claw-turbo

Name: claw-turbo
Author: jacobye2017-afk

功能描述

Zero-latency regex-based skill routing middleware for OpenClaw. Intercepts known user commands (deploy, restart, print, check logs, etc.) using compiled rege...

使用说明 (SKILL.md)

What is claw-turbo?

claw-turbo is a zero-latency, zero-ML skill routing middleware that sits between OpenClaw and your local LLM (Ollama). It intercepts user messages using regex pattern matching and executes skill scripts directly — no LLM inference needed.

Simple commands get instant, perfect execution. Complex queries still go to your LLM.

User message → claw-turbo (regex match, \x3C0.01ms)
                  ├── MATCH → execute script directly (0ms, 100% accurate)
                  └── NO MATCH → forward to LLM (normal processing)

Why use claw-turbo?

Approach	Latency	Accuracy	Dependencies
claw-turbo	5 us	100%	PyYAML only
LLM routing (Gemma/Llama)	2-10s	~80%	Ollama + VRAM
Semantic routing	50-200ms	~95%	embedding model

Local LLMs are unreliable for simple, repetitive commands:

They don't always follow tool-calling instructions
They hallucinate flags and wrong parameters
Context window limits cause instruction loss

Installation

git clone https://github.com/jacobye2017-afk/claw-turbo.git
cd claw-turbo
pip install -e .

Quick Start

1. Define routes in `routes.yaml`

routes:
  - name: deploy-staging
    description: "Deploy a service to staging"
    patterns:
      - 'deploy\s+(?P\x3Cservice>\w+)\s+(?:to\s+)?staging'
    command: 'bash /opt/scripts/deploy.sh {{service}} staging'
    response_template: "Deployed {{service}} to staging"

  - name: restart-service
    patterns:
      - 'restart\s+(?P\x3Cservice>[\w-]+)'
    command: 'systemctl restart {{service}}'
    response_template: "Restarted {{service}}"

2. Test matching

claw-turbo test "deploy auth-service to staging"
# MATCHED: deploy-staging
#   Captures: {'service': 'auth-service'}
#   Time: 4.8us

3. Start the proxy

claw-turbo serve --port 11435

Then change OpenClaw's Ollama baseUrl to http://127.0.0.1:11435.

Use Cases

DevOps: "restart nginx", "deploy to staging", "show logs for api-server"
Document processing: "print report ABC123", "generate invoice 456"
IoT / smart office: "turn on lights", "set AC to 22 degrees"
Data pipelines: "run ETL for 2024-01", "refresh dashboard"
Customer service: "check order ORD-789", "refund order ORD-789"

Features

Sub-microsecond regex matching (compiled patterns)
Named capture groups → template variables
Hot-reload routes.yaml (no restart needed)
Transparent HTTP proxy (Ollama API compatible)
Multi-language patterns (Chinese, English, any language)
Zero ML dependencies (PyYAML + stdlib only)
Works fully offline

CLI

claw-turbo serve [--port 11435]     Start HTTP proxy
claw-turbo test "message"           Test pattern matching
claw-turbo routes                   List all routes
claw-turbo add-skill \x3Cpath>         Generate route from SKILL.md

Links

GitHub: https://github.com/jacobye2017-afk/claw-turbo
Author: Jacob Ye (@jacobye2017-afk)
License: MIT

安全使用建议

This skill claims to run shell commands directly when a regex matches — that’s powerful but dangerous if misconfigured. Before installing or enabling it: 1) Inspect the GitHub repo source (not just SKILL.md) before running pip install; 2) Do not deploy on production hosts until you confirm route templates are safe — avoid systemctl/journalctl/bash calls unless necessary; 3) Sanitize and strongly constrain routes.yaml patterns and command templates (prefer fully controlled commands, not raw insertion of user captures); 4) Run the proxy in a sandboxed environment or container with least privilege and restrict network access (keep baseUrl bound to localhost and firewall it); 5) Fix the metadata oddity (primaryEnv:'python') or ask the author what credential that refers to; 6) Consider alternative approaches (explicit, validated command wrappers or a small service that exposes a safe RPC) if you need automated routing. If you cannot review the external code or enforce strong sandboxing, treat this skill as risky and avoid installing it on critical systems.

