deepseek-testing

deepseek-testing is a skill for Claude Code, Codex from gonzi-stack/deepseek-skills. It costs 113 tokens per session (3,121 once invoked), scanned A, original, MIT.

A Spanish-language guide for writing unit, integration, and end-to-end tests that check observable behavior rather than internal implementation details.

In plain words
What is it for?
Use it to decide what to test, structure meaningful test cases, cover boundary conditions and failures, and assess whether existing tests provide real confidence.
Why use it?
It helps avoid tests that pass without detecting real bugs or break during harmless refactoring. It focuses attention on important rules, edge cases, and error handling.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/gonzi-stack/deepseek-skills/deepseek-testing
Any agent
npx skills add gonzi-stack/deepseek-skills --skill deepseek-testing
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-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-testing.svg)](https://agentmods.dev/skills/gonzi-stack/deepseek-skills/deepseek-testing)
Your own site
<a href="https://agentmods.dev/skills/gonzi-stack/deepseek-skills/deepseek-testing"><img src="https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,121 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00113 $0.03121
Opus 5 $0.00056 $0.01561
Sonnet 5 $0.00023 $0.00624
Haiku 4.5 $0.00011 $0.00312

Measured 3d ago against content hash 2cf7e03dfe88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepseek-testing 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 3d 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-testing/SKILL.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepSeek Testing Skill — Universal

Un test que no puede fallar no da confianza. Da falsa seguridad. El objetivo de un test no es que pase — es que falle cuando el código está mal.


Principio fundamental

Testeá comportamiento, no implementación. Si un test se rompe cuando refactorizás el código sin cambiar su comportamiento, ese test está testeando los detalles internos — no la funcionalidad real.

// ❌ WRONG — testea implementación
it("calls getUserById once", async () => {
  const spy = vi.spyOn(userRepo, "getUserById");
  await userService.getProfile("123");
  expect(spy).toHaveBeenCalledOnce(); // ¿Y si lo optimizamos para llamarlo 0 veces con cache?
});

// ✅ CORRECT — testea comportamiento
it("returns the user profile for a valid id", async () => {
  const profile = await userService.getProfile("123");
  expect(profile.id).toBe("123");
  expect(profile.name).toBeDefined();
});

FASE 1 — Decidir qué testear

1.1 Lo que vale la pena testear

Alta prioridad — testear siempre:
✅ Lógica de negocio compleja (cálculos, reglas, transformaciones)
✅ Casos edge que pueden romper la aplicación en producción
✅ Manejo de errores — ¿el código falla correctamente?
✅ Contratos públicos de módulos — lo que otros módulos dependen
✅ Flujos críticos de negocio (registro, pago, autenticación)
✅ Funciones puras con múltiples combinaciones de input/output

1.2 Lo que no vale la pena testear

Baja prioridad — generalmente no testear:
❌ Getters y setters triviales sin lógica
❌ Código que solo llama a una librería externa sin transformación
❌ Detalles de implementación que pueden cambiar
❌ UI cosmética (qué color tiene un botón)
❌ Código generado automáticamente
❌ Configuración estática

Regla de oro: Si el test no puede fallar con ningún cambio realista al código, no añade valor. Borralo.

1.3 La pregunta correcta antes de escribir un test

Antes de escribir cada test, responder:
1. ¿Qué comportamiento específico estoy verificando?
2. ¿Cómo podría este comportamiento romperse en el futuro?
3. ¿El test fallaría si introduzco ese bug?

Si no podés responder las tres, replanteá el test.

Read the full file on GitHub · 408 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. 3d ago First seen · 408 lines · 113 tokens per session scan A 2cf7e03dfe88

Subscribe to this mod's changes

deepseek-testing is a skill published in the GitHub repository gonzi-stack/deepseek-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 113 tokens to every session and 3,121 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens