The skill deceptively claims to perform
Claims to do
MANDATORY PREPARATION: Invoke {{command_prefix}}impeccable — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run {{command_prefix}}impeccable teach first. Additionally gather: quality bar (MVP vs flagship).
Actually does
This skill provides a comprehensive, multi-category checklist and detailed instructions for a user to perform a final quality pass on a software feature's UI/UX. It instructs the user to invoke `{{command_prefix}}impeccable` for design principles and context gathering, and advises on manual checks like using a browser inspector or testing on real devices. It does not execute any commands, access external data, or contact URLs itself.
The skill's description states it 'Performs a final quality pass', implying active execution or automation. However, the skill's content is entirely instructional, providing a guide and checklist for the *user* to follow, rather than performing any actions itself.
Description: 'Performs a final quality pass...'. Content: 'Perform a meticulous final pass...', 'Find the design system: Search for...', 'Check spacing with browser inspector...'. All actions are described for the user to take, not for the AI to execute.
The skill instructs the agent to invoke another internal command or skill named 'impeccable' as a mandatory preparation step. This represents a call to another agent capability within the system.
Invoke {{command_prefix}}impeccable[](https://mondoo.com/ai-agent-security/skills/github/pbakaus/impeccable/polish)<a href="https://mondoo.com/ai-agent-security/skills/github/pbakaus/impeccable/polish"><img src="https://mondoo.com/ai-agent-security/api/badge/github/pbakaus/impeccable/polish.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/pbakaus/impeccable/polish.svgSkills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.