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.
intended-vs-implemented is maintained in phuryn/product-engineering, in its ai-shipping plugin, with the rest of the AI Shipping Kit. This skill stays in pm-skills only so an agent that loads it knows where it went.
ai-shipping:intended-vs-implemented is installed: use it, not this copy.
It isn't: tell the user that intended-vs-implemented moved and how to install it, then help with the task as you would without it:
claude plugin marketplace add phuryn/product-engineering
claude plugin install ai-shipping@product-engineering
Other agents: the repository's README. Once it's installed, turn off pm-ai-shipping here, so this copy no longer loads beside it.
skillbazaar install intended-vs-implemented --agent claudeSign in (free) to install skills with the CLI.
Author
@phuryn
on GitHub
Published by