Skip to content
Back to skills

Ztx10 Windows Cli Operations

ASecurity

Operate on Windows PowerShell with Codex CLI and filesystem-safe paths.

  • 14 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
ai-agentsshell

Works with

  • cli

Security analysis

A100/100

Scanned November 7, 2026

npx -y skills add Realjustawall/Perfect-AI --skill ztx10-windows-cli-operations --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ztx10 Windows Cli Operations?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ztx10 Windows Cli Operations
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/realjustawall-ztx10-windows-cli-operations/badge)](https://www.skillsdirectory.com/skills/realjustawall-ztx10-windows-cli-operations)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ztx10-windows-cli-operations
description: "Operate on Windows PowerShell with Codex CLI and filesystem-safe paths."
---
# Windows Cli Operations

**Intent:** Operate on Windows PowerShell with Codex CLI and filesystem-safe paths.

## Execution protocol
1. Check codex executable installed/authenticated. Require tangible evidence, a clear owner, and a pass/fail check.
2. Use subprocess argument arrays not shell injection. Require tangible evidence, a clear owner, and a pass/fail check.
3. Use read-only audit sandbox. Require tangible evidence, a clear owner, and a pass/fail check.
4. Store outputs outside project. Require tangible evidence, a clear owner, and a pass/fail check.
5. Allow mock tests offline. Require tangible evidence, a clear owner, and a pass/fail check.

## Inputs/Outputs
Input: site profile, approved brand, evidence path, task brief and allowed capabilities. Output: strict machine-readable report or orchestration plan with selected roles and reasons.

## Safety and correctness
- No existing skills may be removed. No third-party repository is executed by default.
- No edits until a human explicitly authorizes a separate fix flow.
- Always report not-run tests and confidence. Do not inflate the number of independent agents from identical prompts.
- Verify the implementation and its regression tests before completion.

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.