ngrok (MMClaw)

Trust Score 79/100

Expose a local port to the public internet by launching an ngrok tunnel via Python; useful for sharing local web services or receiving webhooks during developme

triggers:ngrokpublic URLexpose my servertunnelaccess from outside

GitHub SKILL.md

What it does

This skill provides a step-by-step pattern to expose a locally running server to the public internet using ngrok invoked as a Python package. It covers installation guidance, storing an authtoken in the agent workspace, launching a background tunnel process, and reliably reporting the public URL back to the user. The instructions emphasise invoking ngrok through Python (not a standalone binary) and include a safe background-run pattern that writes the tunnel URL to a file the agent can read.

When to use it

Use this skill when a user needs a temporary public URL for a development server, to accept incoming webhooks, demo a local site, or allow remote testing without deploying. It's intended for short-lived developer sessions (free tier) and notes differences for paid/static domains.

What's included

Scripts: None bundled in the repo, but the skill body contains a ready-to-run Python background pattern to create and persist the ngrok tunnel URL.
References: No additional reference files detected.
Instructions: Install via pip, store authtoken in $MMCLAW_WORKSPACE/skill-config/ngrok.json, run the provided Python background launcher, then read and report the generated URL. The skill explicitly requires the agent to surface the public URL directly in replies.

Compatible agents

This skill is written for lightweight Python-based agent runtimes that can run background Python processes and use shell_async/shell tools (MMClaw-style agents). Compatible targets: Python-based agents and CLIs that support background execution and file I/O.

Audit Summary

Single-file MMClaw skill for exposing local ports via ngrok Python package. Clear trigger phrases and step-by-step instructions for install, config, and tunnel startup. No bundled scripts — all logic is inline Python/bash snippets in SKILL.md. Minimal error handling in the code snippets; no try/except on ngrok connection or file reads. Authtoken is user-provided and stored in a config file, not hardcoded.

Watch Out

Requires ngrok authtoken from user before first use
No error handling if ngrok.forward() fails
PORT placeholder in usage snippet needs agent to substitute correctly

Notes

Clean skill, no security concerns. Architecture is flat (single file, no scripts/ or references/ directories). Would benefit from a helper script to encapsulate the tunnel startup logic instead of inline python -c strings.

Information

Repository: mmclaw
Stars: 136
Installs: 0

Trust Score

Overall79

Security95

Code Quality68

Architecture55

Usefulness62

Related Skills

Extract Circuit Netlist Edge Features

Extract structured edge features from a bipartite circuit netlist (NetworkX MultiGraph), normalizing device/net ordering, mapping terminal colors, and detecting

Starlark Dev

Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.

Markdrop

Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.

Sandbox0 Integration

Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.

FastAPI Project Templates

Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.

Unitree Robot Controller

Control and command Unitree robots (GO1/GO2/G1/H1) via OpenClaw: initialization, basic motion commands, and sensor integrations.

Alpha Forge Pre-Ship Quality Gates

Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.

Blender Build-Go (bgo)

Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.

Back to Skills