generate-prompts

Scan codebases, verify findings, and generate harness prompts.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/junnv93/equipment_management_system --skill generate-prompts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: generate-prompts
Source: https://github.com/junnv93/equipment_management_system/tree/main/.claude/skills/generate-prompts
Command: npx skills add https://github.com/junnv93/equipment_management_system --skill generate-prompts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Scan codebases to identify actionable issues, verify findings, and generate harness prompts that can be archived once completed, ensuring a credible, repeatable prompt-generation workflow.

Core Features & Use Cases

  • Load existing prompts from .claude/skills/harness/references/example-prompts.md and track statuses (completed, in-progress, pending).
  • Run parallel analyses across backend, frontend, and infra, reporting findings to generate prompts for each item.
  • Verify findings with Read/Grep style checks, then write prompts, archive completed items, and update the harness reference file for future iterations.

Quick Start

Scan a repository, verify findings, generate harness prompts, and archive completed items for future reference.

Frequently Asked Questions about generate-prompts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate generating verified prompts from codebase scans?

To automate prompt generation, scan your codebase to identify actionable issues, verify findings, and generate harness prompts that can be archived once completed, ensuring a repeatable workflow.

What is a harness prompt and when do I need it for repository scanning?

A harness prompt is a verified instruction generated from codebase findings. You need it when scanning repositories to identify actionable issues and track them across pending, in-progress, or completed statuses.

How do I run parallel codebase analyses across backend, frontend, and infra?

Run parallel agent analyses across backend, frontend, and infra layers to report findings, verify them with checks, and generate individual prompts for each identified item in your codebase.

Does the prompt generation workflow verify codebase findings before writing?

Yes, the workflow verifies findings using Read and Grep style checks before writing prompts. It then archives completed items and updates the harness reference file for future iterations.

What's the best way to track existing prompt statuses in a codebase?

The best way to track prompt statuses is by loading existing prompts from your harness reference file, categorizing them as completed, in-progress, or pending, and archiving finished items.

Can I update a harness reference file automatically after archiving completed items?

Yes, after archiving completed items from your codebase scans, the workflow automatically updates the harness reference file to ensure continuous improvement for future prompt-generation iterations.