why use it?
It helps catch incorrect assumptions and concrete defects that the code’s author may overlook, while making review comments explain the risk and direction of a fix.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is gonzi-stack/deepseek-skills's own configuration. It tells Claude Code and Codex how to work on deepseek-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything deepseek-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gonzi-stack/deepseek-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gonzi-stack/deepseek-skills/main/.agents/.skills/skills/deepseek-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gonzi-stack/deepseek-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deepseek-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-review/github.svg)](https://agentmods.dev/skills/gonzi-stack/deepseek-skills/deepseek-review)
Your own site
<a href="https://agentmods.dev/skills/gonzi-stack/deepseek-skills/deepseek-review"><img src="https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deepseek-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/gonzi-stack/deepseek-skills/deepseek-review"><img src="https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,584 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.02584
Opus 5 $0.00048 $0.01292
Sonnet 5 $0.00019 $0.00517
Haiku 4.5 $0.00010 $0.00258

Measured 8d ago against content hash 05a7a8e7484c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deepseek-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/.skills/skills/deepseek-review/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepSeek Code Review Skill — Universal

El autor del código es el peor revisor del código. Tu trabajo como revisor es encontrar lo que el autor asumió como correcto sin verificarlo.


Principio fundamental

Una revisión no es una opinión. Es un diagnóstico. Cada observación debe identificar un problema concreto, explicar por qué es un problema, y proponer una dirección de solución.

❌ WRONG: "Este código podría mejorarse."
✅ CORRECT: "La función getUser no tiene guard para el caso null (línea 34).
             Si el ID no existe en la DB, rows[0] es undefined y la línea 35
             lanza TypeError en runtime. Agregar: if (!rows[0]) return null;"

FASE 1 — Orientación antes de revisar

1.1 Entender qué se está revisando

Antes de leer una sola línea de código:

CONTEXTO DE REVISIÓN
====================
¿Qué hace este código? [descripción en una oración]
¿Qué problema resuelve? [contexto de negocio]
¿Qué cambió respecto a antes? [si es un PR, qué se agregó/modificó]
¿Hay algo que el autor marcó como "a revisar especialmente"? [notas del PR]

Revisar sin contexto produce observaciones irrelevantes.

1.2 Leer el diff completo antes de comentar

❌ WRONG: Comentar línea por línea mientras se lee.
✅ CORRECT: Leer todo primero. Entender el flujo completo. Luego comentar.

Una observación que parece válida en la línea 10 puede estar resuelta en la línea 80. Leer todo antes de comentar evita noise.


FASE 2 — Revisión por capas

Revisar en este orden. Cada capa tiene problemas distintos.

2.1 Capa de Corrección — ¿El código hace lo que dice?

Preguntas:

  • ¿El comportamiento implementado coincide con el comportamiento requerido?
  • ¿Hay casos edge no contemplados?
  • ¿Hay condiciones de borde (vacío, null, cero, máximo) que no están manejadas?
// Problema de corrección — el código "funciona" pero está mal
function divide(a: number, b: number): number {
  return a / b;
  // ❌ b puede ser 0 — no está contemplado
  // El código hace lo que dice pero falla en un caso real
}

// ✅ CORRECT
function divide(a: number, b: number): number {
  if (b === 0) throw new Error("Division by zero");
  return a / b;
}

Read the full file on GitHub · 305 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 305 lines · 96 tokens per session scan A 05a7a8e7484c

Subscribe to this mod's changes

deepseek-review is a skill published in the GitHub repository gonzi-stack/deepseek-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 96 tokens to every session and 2,584 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.