Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Opengui Coremate Install

ASecurity

Install the pinned OpenGUI v0.1.6 release into a DeepSeek Harness web profile on macOS. Use when the user asks to download, install, update, open, or verify OpenGUI for DSH.

1,800 stars
0 votes
0 copies
0 views
Added 8/30/2026
ai-agentsnodegitapi

Works with

cliapi

Security Analysis

A100/100

Scanned 8/30/2026

Install to Claude Code

$npx -y skills add Core-Mate/OpenGUI --skill opengui-coremate-install --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Opengui Coremate Install?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Opengui Coremate Install
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/core-mate-opengui-coremate-install/badge)](https://www.skillsdirectory.com/skills/core-mate-opengui-coremate-install)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: opengui-coremate-install
description: Install the pinned OpenGUI v0.1.6 release into a DeepSeek Harness web profile on macOS. Use when the user asks to download, install, update, open, or verify OpenGUI for DSH.
---

# Install OpenGUI

Install and verify the signed-off `v0.1.6` release without replacing unrelated DSH plugins or settings.

## Run the installer

1. Confirm the host is macOS. Do not improvise a Linux or Windows install.
2. Run `scripts/install-macos.sh` from this skill directory.
3. Report the installed package version, profile path, runtime URL, and whether an existing DSH process still needs a manual restart.

The script checks the host Node version, pins DSH to `0.1.0-rc.7`, downloads both the release tarball and checksum from the public GitHub Release, verifies SHA-256, installs only `dsh-coremate-mobile` into the `web` profile, and validates the package, bundle, Client entry, and `/opengui` command. GitHub authentication is not required.

The script installs a user LaunchAgent with `KeepAlive` so DSH returns after a crash or login. It may safely reload an instance already owned by that exact LaunchAgent. If port 3080 belongs to any other DSH process, preserve it: the installer writes the LaunchAgent but defers takeover until the next login. When DSH is not running, the script starts and verifies `http://127.0.0.1:3080`.

For uninstall requests, run `scripts/uninstall-macos.sh`. It removes only the matching plugin and LaunchAgent; settings, credentials, unrelated DSH instances, and caches remain intact.

## First-run handoff

Tell the user to add or select a DSH workspace, then connect and select an authorized phone. The workbench shows a screenshot immediately and prepares the live view in the background; do not ask the user to understand or approve the underlying phone-view component. Opening DSH, selecting phones, and manually opening mirrors do not require separate model setup. `/opengui <task>` prefers the current DSH conversation model. A model that explicitly supports images runs without a prompt; an unknown model asks once for permission to reuse it; an explicitly incompatible model enters the dedicated visual-model fallback. An empty `/opengui` only prints usage. The legacy `/coremate` alias remains available for compatibility.

The dedicated fallback still requires image input and tool calling. Its setup explains Base URL, API protocol, model ID, and API Key before asking for missing values.

For setup help, direct the user to `https://discord.gg/pqHHw7XgJ3`. The WeChat entry is an explicit non-scannable placeholder in this release, so do not invent or generate a QR code.

## Safety boundaries

- Preserve every unrelated profile dependency, bundle, setting, credential, session, and cache.
- Never expose or request an API Key outside the built-in DSH credential question.
- Never bypass a checksum mismatch or a DSH/Node compatibility failure.
- Never terminate an existing DSH process.
- Do not claim phone runtime validation unless an authorized Android device was actually connected and exercised.

Attribution

Core-MateCore-Mate
View sourceMore from Core-Mate →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →