llm-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

LLM CLI Skill

LLM CLI 技能

Purpose

用途

This skill enables seamless interaction with multiple LLM providers (OpenAI, Anthropic, Google Gemini, Ollama) through the

llm

CLI tool. It processes textual and multimedia information with support for both one-off executions and interactive conversation modes.

该技能通过

llm

CLI工具实现与多家LLM服务商（OpenAI、Anthropic、Google Gemini、Ollama）的无缝交互。它支持处理文本和多媒体信息，同时支持一次性执行和交互式对话两种模式。

When to Use This Skill

适用场景

Trigger this skill when:

User wants to process text/files with an LLM
User needs to choose between multiple available LLMs
User wants interactive conversation with an LLM
User needs to pipe content through an LLM for processing
User wants to use specific model aliases (e.g., "claude-opus", "gpt-4o")

Example user requests:

"Process this file with Claude"
"Analyze this text with the fastest available model"
"Start an interactive chat with OpenAI"
"Use Gemini to summarize this document"
"Chat mode with my local Ollama instance"

在以下场景触发该技能：

用户希望使用LLM处理文本/文件
用户需要在多个可用LLM中进行选择
用户希望与LLM进行交互式对话
用户需要通过管道传递内容给LLM进行处理
用户希望使用特定的模型别名（如"claude-opus"、"gpt-4o"）

示例用户请求：

"使用Claude处理这个文件"
"用最快的可用模型分析这段文本"
"启动与OpenAI的交互式聊天"
"使用Gemini总结这份文档"
"与本地Ollama实例进行聊天模式"

Supported Providers & Models

支持的服务商与模型

OpenAI

Latest Models (2025):
- ```
gpt-5
```
  - Most advanced model
- ```
gpt-4-1
```
  /
```
gpt-4.1
```
  - Latest high-performance
- ```
gpt-4-1-mini
```
  /
```
gpt-4.1-mini
```
  - Smaller, faster version
- ```
gpt-4o
```
  - Multimodal omni model
- ```
gpt-4o-mini
```
  - Lightweight multimodal
- ```
o3
```
  - Advanced reasoning
- ```
o3-mini
```
  /
```
o3-mini-high
```
  - Reasoning variants

Aliases:

openai

gpt

2025年最新模型：
- ```
gpt-5
```
  - 最先进的模型
- ```
gpt-4-1
```
  /
```
gpt-4.1
```
  - 最新高性能模型
- ```
gpt-4-1-mini
```
  /
```
gpt-4.1-mini
```
  - 更轻量、更快的版本
- ```
gpt-4o
```
  - 多模态全能模型
- ```
gpt-4o-mini
```
  - 轻量级多模态模型
- ```
o3
```
  - 高级推理模型
- ```
o3-mini
```
  /
```
o3-mini-high
```
  - 推理变体模型

别名：

openai

gpt

Anthropic

Latest Models (2025):
- ```
claude-sonnet-4.5
```
  - Latest flagship model
- ```
claude-opus-4.1
```
  - Complex task specialist
- ```
claude-opus-4
```
  - Coding specialist
- ```
claude-sonnet-4
```
  - Balanced performance
- ```
claude-3.5-sonnet
```
  - Previous generation
- ```
claude-3.5-haiku
```
  - Fast & efficient

Aliases:

anthropic

claude

2025年最新模型：
- ```
claude-sonnet-4.5
```
  - 最新旗舰模型
- ```
claude-opus-4.1
```
  - 复杂任务专用模型
- ```
claude-opus-4
```
  - 编码专用模型
- ```
claude-sonnet-4
```
  - 性能均衡模型
- ```
claude-3.5-sonnet
```
  - 上一代模型
- ```
claude-3.5-haiku
```
  - 快速高效模型

别名：

anthropic

claude

Google Gemini

Latest Models (2025):
- ```
gemini-2.5-pro
```
  - Most advanced
- ```
gemini-2.5-flash
```
  - Default fast model
- ```
gemini-2.5-flash-lite
```
  - Speed optimized
- ```
gemini-2.0-flash
```
  - Previous generation
- ```
gemini-2.5-computer-use
```
  - UI interaction

