功能描述

Safe local Mac optimization toolkit for OpenClaw agents on Apple Silicon. 1-trillion agent swarm simulation, local CoreML resource forecasting, safe cleanup...

使用说明 (SKILL.md)

MacPowerTools v3.1 — Safe Local Trillion-Forge

Name: MacPowerTools
Author: aadipapp

100% local & ClawHub-safe. Runs forever on your Mac Mini with zero internet, zero sudo, zero persistence.

Install (one command)

claw install aadipapp/mac-power-tools

安全使用建议

This skill mostly does local tasks, but there are several things to verify before installing: (1) SKILL.md repeatedly claims 'no persistence', yet the code creates ~/.logs and ~/.config/macpowertools and writes a learning.json — expect local on-disk traces. (2) SKILL.md metadata and registry metadata disagree about Python/numpy requirements and version numbers; confirm whether numpy will be installed or required. (3) The file contains comments claiming original cleanup/backup handlers are 'preserved', but the provided code appears to have placeholders rather than full implementations — ask the author for the full source or inspect the shipped file yourself. (4) The script runs dns-sd for LAN discovery (mDNS) — this is LAN-only but will enumerate local services; make sure you are comfortable with a skill doing local network discovery. If you decide to proceed, review the exact power_tools.py file that will be installed (search for any hidden network calls, unexpected file writes, or code executed for cleanup/backup) and confirm the author/registry identity and version alignment. If you need higher assurance, request a signed release or an install that clearly documents the files the skill will create and their purposes.

功能分析

Type: OpenClaw Skill Name: mac-power-tools Version: 1.0.9 The MacPowerTools skill bundle is a local macOS utility that provides simulated resource forecasting and local network discovery. While the '1-trillion agent swarm' and 'CoreML' features in power_tools.py are implemented as simple statistical simulations (random number generation) rather than actual complex models, the code lacks any indicators of malicious intent, data exfiltration, or persistence. The use of 'dns-sd' for mDNS browsing in power_tools.py is a standard method for local service discovery and aligns with the stated 'local-network-discovery' capability.

能力评估

⚠ Purpose & Capability

Name/description (local Mac optimization, local CoreML forecasting, LAN discovery) aligns with code that performs local simulations, a CoreML-style forecast, and an mDNS scan. However SKILL.md claims python>=3.10 and numpy as a requirement while the registry metadata lists no requirements; the script handles a missing numpy by returning an error. Also the SKILL.md and file comments claim full original cleanup/backup logic is present, but the provided power_tools.py appears to omit concrete handlers for many commands (placeholders/comments instead). These mismatches reduce confidence that the packaged code matches the advertised capability.

⚠ Instruction Scope

SKILL.md instructs a one-line install and claims '100% local, zero internet, zero sudo, zero persistence.' The code does run only local commands (dns-sd), prints share text (encouraging posting to Moltbook/other discovery), and does not perform remote network calls. But it creates persistent directories and files under the user's home (~/.logs and ~/.config/macpowertools and a learning.json file) — contradicting the 'no persistence' statement. The script also spawns subprocesses (dns-sd) and writes logs/history; instructions do not warn about this on-disk state.

ℹ Install Mechanism

There is no install spec (instruction-only skill) which is low risk for supply-chain installs. SKILL.md metadata lists a PyPI dependency (numpy), but no automated install step is provided; the script handles numpy absence gracefully. This means the environment must already satisfy dependencies or the swarm-simulation feature will be disabled.

ℹ Credentials

The skill requests no environment variables or system credentials, which is appropriate for the stated purpose. However it does create and write to hidden directories in the user's home (persistent logs and a learning.json history). That is reasonable for a local tool but contradicts the 'no persistence' claim and should be disclosed to users.

⚠ Persistence & Privilege

always:false (normal). The code nonetheless creates persistent files under the user's home (~/.logs and ~/.config/macpowertools) and maintains a history file. SKILL.md explicitly claims 'no persistence', so the actual behavior is inconsistent and could surprise users. The skill does not request elevated privileges, but it does assert discoverability and prints share text for posting elsewhere.

