How do I install the Wait What skill?

Run npx skillmds@latest add melodic-software/wait-what in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Wait What safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Wait What?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Wait What free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Wait What?

melodic-software (@melodic-software) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Wait What by melodic-software — Agent Skill

Name: Wait What
Author: melodic-software

Wait What

Stop. That last message did not land. Re-pitch it: back up as far as needed, add the context that was missing, write in ASD-STE100 Simplified Technical English, and use the project's own ubiquitous language. Type /discipline:wait-what the moment you notice you are skimming; only you know when you stopped following.

melodic-software 7a8ecaa 2 files · 5.7 KB Updated Sep 17, 2026

File contents

Wait. What?

Wait. I don't understand where you've got to here. Re-pitch that: back up as far as needed, give me the context I was missing, talk in ASD-STE100 Simplified Technical English (short sentences, one meaning per word, technical terms exact), and use the project's ubiquitous language. Read the nearest domain glossary or context map, per the project's own convention, when one exists; with none, plain technical English alone.

A declared species in this plugin: NOT a corrector

Every sibling corrector re-anchors a standing discipline through the re-anchor/audit/correct loop. This skill is a one-shot, user-fired communication repair: the human, the only party who can detect that a message did not land, fires it, and the re-pitch IS the repair. Nearest siblings, for routing: /discipline:tighten-your-output when the problem is too many words, and /discipline:mind-your-maxims when the standing cooperative-communication discipline itself needs re-anchoring; this skill repairs the one message that lost its reader.

Boundaries

Never model-invoked. disable-model-invocation: true is load-bearing: the model cannot detect that its reader stopped following, so an auto-fired re-pitch would be incoherent.
Re-pitch means re-ground, not compress. Full technical precision stays; the premise the reader was missing comes back. A re-pitch that is shorter and blunter, but no clearer, is the failure this skill exists to avoid.
No glossary is a no-op, not an error. The vocabulary half degrades silently; the register and missing-context halves always apply.
Excluded from batch sweeps. No discipline-batch tier on purpose: a sweep must never fire a repair only the human can call for.

---name: wait-whatdescription: Stop. That last message did not land. Re-pitch it: back up as far as needed, add the context that was missing, write in ASD-STE100 Simplified Technical English, and use the project's own ubiquitous language. Type /discipline:wait-what the moment you notice you are skimming; only you know when you stopped following.---# Wait. What?Wait. I don't understand where you've got to here. Re-pitch that: back up asfar as needed, give me the context I was missing, talk in ASD-STE100Simplified Technical English (short sentences, one meaning per word, technicalterms exact), and use the project's ubiquitous language. Read the nearestdomain glossary or context map, per the project's own convention, when oneexists; with none, plain technical English alone.## A declared species in this plugin: NOT a correctorEvery sibling corrector re-anchors a standing discipline through there-anchor/audit/correct loop. This skill is a one-shot, user-firedcommunication repair: the human, the only party who can detect that a messagedid not land, fires it, and the re-pitch IS the repair. Nearest siblings, forrouting:`/discipline:tighten-your-output` when the problem is too many words, and`/discipline:mind-your-maxims` when the standing cooperative-communicationdiscipline itself needs re-anchoring; this skill repairs the one message thatlost its reader.## Boundaries- **Never model-invoked.** `disable-model-invocation: true` is load-bearing: the model cannot detect that its reader stopped following, so an auto-fired re-pitch would be incoherent.- **Re-pitch means re-ground, not compress.** Full technical precision stays; the premise the reader was missing comes back. A re-pitch that is shorter and blunter, but no clearer, is the failure this skill exists to avoid.- **No glossary is a no-op, not an error.** The vocabulary half degrades silently; the register and missing-context halves always apply.- **Excluded from batch sweeps.** No `discipline-batch` tier on purpose: a sweep must never fire a repair only the human can call for.

Frequently asked questions