llm-processor

Process text tasks locally with self-hosted DeepSeek-R1 via HTTP.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/dayuer/survival --skill llm-processor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-processor
Source: https://github.com/dayuer/survival/tree/main/nanobot/workspace/skills/llm-processor
Command: npx skills add https://github.com/dayuer/survival --skill llm-processor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, and includes scripts (resource) components.

What problem does it solve?

This Skill processes text tasks using self-hosted DeepSeek-R1 to translate, summarize, rewrite, and analyze content without consuming external API quotas.

Core Features & Use Cases

  • Self-hosted translation: Translate text and files locally without API calls.
  • Text summarization: Generate bullet, paragraph, or one-line summaries.
  • Custom prompt processing: Apply user-defined prompts to any text.

Quick Start

Translate a long English article by invoking the translate command on its file and save the Chinese output.

Frequently Asked Questions about llm-processor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I translate text using a local LLM without consuming external API quotas?

You can translate text using a self-hosted DeepSeek-R1 instance to process inputs over a local HTTP API. This approach returns deterministic translated results without consuming external API quotas.

Can I summarize articles into different formats offline?

Yes, you can summarize content offline into bullet, paragraph, or one-line summary formats. The local processing applies explicit prompts and style controls to generate the desired summary output.

Do I need a self-hosted DeepSeek-R1 instance to run custom text processing prompts?

Yes, you need a self-hosted DeepSeek-R1 environment running locally to apply custom prompts to your text. The Skill uses this local API over HTTP to accept text or file inputs and return processed results.

What is the best way to process files for text translation and summarization without external APIs?

The best way is using a local LLM processor that accepts file inputs over HTTP to translate or summarize content. This offline approach ensures deterministic results with explicit prompts and style controls.

Does this text processing tool work with the httpx library for local API requests?

Yes, the tool uses the httpx library to handle local API requests over HTTP. This allows it to accept text or file inputs and return deterministic translation, summarization, or rewriting results.