Installation
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "intended-vs-implemented" skill by following the instructions at https://skill123.me/install/intended-vs-implemented.
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/intended-vs-implemented.sh | bash
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 2 KBAbout this skill
Overview
The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy findings. Use when auditing AI-built code, reviewing access control against documented permissions, or checking whether a codebase matches its own documentation.
Source
- Repo: https://github.com/phuryn/pm-skills
- Path: pm-ai-shipping/skills/intended-vs-implemented
Evaluation
AI-evaluated 2026-09-03: Well-articulated audit method with clear evidence standards (quote the doc, cite the code, name attacker and victim) and explicit prompt-injection defenses, but it is a conceptual essay with no concrete commands, examples, or artifacts. Practically gated on a companion skill having already produced documented intent, so it is not drop-in for most users.