xtlapi

xtlapi is the official XTLAPI user-level Skill for Claude Code, Codex, and OpenClaw. Query models, manage tokens, view groups, check balance, and ask XTLAPI usage questions directly inside your AI coding workflow.

What is xtlapi-skills?

xtlapi-skills is the official AI editor Skill plugin from XTLAPI. Skills are a lightweight extension protocol that enables AI coding assistants — such as Claude Code, Codex, OpenClaw, Cursor, Windsurf, and Cline — to call XTLAPI endpoints directly from within the editor, performing model queries, token management, balance checks, and answering XTLAPI deployment, configuration, and API usage questions without ever leaving your coding environment.

GitHub Repository: github.com/QuantumNous/skills

It now also works inside OpenClaw, so you can run /xtlapi commands for models, tokens, groups, and balance, and ask XTLAPI usage questions without leaving your agent workflow.

Why Use Skills

During everyday AI development, developers frequently switch between their editor and the XTLAPI management dashboard — checking available models, creating API tokens, inspecting balance, adjusting group quotas. These context switches disrupt coding flow.

What xtlapi-skills solves:

Zero context-switching: Issue natural language commands directly in Claude Code, Codex, OpenClaw, or other AI IDEs — no browser or admin panel needed
Built-in help: Ask about XTLAPI deployment, configuration, groups, and API call formats directly from your coding workflow
Security-first design: Keys are never shown in plain text; token copy and injection use secure channels (sk- prefixed keys never appear in terminal output or logs)
Instant setup: A single npx command handles installation; runtime auto-detection (Bun / Node.js / Deno)
Cross-editor compatibility: Works with any AI editor or coding assistant that implements the Skills protocol

Supported AI Editors

xtlapi-skills works with the following AI coding tools:

AI Editor / Coding Assistant	Type	Notes
Claude Code	Terminal AI programming assistant	Official Anthropic CLI
OpenClaw	Self-hosted AI assistant platform	Supports Skills-based `/xtlapi` command workflows
Cursor	AI-native code editor	VS Code based
Windsurf	AI code editor	By Codeium
Cline	VS Code AI extension	Open-source AI coding agent
Codex CLI	Terminal AI programming assistant	Official OpenAI CLI

Any tool that supports the Skills protocol can use xtlapi-skills.

Commands Reference

Below is the complete list of commands provided by xtlapi-skills. These commands interact with the XTLAPI REST API to query and manage resources on your XTLAPI instance.

Query Commands

Command	Description	Use Case
`/xtlapi models`	List available AI models	View all models configured on your XTLAPI instance (OpenAI, Claude, Gemini, etc.)
`/xtlapi groups`	List user groups	View your account's groups with quota and rate multiplier settings
`/xtlapi balance`	Show account balance	Real-time query of current user's balance and usage

Token Management Commands

Command	Description	Use Case
`/xtlapi tokens`	List API tokens	View all created tokens (keys shown masked, e.g. `sk-reHR**********OspA`)
`/xtlapi create-token <name> [--group=xxx]`	Create new API token	Generate independent API keys for different apps or projects
`/xtlapi switch-group <token_id> <group>`	Change token's group	Modify token group to adjust model access permissions and rate multipliers
`/xtlapi copy-token <token_id>`	Copy key to clipboard	Securely copy the real key to system clipboard (key never displayed in terminal)
`/xtlapi apply-token <token_id> <file>`	Inject key into config file	Securely write token key into project config files (e.g. `.env`) via placeholder replacement

Help Command

Command	Description	Use Case
`/xtlapi help <question>`	Ask about XTLAPI	Get help on XTLAPI deployment, configuration, API call formats, and more

Installation & Configuration

Install xtlapi-skills

One-line installation via npx:

npx skills add https://github.com/QuantumNous/skills --skill xtlapi

This pulls the latest Skill definition from the GitHub repository and installs it into your editor environment.

Set Environment Variables

xtlapi-skills requires three environment variables to connect to your XTLAPI instance. Add them to your shell profile:

# ~/.bashrc or ~/.zshrc
export NEWAPI_BASE_URL=https://api.xtlai.cn
export NEWAPI_ACCESS_TOKEN=your-access-token
export NEWAPI_USER_ID=1

Variable	Description	Example
`NEWAPI_BASE_URL`	XTLAPI service URL	`https://api.xtlai.cn`
`NEWAPI_ACCESS_TOKEN`	Admin or user access token	From "Personal Settings → Account → Security → System Access Token"
`NEWAPI_USER_ID`	User ID	`1` (admin default is 1)

You can also create a .env file in your project root. Make sure .env is listed in .gitignore to prevent key leaks.

Start Using

Once installed, type /xtlapi commands in any Skills-compatible AI editor. For example:

Type /xtlapi models to list available models
Type /xtlapi balance to check your current balance
Type /xtlapi create-token my-app to create a new token named my-app
Type /xtlapi help how do I configure groups and tokens? to ask XTLAPI usage questions directly
In OpenClaw, you can also run /xtlapi models, /xtlapi balance, and token commands directly in your agent workflow

Runtime Requirements

xtlapi-skills requires one of the following JavaScript runtimes (auto-detected at startup):

Runtime	Version	Recommendation
Bun	Latest	Recommended (fastest)
Node.js	>= 18	Widely supported
Deno	Latest	Optional

Security

xtlapi-skills has multiple layers of security built in to protect your API keys:

Token listings only show masked keys (e.g. sk-reHR**********OspA) — real keys never appear in terminal output
copy-token copies the key to the system clipboard only, never displaying it in any output
apply-token uses placeholder replacement to inject keys, never exposing raw key content
All sk- prefixed key values are strictly protected throughout the entire execution flow

On this page