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
  • Authors
  • 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.

ProTermsPrivacyRefunds
Back to skills

Lcu

ASecurity

Control Linux desktop windows through the original Codex computer-use runtime.

5 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsjavascriptjavaapidocumentation

Works with

api

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add 0xpolarzero/lcu --skill lcu --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Lcu?

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

Security grade badge for Lcu
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/0xpolarzero-lcu/badge)](https://www.skillsdirectory.com/skills/0xpolarzero-lcu)

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

Files
SKILL.md
---
name: lcu
description: Control Linux desktop windows through the original Codex computer-use runtime.
---

Use LCU's `js` and `js_reset` tools. JavaScript state persists between calls.

Before the first call, read the complete original Linux computer-use guide at `references/upstream/cua/docs/tinysky-alt-core-cua-repl.md`, the Linux launcher description at `references/upstream/cua-repl/instructions/linux/description.md`, and the native Linux guide at `references/upstream/sky/linux/SKILL.md`. LCU setup populates these paths beside the generated local skill; the release template does not contain copied upstream documents. LCU uses the unified original `cua` entrypoints and the capability-specific guidance returned by its runtime.

On first use or after reset, make one documented entrypoint call by itself, normally `await cua.getState()`. Do not combine it with other API calls, waits, or snapshots. Read the returned tool descriptions, policies, and inventory before continuing. After context compaction, call `await cua.rewriteDocumentation()` by itself and reread the returned guidance.

Use the original `cua` entrypoints and only capabilities shown by the connected provider and effective policy. For native Linux windows, target an exact observed window ID.

This skill's references are generated from the selected installed Linux application during setup. If they are missing, run `lcu setup` on the Linux machine that hosts the agent.

Attribution

0xpolarzero0xpolarzero
View sourceMore from 0xpolarzero →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

695601 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.

691 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 →