with one click
deepseek-api
Help build/debug DeepSeek API usage (openai-compatible).
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Help build/debug DeepSeek API usage (openai-compatible).
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Run a command on a recurring interval (poll CI etc.).
Read/extract/combine/split PDFs.
Launch this project's app to see a change in action.
Schedule a one-off or cron task via DeepCode's daemon.
Help author a new skill — frontmatter + body + best-trigger description.
Modify settings.json / hooks / permissions safely + explain trade-offs.
| name | deepseek-api |
| description | Help build/debug DeepSeek API usage (openai-compatible). |
DeepSeek's HTTP API is OpenAI-Compatible. Use the same patterns; just swap the base URL and key.
https://api.deepseek.com/v1Authorization: Bearer <DEEPSEEK_API_KEY> (or set via env)openai npm with
baseURL: 'https://api.deepseek.com/v1'.| Model | Alias | Strengths |
|---|---|---|
deepseek-chat | → deepseek-v4-flash | Fast general chat; tool use |
deepseek-reasoner | → deepseek-v4-pro | Multi-step reasoning; emits reasoning_content |
Set via the standard model field.
Pass stream: true. SSE chunks come back as data: {...}\n\n. Each
chunk has choices[0].delta.content for text deltas, and
choices[0].delta.tool_calls[] for partial tool calls.
deepseek-reasoner ALSO emits choices[0].delta.reasoning_content —
the thinking trace. UI should render this in a collapsible panel.
Standard OpenAI shape:
const r = await client.chat.completions.create({
model: 'deepseek-chat',
messages: [...],
tools: [{
type: 'function',
function: {
name: 'Read',
description: '...',
parameters: { type: 'object', properties: {...}, required: [...] }
}
}],
tool_choice: 'auto',
});
Response includes choices[0].message.tool_calls[] when the model
chose to call a tool. Loop: send back role: 'tool' messages with the
tool_call_id, get next assistant message, repeat until no tool calls.
| Tier | Input | Output | Reasoning |
|---|---|---|---|
| deepseek-chat | 1¥/M | 2¥/M | — |
| deepseek-reasoner | 1¥/M | 16¥/M | 4¥/M |
temperature: 1.0 makes tool calls flaky — drop to 0.3 for tool use.reasoning_content is not in messages — it's separate; don't try
to echo it back as a content block to the model.