add-top-openrouter-models
Sync OpenRouter models used by OpenClaw into this installation's config. Fetches the OpenClaw app leaderboard from OpenRouter, verifies model IDs against the API catalog, and adds missing models with correct specs and aliases. Use when asked to "sync openrouter models", "add missing models", "update openrouter config", or "check openrouter models".
Why use this skill?
Automate the synchronization of OpenRouter models into your OpenClaw agent configurations. Easily fetch, verify, and add the latest AI models from the leaderboard.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/chunhualiao/add-top-openrouter-modelsWhat This Skill Does
The add-top-openrouter-models skill is an essential automation tool for OpenClaw users who rely on up-to-date model access via OpenRouter. This skill streamlines the complex task of identifying, verifying, and registering the latest AI models showcased on the OpenClaw leaderboard. Instead of manually parsing web data and updating sensitive configuration files, this skill automates the entire lifecycle: it uses a headless browser to extract model identifiers from the React-based OpenClaw leaderboard, validates these identifiers against the official OpenRouter API catalog, calculates metadata (such as context window and modalities), and injects them into your local OpenClaw configuration files.
Installation
To integrate this skill into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/chunhualiao/add-top-openrouter-models
Ensure that you have the necessary permissions for the script to modify your ~/.openclaw directory, as the skill performs file-write operations to update your agent and system configurations.
Use Cases
This skill is ideal for power users who want to stay on the bleeding edge of AI performance. Use it when:
- You notice that new, high-performance models have appeared on the OpenRouter leaderboard but are not yet selectable in your OpenClaw interface.
- You want to ensure your
agent/models.jsonis synced with the community's top-rated models. - You are troubleshooting model availability issues and suspect your local config is out of sync with the OpenRouter catalog.
Example Prompts
- "Sync openrouter models so I can access the latest leaderboard options."
- "Check openrouter models and add any missing ones to my current configuration."
- "Update openrouter config to make sure I have all the latest models and aliases available."
Tips & Limitations
- Browser Necessity: Because the OpenClaw leaderboard is a dynamic SPA, you must have the browser tool enabled. The skill cannot function if it cannot render the JavaScript on the leaderboard page.
- Additive Design: Note that this skill only performs additive updates. It will not automatically purge delisted or deprecated models from your configuration. You may periodically need to audit your files to remove obsolete entries.
- Safe Backups: Always check the
.bak.<timestamp>files created in your config folder if you suspect a sync went wrong. The script is designed to be idempotent and safe, but manual verification is recommended when performing major configuration updates.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-chunhualiao-add-top-openrouter-models": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api, code-execution
Related Skills
task-runner
Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronously via subagents. A heartbeat/cron dispatcher wakes periodically to check pending tasks, spawn workers, and report completions. The system never "finishes" — it always remains ready for the next task.
git-repo-to-book
Write a full-length technical book using multi-agent AI orchestration. Spawns parallel research, writing, and review agents to produce 60K-100K+ word manuscripts. Also supports revising individual chapters of existing books. Based on the real workflow that produced an 88,000-word, 14-chapter book in under 18 hours.
claude-usage
Check Claude Max plan usage limits by launching Claude Code and running /usage. Use when the user asks about Claude plan usage, remaining quota, rate limits, or sends /claude_usage.
skill-engineer
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester subagents for quality-gated skill development. Use when user asks to "design skill", "review skill", "test skill", "audit skills", "refactor skill", or mentions "agent kit quality".
deepwiki
Query DeepWiki MCP to get AI-grounded answers about any public GitHub repository. Use when answering questions about a repo's source code, architecture, configuration, or internals. Triggers on "how does X work in <repo>", "deepwiki", "look up in codebase", "ask deepwiki", "check the source code".