WTF

Use this skill when the immediately previous response from an LLM was unclear, too dense, or difficult to follow.

Procedure

1. Read the immediately previous LLM response.
2. If no previous LLM response exists, this skill was started in error. Say that there is nothing to re-explain. Ask which response or text to explain. Stop. Do not invent, quote, or guess a previous response.
3. If the response uses domain terms, look for CONTEXT.md, GLOSSARY.md, UBIQUITOUS_LANGUAGE.md, and files matching *.glossary.yml in the current project.
4. Use those files to select the canonical terms and meanings.
5. Re-explain the previous response with a clearer structure and simpler wording.
6. Preserve every detail that changes how the response should be understood, including each condition, causal link, uncertainty, technical identifier, value, scope, conclusion, and relationship.
7. Attribute operational actions to the previous response so the explanation cannot read as a new task.
8. Do not perform a new task.
9. Do not introduce information from the terminology files that the previous response did not contain.

Writing Rules

Write in a style inspired by ASD-STE100 Simplified Technical English.