TabbitDeepSeek V4 Pro · Prompts and workflows
Browse executable prompts and workflows by task, content type, and runtime. Each card shows inputs, verification status, and the original source.
Runtimes vary by resource and may include an API, CLI, agent framework, or browser coding environment. Check each card for details.
Editor picks
V4-Pro enables thinking by default and uses high as the default effort level; use low for simple tasks, high for day-to-day Agents, and max for complex tasks, and pass the complete `reasoning_content` back on every round of a tool call.
DeepSeek-V4-Pro can be connected to the Codex CLI, the ChatGPT desktop app, and the VS Code extension through the native Responses API; a single configuration is shared across them, but you should back up and validate `config.toml`/`models.json` first.
All resources
V4-Pro enables thinking by default and uses high as the default effort level; use low for simple tasks, high for day-to-day Agents, and max for complex tasks, and pass the complete `reasoning_content` back on every round of a tool call.
DeepSeek-V4-Pro can be connected to the Codex CLI, the ChatGPT desktop app, and the VS Code extension through the native Responses API; a single configuration is shared across them, but you should back up and validate `config.toml`/`models.json` first.
With 8 environment variables, you can point Claude Code (and Claude Desktop Developer Mode) to DeepSeek, unlock a 1M context window with `deepseek-v4-pro[1m]`, use `deepseek-v4-flash` for subagents, set the main model's effort to `max`, and set the automatic compaction window to 786432.
DeepSeek’s official open-source Agent framework is built on the principle that `everything is a plugin` (models, tools, skills, sessions, sandboxes, file systems, loops, orchestration, and UI can all be replaced); a single `npx @deepseek-ai/dsh web` command launches the Web UI locally. It is currently in developer preview and will introduce compatibility-breaking changes.
A MIT-licensed, ready-to-use DeepSeek V4 concise system prompt (about 1.4 KB) that can be placed directly in a system message. It covers language responses, effort matching, hallucination prevention, and conventions for code and structure。.
The platform publishes the complete system prompt, user prompt, the model's actual generated output, and scores at two difficulty levels (Basic 98.0 / Advanced 92.6): a directly reusable Agent execution prompt that says “plan with `<plan>` first, call tools via JSON, review with `<observation>`, and wrap up with `<summary>`.”.
A community Agent skill that defines three executable rules for multi-step tasks in V4 thinking mode—verify before citing, dispatch a flash sub-agent for verification before executing across multiple files, and require `path:line` in plan output—each mapped to an observable failure class.
DeepSeek V4 Pro
After downloading, check the models and features available to your account. API and local-code steps still require their own runtime.