功能分析

Type: OpenClaw Skill Name: claw-turbo Version: 1.0.0 The skill bundle describes a middleware ('claw-turbo') designed to intercept user commands via regex and execute shell commands directly to bypass LLM latency. This architecture introduces a significant Remote Code Execution (RCE) risk, as seen in 'routes.example.yaml', which demonstrates passing the '{{raw_message}}' variable directly into bash scripts without sanitization. While the stated intent is performance optimization, the tool functions as a transparent proxy that executes arbitrary system commands (e.g., systemctl, journalctl) based on unvalidated input, creating a high-risk attack surface.

能力标签

cryptocan-make-purchases

能力评估

ℹ Purpose & Capability

The declared purpose (zero-latency regex routing that executes skill scripts) is coherent with requested binaries (python3, bash). However the packaged files contain only docs and examples (no implementation or CLI), while SKILL.md instructs installing a GitHub project and running a 'claw-turbo' CLI. The metadata's primaryEnv is set to 'python' (not an environment variable name) which is incoherent with how primary credentials are normally declared.

⚠ Instruction Scope

SKILL.md instructs the agent to execute system-level commands templated from regex captures (e.g., 'systemctl restart {{service}}', 'journalctl -u {{service}}', 'bash /opt/scripts/deploy.sh {{service}} staging'). There is no guidance about sanitizing capture groups, quoting, or running in a restricted environment. That design is coherent with 'devops' use but introduces a high risk of command injection or accidental execution of privileged operations if routes.yaml contains unsafe templates or an attacker can influence inputs.

ℹ Install Mechanism

There is no registry install spec; the SKILL.md tells users to git clone and pip install from the GitHub repo (a normal, traceable pattern). Because the distributed bundle here contains only docs/examples, the skill as presented relies on fetching code at install time from the external GitHub URL — that external code would need review before pip install. No opaque download URLs or archive extraction are present in the metadata.

⚠ Credentials

The skill requests no secrets or environment variables (good), and only requires python3 and bash. However the metadata's primary credential field is set to 'python', which is nonsensical and may indicate sloppy metadata. The lack of required env vars is proportionate to the stated purpose, but the ability to run arbitrary system commands via templates creates an implicit need for careful privilege control that the instructions do not address.

✓ Persistence & Privilege

always:false and default autonomous invocation are used (normal). The skill does not request permanent system-wide privileges in metadata, and does not attempt to modify other skills' config. The main persistence/privilege concern is operational: once installed and wired as Ollama's baseUrl, it will intercept user messages and can run commands on the host — a powerful capability that should be limited by policy and environment, but this is consistent with its declared purpose.

版本历史

v1.0.0

Initial release of claw-turbo — zero-latency regex-based skill routing for OpenClaw. - Instantly intercepts and executes common user commands using compiled regex patterns, bypassing LLM inference for matched routes. - Achieves sub-microsecond (5μs) matching and response, with 100% accuracy for defined commands. - Supports easy route definition via YAML and hot-reloading without restart. - Compatible with Ollama API, works offline, and requires only PyYAML as a dependency. - Includes CLI for testing, serving, and managing routes and skills.

元数据

Slug claw-turbo

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

claw-turbo 是什么？

Zero-latency regex-based skill routing middleware for OpenClaw. Intercepts known user commands (deploy, restart, print, check logs, etc.) using compiled rege... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 68 次。

如何安装 claw-turbo？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install claw-turbo」即可一键安装，无需额外配置。

claw-turbo 是免费的吗？

是的，claw-turbo 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

claw-turbo 支持哪些平台？

claw-turbo 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（macos, linux）。

谁开发了 claw-turbo？

由 jacobye2017-afk（@jacobye2017-afk）开发并维护，当前版本 v1.0.0。