Skip to content
TrustedSkillsbeta
Back to all skills

Wezterm

Listed
dicklesworthstone·vlatest·other

Wezterm provides a terminal emulator for Linux across platforms, offering seamless remote access and development workflows.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill wezterm -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

dicklesworthstone

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: apt.fury.io.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    raw.githubusercontent.comsource hostapt.fury.ioundeclared

    What it found

    • skills/wezterm/references/PERSISTENT-SESSIONS.md:62contacts apt.fury.io
      curl -fsSL https://apt.fury.io/wez/gpg.key | sudo gpg --dearmor -o /usr/share/keyrings/wezterm-fury.gpg

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 2 places.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

    What it found

    • skills/wezterm/SKILL.md:75remote script piped into a shell
      curl -fsSL https://raw.githubusercontent.com/Dicklesworthstone/misc_coding_agent_tips_and_scripts/main/wezterm-mux-tune.sh | bash
    • skills/wezterm/references/PERFORMANCE-TUNING.md:245remote script piped into a shell
      curl -fsSL https://raw.githubusercontent.com/Dicklesworthstone/misc_coding_agent_tips_and_scripts/main/wezterm-mux-tune.sh | bash

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • Pinned to a commit: passed

    Scanned dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations at 4d332440c3.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
4d332440c3
Manifest
skills/wezterm/SKILL.md
Scanned
4 files, 1,232 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill allows an AI agent to control and interact with WezTerm, a terminal emulator available on Linux across platforms. It provides access to WezTerm's command-line interface (CLI), enabling actions like listing panes and clients, managing tabs and workspaces, sending commands to running terminals, and launching new instances. This facilitates seamless remote access and development workflows within the WezTerm environment.

When to use it

  • Automating terminal tasks such as splitting panes and activating specific ones.
  • Managing multiple SSH connections or terminal sessions through Wezterm.
  • Launching applications or commands within a WezTerm tab or pane.
  • Listing available workspaces or domains (like SSH servers) configured in WezTerm.
  • Sending pre-defined commands to running terminals for scripting and automation.

Key capabilities

  • Pane Management: List, split, activate, and get the direction of panes.
  • Tab Management: Create new tabs, activate existing ones by index or relative position.
  • Command Sending: Send text (commands) to specific panes or the current pane.
  • Workspace & Domain Listing: Retrieve lists of configured workspaces and domains.
  • Zoom Control: Toggle and control pane zoom levels.
  • Launching WezTerm: Start new windows, connect to running mux servers, and launch with specified commands or directories.

Example prompts

  • "List all active panes in Wezterm."
  • "Split the current Wezterm pane horizontally and run htop in it."
  • "Activate the tab at index 0."
  • "Send 'ls -la' to the pane with ID <pane-id>."

Tips & gotchas

  • The CLI is located at /Applications/WezTerm.app/Contents/MacOS/wezterm or can be accessed by adding it to your system’s PATH.
  • Commands often require a pane-id, which needs to be obtained first using the "list" commands.
  • Newline characters (\n) are required at the end of text sent via send-text for commands to execute properly.