← 返回 Skills 市场
jiajiaoy

Deepseek V4

作者 jiajiaoy · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
47
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install deepseek-v4
功能描述
Use DeepSeek V4 (Flash & Pro) from the command line — one-shot Q&A, thinking mode, multi-turn chat. OpenAI-compatible API, no special CLI needed. Supports de...
使用说明 (SKILL.md)

DeepSeek V4

Use DeepSeek V4 Flash and Pro directly from your terminal — one-shot questions, deep reasoning with thinking mode, and multi-turn chat. No special CLI required; uses the OpenAI-compatible API via a small Python script.

Setup

1. Get API key: https://platform.deepseek.com/api_keys

2. Set environment variable:

export DEEPSEEK_API_KEY=your_key_here
# Add to ~/.zshrc or ~/.bashrc to persist

Models

Model ID Best for Price (input/output)
V4 Flash ⚡ deepseek-v4-flash Q&A, writing, coding, summaries $0.014 / $0.028 per 1M
V4 Pro 🚀 deepseek-v4-pro Hard reasoning, math, deep analysis $0.174 / $0.348 per 1M

Both support 1M token context. Cache hits are 10× cheaper.

Legacy aliases (deepseek-chat → flash, deepseek-reasoner → pro) deprecated 2026-07-24.

Commands

One-shot question (Flash — fast & cheap)

uv run {baseDir}/scripts/ask.py "Explain the difference between V4 Flash and V4 Pro"

One-shot with Pro model

uv run {baseDir}/scripts/ask.py "Write a merge sort in Rust" --model pro

Thinking mode (Pro with visible reasoning trace)

uv run {baseDir}/scripts/ask.py "Prove that there are infinitely many primes" --think

Multi-turn chat

uv run {baseDir}/scripts/chat.py --model flash
uv run {baseDir}/scripts/chat.py --model pro --think

Show models & pricing

uv run {baseDir}/scripts/models.py

Model Selection Guide

Use Flash when:

  • Everyday Q&A and explanations
  • Writing, editing, translation
  • Code generation and review
  • Summarization and classification
  • Cost is a priority

Use Pro when:

  • Multi-step math or logic problems
  • Complex debugging or architecture decisions
  • Deep research and analysis
  • You want to see the reasoning process (--think)

Tips

  • Thinking mode (--think) streams the internal reasoning before the final answer — useful for hard problems and to verify correctness
  • System prompt: --system "You are a concise assistant" to set tone
  • No streaming: --no-stream for cleaner output in scripts
  • DeepSeek's API is OpenAI-compatible — any OpenAI SDK works with base_url="https://api.deepseek.com/v1"
安全使用建议
This skill appears to do exactly what it claims: a small Python wrapper that calls DeepSeek's OpenAI-compatible API. Before installing, confirm you trust the DeepSeek service and the 'uv' Homebrew package on your machine. Note the scripts require the Python 'openai' package (not installed by the brew step) and rely on DEEPSEEK_API_KEY — keep that key private. Also be aware 'thinking mode' streams internal reasoning (chain-of-thought), which can reveal intermediate deductions you may prefer not to log or share. If you need stronger assurance, verify the 'uv' formula source and inspect the installed Python package versions before use.
功能分析
Type: OpenClaw Skill Name: deepseek-v4 Version: 1.0.1 The skill provides a legitimate CLI interface for interacting with the DeepSeek V4 API. Analysis of the Python scripts (ask.py, chat.py, models.py) shows they function as described, using the official OpenAI-compatible endpoint (api.deepseek.com) and requiring only the necessary DEEPSEEK_API_KEY environment variable. No evidence of data exfiltration, unauthorized execution, or malicious prompt injection was found.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
Name/description request DEEPSEEK_API_KEY and the 'uv' runner and the Python scripts implement an OpenAI-compatible client against https://api.deepseek.com/v1 — this matches the claimed functionality (one-shot Q&A, thinking mode, multi-turn chat).
Instruction Scope
SKILL.md and scripts only instruct reading DEEPSEEK_API_KEY, invoking the DeepSeek API via the OpenAI-compatible client, and using 'uv run' for the scripts. There are no instructions to read unrelated files, other env vars, or send data to unexpected endpoints.
Install Mechanism
Install spec only installs the 'uv' binary via brew which is appropriate for running the provided commands. The Python scripts depend on the 'openai' package but the install spec doesn't list Python dependency installation — this is an operational omission rather than a security red flag.
Credentials
Only DEEPSEEK_API_KEY is required, which is proportional and expected for a client that calls the DeepSeek API. No unrelated credentials or broad filesystem/config paths are requested.
Persistence & Privilege
always:false and no modifications to other skills or system-wide settings. The skill does not request elevated or persistent platform privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install deepseek-v4
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /deepseek-v4 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
- Updated homepage URL in SKILL.md to point to the skill-specific page. - No changes to functionality or usage—documentation and metadata update only.
v1.0.0
Initial release of DeepSeek V4 command-line integration. - Supports DeepSeek V4 Flash and Pro models via OpenAI-compatible API. - Use one-shot Q&A, "thinking mode" for visible reasoning, and multi-turn chat directly from the terminal. - Provides pricing information and usage instructions for each model. - No special CLI required; leverages Python scripts for all operations. - Legacy aliases deprecated as of 2026-07-24.
元数据
Slug deepseek-v4
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Deepseek V4 是什么?

Use DeepSeek V4 (Flash & Pro) from the command line — one-shot Q&A, thinking mode, multi-turn chat. OpenAI-compatible API, no special CLI needed. Supports de... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 47 次。

如何安装 Deepseek V4?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install deepseek-v4」即可一键安装,无需额外配置。

Deepseek V4 是免费的吗?

是的,Deepseek V4 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Deepseek V4 支持哪些平台?

Deepseek V4 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Deepseek V4?

由 jiajiaoy(@jiajiaoy)开发并维护,当前版本 v1.0.1。

💬 留言讨论