wait-what is a user-invoked skill for the moment you lose the thread of what the agent is saying. Typing it makes the agent re-pitch its last message: a little background first, then the point, in ASD-STE100 Simplified Technical English.
The agent reuses the ubiquitous language from the repository’s GLOSSARY.md, and follows GLOSSARY-MAP.md to the right glossary when the repository has more than one.
What You Get
- A slash command that fires a re-pitch on demand
- A re-explanation with background context added up front
- Wording drawn from your GLOSSARY.md, so terms match your codebase
Common Use Cases
- Recovering when an agent summary jumps ahead of what you know
- Re-reading a dense design proposal in shorter sentences
- Getting a second pass on a message full of project jargon
What Makes It Unique
The skill is a single instruction that combines three ideas: add context, write in ASD-STE100 Simplified Technical English, and use the project’s glossary. It stays tiny, costs nothing in always-loaded context because only you can invoke it, and ties the explanation to the shared language of the repository.
Under The Hood
The skill is one short SKILL.md with no scripts and no tool calls of its own. It sets disable-model-invocation, so the agent never fires it unprompted and its description stays out of context. When you run it, the instruction tells the agent to read GLOSSARY.md, follow GLOSSARY-MAP.md when several glossaries exist, and answer again.