Agent skill

Deepseek Helper

by dongsheng123132 in dongsheng123132/u-claw

DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息. An agent skill from dongsheng123132/u-claw.

MITAuto-check passedAI & LLM Engineering

Install Deepseek Helper

skills CLI
$ npx skills add dongsheng123132/u-claw --skill deepseek-helper -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dongsheng123132/u-claw deepseek-helper --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dongsheng123132/u-claw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/portable/skills-cn/deepseek-helper .claude/skills/deepseek-helper && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deepseek-helper
GitHub stars
1.8k
Token cost
~367 tokens
SKILL.md length
116 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息. An agent skill from dongsheng123132/u-claw.

  • AI & LLM Engineering work in your project
  • SKILL.md covers 功能概述, 模型对比, 使用示例 and 适用场景, plus 2 more sections
  • Reaches api.deepseek.com

What it does

Deepseek Helper is an agent skill from dongsheng123132/u-claw. DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息

Its SKILL.md is about 370 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering. It works with DeepSeek. The repository describes itself as: U-Claw 虾盘 — OpenClaw AI 助手离线安装 U 盘:一键装好 Claude Code/Codex/OpenClaw,无需联网即插即用;新品 U-King AI 装机管家详见 u-king.org,另有远程支持与定制 AI 开发。 The licence is MIT.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “/deepseek-helper”

Requirements

  • Python 3
  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 9e769e6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.deepseek.com

    Also links to:

    • platform.deepseek.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deepseek Helper loads about 367 tokens when it runs. Until then it costs about 14 tokens; SKILL.md has 116 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~14
When it runs · the whole SKILL.md, loaded when a task matches
~367

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dongsheng123132/u-claw at commit 9e769e6, republished under its MIT licence (© dongsheng123132). 116 words, ~367 tokens.

Download SKILL.mdSave it as .claude/skills/deepseek-helper/SKILL.md (or your agent's skills folder).
name
deepseek-helper
description
DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息

DeepSeek API 助手

帮助用户高效使用 DeepSeek 系列模型,包括模型选择建议、API 调用示例、编程辅助和定价计算。

功能概述

  • 模型选择指南: deepseek-v4-flash vs deepseek-v4-pro 的使用场景对比
  • API 调用示例: 提供 Python、curl、Node.js 等语言的调用代码
  • 定价计算: 根据 token 用量估算费用(输入 ¥1/百万tokens,输出 ¥2/百万tokens)
  • Prompt 优化: 针对 DeepSeek 模型特性优化提示词
  • 错误排查: 常见 API 错误码解读和解决方案

模型对比

模型适用场景上下文长度
deepseek-v4-flash日常对话、文案写作、知识问答,快且便宜128K
deepseek-v4-pro复杂推理、数学、代码生成与审查128K

⚠️ 旧名 deepseek-chat / deepseek-coder / deepseek-reasoner 已下线, api.deepseek.com 现在只接受 deepseek-v4-flash 和 deepseek-v4-pro, 用旧名调用会直接返回 HTTP 400。

使用示例

基础 API 调用
帮我写一个调用 DeepSeek API 的 Python 脚本,实现多轮对话
模型选择
我要做一个客服机器人,应该用 deepseek-v4-flash 还是 deepseek-v4-pro?
费用估算
我每天大约处理 1000 条用户消息,平均每条 500 token,帮我算下月费用
错误排查
调用 DeepSeek API 返回 429 错误,怎么处理?

适用场景

  • 首次接入 DeepSeek API 的开发者
  • 需要在 deepseek-v4-flash 和 deepseek-v4-pro 之间做选择
  • 想要优化 API 调用成本
  • 排查 API 调用问题
  • 需要快速生成 API 调用代码片段

不适用场景

  • 需要调用 OpenAI / Claude 等其他模型的 API(请使用对应工具)
  • 需要实时获取 DeepSeek 最新公告(本技能基于已知信息)
  • 需要部署私有化 DeepSeek 模型(涉及运维,超出范围)

关键提示

  • DeepSeek API 兼容 OpenAI 格式,base_url 改为 https://api.deepseek.com
  • 国内访问无需翻墙,延迟低
  • 支持 function calling 和 JSON mode
  • 建议使用 stream 模式提升用户体验
  • API Key 申请地址: https://platform.deepseek.com

© dongsheng123132, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in portable/skills-cn/deepseek-helper of dongsheng123132/u-claw.

Open the folder on GitHubat commit 9e769e6

Compare with similar skills

Deepseek Helper next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deepseek Helper compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deepseek Helper this skilldongsheng123132/u-claw1.8k—~367Automated safety check: PassMIT
Dingo VerifyMigoXLab/dingo757—~833Automated safety check: PassApache-2.0
SimPO Preference TrainingOrchestra-Research/AI-Research-SKILLs13k4 repos~1.5kAutomated safety check: PassMIT
slime RL Post-TrainingOrchestra-Research/AI-Research-SKILLs13k4 repos~2.8kAutomated safety check: PassMIT
Oracle Agent Team OrchestratorBald0Wang/DeepSeek-Oracle187—~551Automated safety check: PassNone
Token Saverlokikill123/codex-token-skills119—~298Automated safety check: PassMIT

Similar skills

  • Dingo Verify

    MigoXLab/dingo

    A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

    757 GitHub stars~833 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • SimPO Preference Training

    Orchestra-Research/AI-Research-SKILLs

    Walks through aligning language models with SimPO, a reference-free preference optimization method, using accelerate configs for Mistral 7B, Llama 3 8B and math-focused models.

