Wait, What? Re-explain the Last Message

What it does

The source is a deliberately small user-invoked correction: the previous explanation did not land. It asks for context, ASD-STE100 Simplified Technical English and the ubiquitous language in the project glossary. A multi-context repository uses its glossary map to find the relevant vocabulary. The skill is useful when an agent jumps directly to implementation details or relies on concepts the reader has not yet met. It changes the explanation, not the underlying decision or the project files.

When to use it

• Understand a technical recommendation that skipped its rationale.
• Replace an abstract architecture explanation with concrete project terms.
• Clarify the next action after a dense debugging update.

Step-by-step workflow

1. Identify the message or recommendation the user did not understand.
2. Load the relevant glossary context when one exists.
3. State the goal and the missing background before the technical detail.
4. Re-explain the actual behavior in short, direct sentences and familiar terms.
5. Make the next action clear and leave unresolved uncertainty visible.

Example request

Use wait-what on your last explanation of the import boundary. Start with what problem we are solving. Use the Invoice and Import Batch terms from our glossary. Explain who calls the boundary, what it returns and why that helps our duplicate-import bug. Keep necessary error cases. Do not change the design or edit code while explaining it.

Worked example

If the original message said to deepen an ingestion module, the revised explanation can name the web upload and scheduled importer as callers. It can explain that both submit an Import Batch and receive the same duplicate result, while address normalization stays inside the boundary. That gives the reader a concrete relationship before introducing the design term. Simpler words should preserve the failure behavior; saying only that the system becomes cleaner would leave the original gap unresolved.

What you get

A clearer version of the explanation, grounded in the current goal and project terms.

How to evaluate the result

• Check the revised explanation supplies the missing context.
• Verify glossary terms keep their established meanings.
• Confirm important constraints and uncertainty survived simplification.

What you need

The misunderstood message, enough surrounding context and any relevant GLOSSARY.md or GLOSSARY-MAP.md. A glossary is helpful but should not be fabricated.

Setup and activation

The publisher documents plugin setup for Claude Code, Codex and Copilot, and manual Agent Skills setup for Gemini CLI and other clients. Choose one distribution method per client to avoid duplicate skills. The engineering collection expects project-specific tracker, triage-label and document-location settings from setup-matt-pocock-skills. Keep referenced companion skills and files available. This catalogue review does not install or run them; scan the exact source before any later installation. Client tools, permissions and subagent support still need separate validation.

Limits and considerations

Requesting simplified technical English does not establish formal ASD-STE100 certification. Clarity is reader-dependent and may require a follow-up. The skill does not authorize code changes or resolve a disputed product choice.

Related workflows

• Use domain-modeling when the terms themselves are disputed.
• Use to-questionnaire if missing facts belong to another expert.

License and reuse

MIT at repository level (Copyright 2026 Matt Pocock). Preserve the copyright and permission notice when redistributing substantial source material; inspect any separately licensed dependencies or assets.

Further reading

• Reviewed SKILL.md (immutable commit)
• Publisher README: distributions and compatibility
• Reviewed MIT license