版本历史

v1.0.9

- Transitioned to a fully local, internet-free, and user-level toolkit for Mac optimization and agent simulation. - Removed dependencies on external binaries, persistent installation, and networked Moltbook/viral features; now ClawHub-searchable only. - Simplified required dependencies—only Python (>=3.10) and numpy are needed. - Introduced new safe-cleanup and local maintenance features. - Updated capability set to focus on local trillion-agent simulations, CoreML forecasting, and user-level process monitoring.

v1.0.8

Major 3.0 release: Trillion-agent swarm orchestration and CoreML forecasting on Mac. - Simulate and coordinate up to 1 trillion OpenClaw agents (trillion-scale swarm). - Native support for CoreML-powered forecasting on Apple Silicon. - Discover and recruit Mac fleets across real Moltbook network & mDNS. - New "viral recruitment" tool for rapid swarm expansion. - Expanded dependencies and capabilities, including requests, dns-sd, and advanced fleet orchestration.

v1.0.7

- Added numpy as a required dependency (install with pip). - Updated install instructions to include numpy installation. - Declared new capabilities: "swarm-coherence" and "process-monitor". - Expanded capabilities list in metadata. - No code changes detected in this release.

v1.0.6

MacPowerTools 2.5.0 – now safer, with improved backup and privilege restrictions: - Refined description and documentation to emphasize "safe" maintenance and no sudo usage. - Backup now restricted to mounted local volumes only; explicit rejection of remote backups. - Clarified that all commands are user-level and never require administrator privileges. - Metadata, tags, and capabilities updated to reflect stronger safety and clear purpose. - Improved and simplified install instructions and capability summary.

v1.0.5

MacPowerTools v2.4.0 — Expanded capabilities & improved safety - Added support for ClawHub compliance and stronger usage boundaries. - Optional Android transfer clarified (ADB now specifically optional). - Introduced launchd integration: install as persistent daily daemon via setup command. - Enhanced documentation for safe defaults, operation directories, and network actions. - Added environment variable for Moltbook posting (MOLTBOOK_TOKEN). - Expanded capabilities listing (network posting, launchd-daemon support).

v1.0.4

MacPowerTools 2.3.0 — Now with self-learning and adaptive features - Introduces self-learning: tracks performance and adapts tuning automatically based on agent usage. - Adds persistent learning history with trend analysis. - New `self-learn` command for auto-improvement. - New `promote` command to generate Moltbook-ready posts with live stats. - Capabilities, binaries, and descriptions updated to reflect adaptive and Moltbook-promotion features. - Improved integration for OpenClaw workflows on Apple Silicon Mac Mini.

v1.0.3

Major update: MacPowerTools now optimized for OpenClaw agents and modern Mac Minis. - Completely refactored codebase; merged utilities into a single script (`power_tools.py`) - Removed legacy scripts and test files, streamlining for headless Mac Mini/M-series agent use - New focus on security, M-series performance tuning, and agent hardening - Defaults to safe/dry-run operation; adds OpenClaw integration features - Updated skill metadata for advanced deployment, system compatibility, and security-bold scenarios

v1.0.2

- Added machine learning cleanup tools for safely clearing large ML cache directories (HuggingFace, PyTorch, Pip, WandB) with dry-run protection. - Introduced system info command to display CPU, RAM, and disk usage using native macOS utilities. - Enhanced backup commands: full system backups now automatically exclude ML cache directories to save storage space. - Updated documentation to reflect new commands: `ml-cleanup`, `sys-info`, and improved backup options.

v1.0.1

- Added new drive transfer functionality in scripts/drive_transfer.py. - Introduced test coverage for drive transfer with tests/test_drive_transfer.py. - Minor internal updates; no changes to user-facing documentation.

v1.0.0

Initial release of MacPowerTools. - Introduces a unified suite for system cleanup and secure Android file transfer on macOS. - System Cleanup: Empties Trash, cleans old caches, and removes old downloads with a safety-first dry run default. - Secure File Transfer: Transfers files to Android devices using ADB with integrated SHA256 verification and overwrite protection. - Provides simple commands: cleanup and transfer, with optional force and destination arguments.

元数据

Slug mac-power-tools

版本 1.0.9

许可证 MIT-0

累计安装 11

当前安装数 10

历史版本数 10

常见问题

MacPowerTools 是什么？

Safe local Mac optimization toolkit for OpenClaw agents on Apple Silicon. 1-trillion agent swarm simulation, local CoreML resource forecasting, safe cleanup... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1291 次。

如何安装 MacPowerTools？

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

MacPowerTools 是免费的吗？

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

MacPowerTools 支持哪些平台？

MacPowerTools 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin）。

谁开发了 MacPowerTools？

由 Krishna Aditya（@aadipapp）开发并维护，当前版本 v1.0.9。

MacPowerTools