skills.rest
sanand0
sanand0COMMUNITY
Explore all skills by this author →
WebsiteGitHub

llm

Automate LLM transcription, image description, and speech or image generation via CLI.

11|Updated Apr 4, 2025
Search Tags:#cli#image generation#ai#llm#transcription#generative ai#speech generation
One-click install
npx skills add https://github.com/sanand0/scripts --skill llm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm
Source: https://github.com/sanand0/scripts/tree/main/agents/llm
Command: npx skills add https://github.com/sanand0/scripts --skill llm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill centralizes and simplifies interaction with various Large Language Models (LLMs) and their advanced capabilities (transcription, vision, image/speech generation) through a unified command-line interface, eliminating the need to learn multiple APIs and SDKs.

Core Features & Use Cases

  • Multi-Model Access: Interact with different LLM providers (e.g., GPT, Gemini) and specific models using a single CLI command.
  • Advanced Capabilities: Perform audio transcription, image description, speech generation, and image generation directly from the command line.
  • Structured Output: Utilize JSON schema (--schema) for precise, structured LLM responses, ideal for programmatic consumption.
  • Use Case: Transcribe an audio file, then ask an LLM to summarize the transcription, and finally generate a related image, all with simple CLI commands, automating complex multi-modal AI workflows.

Quick Start

Transcribe the attached audio file 'meeting.opus' using the gemini-2.5-flash model.

Frequently Asked Questions about llm

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

FAQPage Schema
How do I transcribe audio files using a CLI LLM?▼

Audio transcription via CLI LLM uses the `llm` command with `--attachment` to pass audio files to supported models like gemini-2.5-flash, which output text transcriptions directly to stdout for piping into further processing steps.

Can I generate images and speech from the command line with LLM models?▼

Yes, the `llm` CLI supports image and speech generation through compatible models and options; pipe text prompts as arguments or stdin to produce image or audio output files, automating multi-modal workflows without switching tools.

How do I structure LLM responses as JSON for programmatic use?▼

Use the `--schema` option with `llm` CLI to enforce structured JSON output from LLM calls, enabling reliable parsing and consumption in data pipelines without post-processing validation.

What LLM models and providers does the CLI support?▼

The `llm` CLI works with multiple LLM providers and models via the `--model` option; supported models include GPT and Gemini variants, with capabilities determined by the underlying provider's API offerings.

Can I chain LLM operations together—like transcribe, summarize, then generate an image?▼

Yes, pipe CLI outputs between `llm` commands using stdin and stdout to chain transcription, summarization, and image generation sequentially, automating complex multi-step AI workflows without manual intervention.

What prerequisites do I need to use the LLM CLI?▼

A compatible `llm` CLI tool, API access to supported LLM providers and models, and input delivery capability via command arguments or pipes; no additional SDKs or API learning required.

Related Skills

Explore More Software Engineering Skills→
chengyihuachengyihua

baoyu-image-gen

Generate AI images from text prompts via OpenAI, Google, or DashScope.

Community
Advanced
hoanghn61hoanghn61

report_exporter

Converts TechStackReport JSON into Markdown, HTML, and PDF exports.

Community
Intermediate
pradyumnasagarpradyumnasagar
6

agent-handoff

Automate inter-skill data transfer and provenance capture via JSON Material Passports.

Community
Advanced
rahulrajaramrahulrajaram

invokellm

Invoke AI CLI tools like claude, codex, and gemini with model and session options.

Community
Basic