prompt-auditor-pass

Community

Audit and harden prompts before downstream use.

Authorblucsigma05
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It prevents wasted work by turning a first-draft prompt into a target-fit, failure-defended instruction set before another AI system uses it for review, evaluation, or structured analysis.

Core Features & Use Cases

  • Two-pass prompt construction: builds a draft prompt and then audits it specifically against the user’s stated goal rather than generic “best practices.”
  • Failure-mode defense: checks for specific risks like scope drift, hidden assumptions, capitulation, and under-specified outputs.
  • Hardened final deliverable: produces an improved prompt (and a required scoring matrix) that is usable by downstream workflows, including rubrics and system-prompt generation.

Quick Start

Use the prompt-auditor-pass skill to build an evaluation prompt for another model to audit a migration plan, then request the hardened Pass 3 deliverable.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: prompt-auditor-pass
Download link: https://github.com/blucsigma05/tbm-apps-script/archive/main.zip#prompt-auditor-pass

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.