Aliases:

google

gemini

2025年最新模型：
- ```
gemini-2.5-pro
```
  - 最先进模型
- ```
gemini-2.5-flash
```
  - 默认快速模型
- ```
gemini-2.5-flash-lite
```
  - 速度优化模型
- ```
gemini-2.0-flash
```
  - 上一代模型
- ```
gemini-2.5-computer-use
```
  - UI交互模型

别名：

google

gemini

Ollama (Local)

Ollama（本地）

Popular Models:
- ```
llama3.1
```
  - Meta's latest (8b, 70b, 405b)
- ```
llama3.2
```
  - Compact versions (1b, 3b)
- ```
mistral-large-2
```
  - Mistral flagship
- ```
deepseek-coder
```
  - Code specialist
- ```
starcode2
```
  - Code models

Aliases:

ollama

local

热门模型：
- ```
llama3.1
```
  - Meta最新模型（8b、70b、405b参数版本）
- ```
llama3.2
```
  - 紧凑版本（1b、3b参数版本）
- ```
mistral-large-2
```
  - Mistral旗舰模型
- ```
deepseek-coder
```
  - 编码专用模型
- ```
starcode2
```
  - 代码模型

别名：

ollama

local

Workflow Overview

工作流程概述

User Input (with optional model)
    ↓
Check Available Providers (env vars)
    ↓
Determine Model to Use:
  - If specified: Use provided model
  - If ambiguous: Show selection menu
  - Otherwise: Use last remembered choice
    ↓
Load/Create Config (~/.claude/llm-skill-config.json)
    ↓
Detect Input Type:
  - stdin/piped
  - file path
  - inline text
    ↓
Execute llm CLI:
  - Non-interactive: Process & return
  - Interactive: Keep conversation loop
    ↓
Save Model Choice to Config

User Input (with optional model)
    ↓
Check Available Providers (env vars)
    ↓
Determine Model to Use:
  - If specified: Use provided model
  - If ambiguous: Show selection menu
  - Otherwise: Use last remembered choice
    ↓
Load/Create Config (~/.claude/llm-skill-config.json)
    ↓
Detect Input Type:
  - stdin/piped
  - file path
  - inline text
    ↓
Execute llm CLI:
  - Non-interactive: Process & return
  - Interactive: Keep conversation loop
    ↓
Save Model Choice to Config

Features

功能特性

1. Provider Detection

1. 服务商检测

Checks environment variables for API keys
Suggests available LLM providers on first run

Detects:

OPENAI_API_KEY

ANTHROPIC_API_KEY

GOOGLE_API_KEY

OLLAMA_BASE_URL

检查环境变量中的API密钥
首次运行时推荐可用的LLM服务商

检测的变量：

OPENAI_API_KEY

ANTHROPIC_API_KEY

GOOGLE_API_KEY

OLLAMA_BASE_URL

2. Model Selection

2. 模型选择

Accept model aliases (
```
gpt-4o
```
,
```
claude-opus
```
,
```
gemini-2.5-pro
```
)
Accept provider aliases (
```
openai
```
,
```
anthropic
```
,
```
google
```
,
```
ollama
```
)
Interactive menu when selection is ambiguous
Remembers last used model in
```
~/.claude/llm-skill-config.json
```

支持模型别名（
```
gpt-4o
```
,
```
claude-opus
```
,
```
gemini-2.5-pro
```
）
支持服务商别名（
```
openai
```
,
```
anthropic
```
,
```
google
```
,
```
ollama
```
）
当选择不明确时显示交互式菜单
在
```
~/.claude/llm-skill-config.json
```
中记住上次使用的模型

3. Input Processing

3. 输入处理

Accepts stdin/piped input
Processes file paths (detects: .txt, .md, .json, .pdf, images)
Handles inline text prompts
Supports multimedia files with appropriate encoding

支持标准输入/管道输入
处理文件路径（支持的格式：.txt、.md、.json、.pdf、图片）
处理内嵌文本提示
支持对多媒体文件进行适当编码

4. Execution Modes

4. 执行模式

Non-Interactive (Default)

