Define and document the core-plugin evaluation model and quality metrics

## Context
> For the core plugin/skills we own. We will continuously invest in refining the evaluation metrics to answer the following questions:
> - What user prompts do we expect to trigger the skill
> - What do we expect the LLM to do with the skill
> - With the skill, does the LLM accomplish the goal meeting the expectations
> - Without the skill, does the LLM accomplish the goal meeting the expectations

## Scope
- Define the evaluation model covering the four questions above.
- Document quality metrics used to measure core-plugin skill quality.

## Acceptance criteria
- A documented, repeatable evaluation model + metrics exists for the core plugin.

No files, tests, or entry points are named. Start by reviewing the core plugin/skills context and map the four stated questions into a repeatable evaluation model with quality metrics. Done means the model and metrics are documented and can be applied consistently to core-plugin skills.

Written by the indexing model from the issue text.