Skip to content
Back to skills

Deepseek

ASecurity

DeepSeek provides state-of-the-art open reasoning and conversational language models via an OpenAI-compatible REST API. Key models include `deepseek-chat` (DeepSeek-V3) and `deepseek-reasoner` (DeepSeek-R1).

  • 13 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 21, 2026
ai-agentstypescriptbashsqlapi

Works with

  • cli
  • api

Security analysis

A92/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned September 21, 2026

npx -y skills add ashish7802/awesome-api-skills --skill deepseek --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Deepseek?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Deepseek
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashish7802-deepseek/badge)](https://www.skillsdirectory.com/skills/ashish7802-deepseek)

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

Download with Pro
SKILL.md
# DeepSeek API Skill

## Overview
DeepSeek provides state-of-the-art open reasoning and conversational language models via an OpenAI-compatible REST API. Key models include `deepseek-chat` (DeepSeek-V3) and `deepseek-reasoner` (DeepSeek-R1).

## Installation
```bash
npm install openai
pip install openai
```

## Authentication & Client Setup
```typescript
import OpenAI from 'openai';

const deepseek = new OpenAI({
  apiKey: process.env.DEEPSEEK_API_KEY,
  baseURL: 'https://api.deepseek.com',
});
```

## Core API Operations

### 1. General Conversational Chat (DeepSeek-V3)
```typescript
const response = await deepseek.chat.completions.create({
  model: 'deepseek-chat',
  messages: [
    { role: 'system', content: 'You are an expert software architect.' },
    { role: 'user', content: 'Explain transaction isolation levels in PostgreSQL.' },
  ],
  temperature: 0.7,
  max_tokens: 2048,
});

console.log(response.choices[0].message.content);
```

### 2. Deep Reasoning Stream (DeepSeek-R1 with Chain-of-Thought)
```typescript
const stream = await deepseek.chat.completions.create({
  model: 'deepseek-reasoner',
  messages: [
    { role: 'user', content: 'Prove that the square root of 2 is irrational.' },
  ],
  stream: true,
});

for await (const chunk of stream) {
  // Reasoning chain tokens
  const reasoning = (chunk.choices[0]?.delta as any)?.reasoning_content;
  if (reasoning) {
    process.stdout.write(reasoning);
  }
  // Final output content tokens
  const content = chunk.choices[0]?.delta?.content;
  if (content) {
    process.stdout.write(content);
  }
}
```

### 3. Structured JSON Output
```typescript
const response = await deepseek.chat.completions.create({
  model: 'deepseek-chat',
  messages: [
    { role: 'system', content: 'Extract entities and output valid JSON.' },
    { role: 'user', content: 'John bought 3 apples from Whole Foods for $4.50' },
  ],
  response_format: { type: 'json_object' },
});
```

## AI Pitfalls & Anti-Hallucination Guidelines
- **Custom SDK Hallucination**: There is no official `@deepseek/sdk` npm package. Always use the official `openai` package with `baseURL: 'https://api.deepseek.com'`.
- **Reasoning Content Ingestion**: On `deepseek-reasoner`, reasoning thoughts arrive under `delta.reasoning_content`, not `delta.content`.
- **System Prompt Restrictions**: `deepseek-reasoner` discourages heavy system prompt steering that constrains reasoning chains.

## Production Verification Checklist
- [ ] `baseURL` is explicitly set to `https://api.deepseek.com`
- [ ] Fallback error handling for HTTP 429 and rate-limiting exponential backoff
- [ ] UI provides distinct tabs or accordions for reasoning thoughts vs final response

---
> **Last Verified:** 2026-07-03

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.