skills.rest
cruzanstx
cruzanstxCOMMUNITY
Explore all skills by this author →
GitHub

prompt-executor

Execute prompts from ./prompts/ against AI models with optional worktrees and verification loops.

6|Updated Jan 5, 2026
Search Tags:#verification#worktree#tmux#prompt#executor#prompt execution
One-click install
npx skills add https://github.com/cruzanstx/daplug --skill prompt-executor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-executor
Source: https://github.com/cruzanstx/daplug/tree/main/skills/prompt-executor
Command: npx skills add https://github.com/cruzanstx/daplug --skill prompt-executor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill executes prompts from the ./prompts/ directory against AI models (Claude, Codex, Gemini, Z.AI, etc.), with optional worktrees, tmux sessions, and verification loops to ensure tasks complete reliably.

Core Features & Use Cases

  • Execute prompts from ./prompts/ using multiple AI models
  • Optionally run in an isolated worktree or within a tmux session
  • Verification loop to retry until completion

Quick Start

Resolve a prompt (e.g., 123) from the prompts directory and run it with a selected model (e.g., codex). Enable a verification loop with --loop to auto-retry until a VERIFICATION_COMPLETE marker is reached.