Files
VincentShipsIt e20ffde84f Prune no-op text from skills, commands, and prompts
Remove text that doesn't change agent behavior (Matt Pocock's no-op test):
role-priming openers that restate the frontmatter description, "When to Use
This Skill" -> "When to Use", "Activate this skill when:" preambles, trailing
Skill Metadata provenance blocks, marketing adjectives
(comprehensive/world-class/robust), and justification clauses that state no
action. Dispatcher commands lose "instead of remembering which skill fits"
and "thin dispatcher" filler tails.

Frontmatter (name/description/license/etc.) left byte-for-byte untouched to
preserve discoverability. 155 SKILL.md + 11 commands + 1 prompt edited;
~247 net source lines removed. markdownlint passes; skill-sync validation
clean; marketplace bundles regenerated.
2026-06-29 15:02:50 +02:00

382 B

PRD Interview Prompt

Source: @trq212

Read this @SPEC.md and interview me in detail using the AskUserQuestionTool about literally anything: technical implementation, UI & UX, concerns, tradeoffs, etc. but make sure the questions are not obvious.

Continue interviewing me until it's complete, then write the spec to the file.