A deterministic utility for matching user tasks to the most relevant installed skills while maintaining library health through daily audits.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install skill-auto-router
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install skill-auto-router using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Skill Auto Router?
The Skill Auto Router is a sophisticated preflight engine designed to streamline how AI agents interact with their environment. By analyzing task requirements before execution, it ensures that your agent only loads the most pertinent Openclaw Skills, preventing context bloat and improving response accuracy. This skill acts as a traffic controller, utilizing a local matching algorithm to rank candidates and provide clear reasoning for each selection.
Beyond simple routing, it serves as a maintenance tool for developers managing a growing library of Openclaw Skills. Through its daily audit functionality, it identifies overlapping triggers and weak descriptions that could lead to agent confusion. This proactive approach ensures that the skill ecosystem remains sharp, efficient, and free from redundant or vague capabilities.
Skill Auto Router Use Cases
- Automatically selecting the best tools for a specific developer task to reduce token usage.
- Conducting a daily heartbeat audit to find duplicate trigger language across installed Openclaw Skills.
- Enhancing workspace steering by integrating automated routing into agent pre-task checklists.
- Identifying and refining vague skill descriptions that negatively impact trigger quality.
How Skill Auto Router Works
- The router accepts a task string or an audit flag via the command line interface.
- It scans the local environment to discover all available Openclaw Skills and parses their metadata.
- For tasks, it applies a deterministic ranking algorithm to find the top 1-3 matching skills based on trigger specificity.
- For audits, it analyzes the entire skill set for overlaps, duplicates, and description quality.
- The results are output as ranked candidates with match reasons or a comprehensive health report.
Skill Auto Router Setup
To integrate this routing logic into your workspace for Openclaw Skills, use the provided scripts:
# Perform a pre-task routing check
python scripts/skill_router.py --task "<your task description>"
# Run the daily skill health audit
python scripts/skill_router.py --daily
For seamless automation, it is recommended to add these commands to your AGENTS.md pre-task checklist and HEARTBEAT.md daily logs using the snippets found in the references directory.
Skill Auto Router Data Schema & Taxonomy
The Skill Auto Router organizes its logic and integration data through a simple file structure:
| File Path | Purpose |
|---|---|
scripts/skill_router.py |
The main execution script for matching and auditing logic. |
references/setup-checklist.md |
Contains integration snippets for workspace steering files. |
Match Output |
Ranked list of skill candidates, match scores, and justification strings. |
Audit Logs |
Reports on total skill count, duplicate triggers, and metadata quality. |
Skill Auto Router Advanced Features
- Deterministic matching that avoids the hallucinations often associated with LLM-based tool selection.
- Multi-agent workflow support by wiring routing into shared steering documents.
- Specificity bias that prioritizes specialized Openclaw Skills over general-purpose ones when matches tie.
- Integration-ready hooks for HEARTBEAT workflows to ensure constant library optimization.
SKILL.md
Loading
Related Openclaw Skills
Playwright Pro
A comprehensive, production-grade toolkit for AI coding agents to architect, generate, and maintain robust Playwright test suites.
Hello World Skill
A foundational testing skill designed to demonstrate custom AI agent greeting protocols and basic skill integration.
Code Security Auditor
A specialized skill for identifying and fixing critical security vulnerabilities within application source code.
Shell Safe Exec
A secure execution environment for running non-destructive repository commands like testing, building, and linting within local workspaces.
copypaste-cloud
A streamlined integration for interacting with the copy-paste.cloud pastebin to share code snippets and retrieve public text data.
Promptfoo
Promptfoo is a powerful framework for running local, repeatable LLM evaluations and adversarial red-team security scans to ensure model reliability.
Featured*
