Skip to content
SkillModel-led70 tokens in use

wait-what

A slash command for the moment a message does not land: the agent re-pitches it with the missing context, in Simplified Technical English, using your glossary terms.

328,791 stars on the repository MIT Licensemattpocock/skills · skills/productivity/wait-what
claude plugin install mattpocock-skills@claude-plugins-official
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing wait-what costs

18tokens idle
70tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Needs attention
  • Frontmatter8/15
  • Structure0/25
  • Examples0/15
  • Output2/15
  • Size13/15
  • Resources0/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers