Agent skill

claude

Enhanced CLI module for Claude Code, supporting third-party model providers and session management. Core Scenario: When the user wants to use Claude Code with alternative models (DeepSeek, etc.), track token usage, or manage MCP servers.

View SKILL.md on GitHub Repository
Stars 19
Forks 4

Install this agent skill to your Project

npx add-skill https://github.com/x-cmd/skill/tree/main/data/x-cmd/claude

SKILL.md

claude - Claude Code Enhancement Module

The claude module extends the capabilities of Anthropic's claude-code, allowing users to connect to various AI model providers, manage sessions, and monitor token usage through a unified CLI.

When to Activate

  • When the user wants to start a Claude Code session with a specific provider (e.g., DeepSeek, Kimi, Moonshot, SiliconFlow, Doubao, MiniMax, Zhipu, etc.).
  • When the user needs to configure Claude Code to use a third-party model globally or per project.
  • When the user wants to track token consumption and costs for the last 7 days.
  • When the user needs to manage Model Context Protocol (MCP) servers.
  • When the user wants to clean up or customize Claude Code's status line or author attribution.

Core Principles & Rules

  • Provider Connection: Use subcommands like ds (DeepSeek), kimi, moonshot, sili (SiliconFlow), doubao, mm (MiniMax), zhipu (GLM), or (OpenRouter), ali (Qwen), baidu (Ernie), tencent (Hunyuan), or mt (Mthreads) to launch Claude Code with those specific backends.
  • Global vs. Project Config: Use use for global settings and use --project for project-specific model overrides.
  • Session Management: Use sess (Interactive FZF App) or resume to manage and recover previous conversations.
  • Security: Be cautious when using the --dangerously-skip-permissions flag; it should only be recommended in trusted sandbox environments.

Additional Scenarios

  • Local LLM: Connect Claude Code to a local Ollama service using x claude use other.
  • Token Analysis: Run x claude usage to get a detailed breakdown of costs and token count.
  • Clean Git History: Remove the automatic Co-Author signature from Git commits using x claude attribution rm.

Patterns & Examples

Launch with Third-party Providers

bash
# Start Claude Code using the DeepSeek model
x claude ds

# Start Claude Code using SiliconFlow
x claude sili

# Start Claude Code using Kimi
x claude kimi

Configure Project Model

bash
# Set the current project to use Zhipu (GLM) model provider
x claude use --project glm

# Set the current project to use SiliconFlow
x claude use --project sili

Track Usage

bash
# Analyze token usage and costs for the past 7 days
x claude usage

Interactive Session Management

bash
# Browse and manage local sessions via FZF
x claude sess

Checklist

  • Confirm if the user wants to use a specific model provider (DeepSeek, MiniMax, etc.).
  • Verify if the configuration should be global or project-specific.
  • Ensure the relevant API Key is configured for the chosen provider.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

x-cmd/skill

pufferlib

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

19 4
Explore
x-cmd/skill

fluidsim

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.

19 4
Explore
x-cmd/skill

metabolomics-workbench-database

Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.

19 4
Explore
x-cmd/skill

geniml

This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.

19 4
Explore
x-cmd/skill

zinc-database

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

19 4
Explore
x-cmd/skill

astropy

Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.

19 4
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results