    13k GitHub starsUsed in 4 repos~1.5k tokens
    AI & LLM EngineeringAuto-check passed
  • slime RL Post-Training

    Orchestra-Research/AI-Research-SKILLs

    Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.

    13k GitHub starsUsed in 4 repos~2.8k tokens
    AI & LLM EngineeringAuto-check passed
  • Oracle Agent Team Orchestrator

    Bald0Wang/DeepSeek-Oracle

    Orchestrate DeepSeek Oracle multi-agent workflows by routing user intents to specialist oracle skills, enforcing safety gates, and composing one unified answer with follow-up questions and action…

    187 GitHub stars~551 tokensUpdated 7 mo ago
    AI & LLM EngineeringAuto-check passed
  • Token Saver

    lokikill123/codex-token-skills

    Minimize token consumption & maximize prompt cache hit rate.

    119 GitHub stars~298 tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed
  • Video Memory

    oxbshw/watch-skill

    The user asks about videos watched in the past or across sessions — "have we watched anything about X", "which video showed that error", "what did that meeting decide", "search my videos", or a…

    470 GitHub stars~569 tokensUpdated 26 days ago
    AI & LLM EngineeringAuto-check: notes

More from dongsheng123132/u-claw

All 17 skills in this repo
  • Image Compress

    dongsheng123132/u-claw

    图片压缩/转换 - 批量压缩、改尺寸、转格式(jpg/png/webp),本地处理不失隐私. An agent skill from dongsheng123132/u-claw.

    1.8k GitHub stars~274 tokensUpdated 4 days ago
    Auto-check passed
  • Web To Markdown

    dongsheng123132/u-claw

    网页转 Markdown - 抓取任意网页正文并转成干净的 Markdown,便于阅读/收藏/二次创作. An agent skill from dongsheng123132/u-claw.

    1.8k GitHub stars~347 tokensUpdated 4 days ago
    Auto-check passed
  • China Translate

    dongsheng123132/u-claw

    中英互译 + 本地化 - 技术翻译、UI本地化、文化适配、避免机翻腔

    1.8k GitHub stars~526 tokensUpdated 4 days ago
    Auto-check passed
  • Ppt Designer

    dongsheng123132/u-claw

    PPT 演示助手 - 幻灯片设计、内容结构、视觉优化、动画建议、演讲稿

    1.8k GitHub stars~415 tokensUpdated 4 days ago
    Auto-check passed
  • Bilibili Helper

    dongsheng123132/u-claw

    B站内容助手 - 视频标题描述优化、标签策略、封面设计建议、分区选择、评论互动

    1.8k GitHub stars~380 tokensUpdated 4 days ago
    Auto-check passed
  • China Search

    dongsheng123132/u-claw

    国内搜索引擎 - 百度、搜狗、Bing中国搜索,绕过GFW限制

    1.8k GitHub stars~385 tokensUpdated 4 days ago
    Auto-check passed

Works with

Questions about Deepseek Helper

What does Deepseek Helper do?

DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息. An agent skill from dongsheng123132/u-claw. Deepseek Helper is an agent skill from dongsheng123132/u-claw.

When should I use Deepseek Helper?

Deepseek Helper fits situations like: AI & LLM Engineering work in your project.

How do I install Deepseek Helper in Claude Code?

Run `npx skills add dongsheng123132/u-claw --skill deepseek-helper -a claude-code`. Or copy the skill folder (portable/skills-cn/deepseek-helper in dongsheng123132/u-claw) into .claude/skills/deepseek-helper in your project. Claude Code loads it when a task matches its description.

How do I install Deepseek Helper in Codex?

Run `npx skills add dongsheng123132/u-claw --skill deepseek-helper -a codex`. Or copy the skill folder (portable/skills-cn/deepseek-helper in dongsheng123132/u-claw) into .agents/skills/deepseek-helper in your project. Codex loads it when a task matches its description.

Can I use Deepseek Helper in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dongsheng123132/u-claw --skill deepseek-helper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deepseek-helper, .gemini/skills/deepseek-helper, .github/skills/deepseek-helper and .opencode/skills/deepseek-helper in your project.

What does Deepseek Helper need to run?

SKILL.md names no scripts, command-line tools or credentials: Deepseek Helper is instructions for the agent only. Our summary lists: Python 3; Node.js.

Does Deepseek Helper access the network?

SKILL.md names 2 domains. In commands or code: api.deepseek.com; the agent is likely to contact it when it follows the instructions. As links in the text: platform.deepseek.com. This is read from the text; nothing was executed.

Is Deepseek Helper safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deepseek Helper use?

Deepseek Helper is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deepseek Helper use?

About 367 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deepseek Helper?

Skills that share tags, products or a category with Deepseek Helper: Dingo Verify (MigoXLab/dingo, 757 stars), SimPO Preference Training (Orchestra-Research/AI-Research-SKILLs, 13k stars), slime RL Post-Training (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Oracle Agent Team Orchestrator (Bald0Wang/DeepSeek-Oracle, 187 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deepseek Helper?

dongsheng123132 (a GitHub user) maintains it in dongsheng123132/u-claw, which has 1,759 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 6, 2026.

Source: dongsheng123132/u-claw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.