非交互模式（默认）

bash

llm "Your prompt here"
llm --model gpt-4o "Process this text"
llm < file.txt
cat document.md | llm "Summarize"

bash

llm "Your prompt here"
llm --model gpt-4o "Process this text"
llm < file.txt
cat document.md | llm "Summarize"

Interactive Mode

交互模式

bash

llm --interactive
llm -i
llm --model claude-opus --interactive

bash

llm --interactive
llm -i
llm --model claude-opus --interactive

5. Configuration

5. 配置

Persistent config location:

~/.claude/llm-skill-config.json

json

{
  "last_model": "claude-sonnet-4.5",
  "default_provider": "anthropic",
  "available_providers": ["openai", "anthropic", "google", "ollama"]
}

持久化配置文件路径：

~/.claude/llm-skill-config.json

json

{
  "last_model": "claude-sonnet-4.5",
  "default_provider": "anthropic",
  "available_providers": ["openai", "anthropic", "google", "ollama"]
}

Implementation Details

实现细节

Core Files

核心文件

```
llm_skill.py
```
- Main skill orchestration
```
providers.py
```
- Provider detection & config
```
models.py
```
- Model definitions & aliases
```
executor.py
```
- Execution logic (interactive/non-interactive)
```
input_handler.py
```
- Input type detection

```
llm_skill.py
```
- 技能主协调文件
```
providers.py
```
- 服务商检测与配置文件
```
models.py
```
- 模型定义与别名文件
```
executor.py
```
- 执行逻辑（交互/非交互模式）
```
input_handler.py
```
- 输入类型检测文件

Key Functions

关键函数

detect_providers()

detect_providers()

Scans environment for provider API keys
Returns dict of available providers

扫描环境变量中的服务商API密钥
返回可用服务商的字典

get_model_selector(input_text, provider=None)

get_model_selector(input_text, provider=None)

Returns selected model, showing menu if needed
Respects
```
last_model
```
config preference

返回选中的模型，必要时显示选择菜单
遵循
```
last_model
```
配置偏好

load_input(input_source)

load_input(input_source)

Handles stdin, file paths, or inline text
Returns content string

处理标准输入、文件路径或内嵌文本
返回内容字符串

execute_llm(content, model, interactive=False)

execute_llm(content, model, interactive=False)

Calls
```
llm
```
CLI with appropriate parameters
Manages stdin/stdout for interactive mode

使用适当的参数调用
```
llm
```
CLI
管理交互模式下的标准输入/输出

Usage in Claude Code

在Claude Code中的使用方式

When user invokes this skill, Claude should:

Parse input for model specification (e.g.,
```
--model gpt-4o
```
)
Call skill with content and optional model parameter
Wait for provider/model selection if needed
Execute and return results
For interactive mode, maintain conversation loop

当用户调用该技能时，Claude应：

解析输入中的模型指定（如
```
--model gpt-4o
```
）
携带内容和可选的模型参数调用技能
必要时等待服务商/模型选择
执行并返回结果
对于交互模式，维持对话循环

Error Handling

错误处理

If no providers available: Suggest installing API keys
If model not found: Show available models for chosen provider
If llm CLI not installed: Suggest installation via
```
pip install llm
```
If file not readable: Fall back to treating as inline text

若无可用服务商：建议安装API密钥
若模型未找到：显示所选服务商的可用模型
若未安装llm CLI：建议通过
```
pip install llm
```
进行安装
若文件无法读取：退回到将其视为内嵌文本

Configuration

配置

Users can pre-configure preferences:

json

{
  "last_model": "claude-sonnet-4.5",
  "default_provider": "anthropic",
  "interactive_mode": false,
  "available_providers": ["openai", "anthropic"]
}

用户可以预先配置偏好：

json

{
  "last_model": "claude-sonnet-4.5",
  "default_provider": "anthropic",
  "interactive_mode": false,
  "available_providers": ["openai", "anthropic"]
}

Slash Command Integration

斜杠命令集成

Support

/llm

command:

/llm process this text
/llm --interactive
/llm --model gpt-4o analyze this

支持

/llm

命令：

/llm process this text
/llm --interactive
/llm --model gpt-4o analyze this