Read, write, list, move, and inspect files and directories on a remote host via QuickDesk. Use when the user needs to browse folders, view file contents, create or edit files, rename or relocate files, or check file metadata (size, permissions, modification time) on a remote machine.
Execute shell commands on a remote host via QuickDesk and return stdout, stderr, and exit code. Use when the user asks to run a command, script, or terminal operation on a remote machine — supports configurable timeout and working directory.
Retrieve system information and list running processes on a remote host via QuickDesk. Use when the user asks to check server health, monitor CPU or memory usage, view disk space, list running processes, or query OS and uptime details on a remote machine.
Capture headless-Chrome screenshots of the tingly-box frontend (running locally in mock mode) so frontend changes can be visually verified in environments without a real browser. Use when the user asks to "preview", "screenshot", "see the page", "show me the UI", "verify visually", or when frontend layout / component…
Use when a local AI agent needs to reach into a remote Linux server over SSH — to explore data, run commands, inspect logs, diagnose something on the server, or pull data down to the local machine — or to set up that SSH access for the first time. Triggers include "luffy-arm", "connect to my server", "ssh into the…
Use when the user asks to turn off, disable, close, or disarm luffy-arm full-power mode, including "turn off full power", "disable full-power", 关闭 full power, 退出全功率模式. Removes the dedicated admin key, verifies that credential is off, and reports alternate user-level SSH access separately.
Use when the user explicitly asks to turn on, enable, open, or arm luffy-arm full-power mode, including "turn on full power", "enable full-power", 打开 full power, 开启全功率模式. Check layered host status first and reuse an already-ON dedicated gate; gate state and effective ADMINUSER access are distinct. The agent never…
A development command that starts the project with Bun, a JavaScript runtime and toolchain. It runs the CLI application's development server and checks whether the chosen port is already in use.
A release workflow for changing a package's version, checking its types, and publishing a matching Git commit and tag. A Git tag is a named marker that identifies a specific version of the code.
This skill should be used when the user asks to "communicate via Discord", "send a message to Discord", "check Discord for instructions", "ask a question on Discord", "notify on Discord", "share a file on Discord", "離席する", "離席モード", "Discord で待機して", "Discord待機", or when Claude Code needs to reach the user who is away…
A read-only workflow that asks the Codex command-line tool for an independent review of code, a plan or a proposed change. It supports detailed review, deliberate attempts to break a solution, a second opinion, plan-compliance checks and diagnosis when work is stuck.
A handoff skill that turns the current coding session into an independent background agent managed by claude-control. The agent continues the stated mission after you leave the session.
A web-research workflow for answering questions with current, checked information from multiple online sources. It breaks the question into searches, reads full pages, compares claims and records citations with URLs and access dates.
Use when the user wants to start, inspect, stop, restart, or troubleshoot the local NordRelay runtime, including prompts like "remote", "/remote", "NordRelay Remote", "NordRelay", or coding-agent remote control.
Install, configure, validate, or troubleshoot the community DSH Weixin ClawBot bridge that connects Tencent's official iLink channel to DeepSeek Harness. Use for phone-to-computer DSH setup, pairing, profile installation, session commands, updates, or compatibility checks; not for OpenClaw's own Weixin plugin or…
Use when changing anything in this repository - before running its suites, adding a tracked file, growing a size-baselined module, writing a regression test, judging a CI failure, or filing, claiming and labelling an issue.
Use when the user asks to control the living-room TV — turn it on or off, change volume or channel, open an app like Netflix or YouTube, switch inputs, type into a search field, check what is playing, or see what is on the screen — through the local LG TV MCP.