Proactive Clarification Discipline skill

[Tim (Timziito)]

Decides when an ambiguous request is worth one focused clarifying question versus a stated, reasonable default, avoiding both silent wrong guesses and stalling on twenty-questions before starting work.

[Copilot]

Pull request overview

Adds a new submission to the CAT Agent Skills gallery: “Proactive Clarification Discipline”, a general-purpose skill that guides an agent on when to ask a single clarifying question vs. proceed with an explicit, reasonable default.

Changes:

• Introduces a new SKILL.md defining a decision test and guardrails for clarification vs. assumptions.
• Adds a human-facing README.md describing intent and usage context.
• Adds metadata.json to register the skill in the gallery (platforms/tags/author/version).

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
submissions/proactive-clarification-discipline/SKILL.md	New skill instructions and guardrails for “ask vs assume” decisions.
submissions/proactive-clarification-discipline/README.md	Human-facing overview and positioning of the skill.
submissions/proactive-clarification-discipline/metadata.json	Gallery metadata (name/description/platforms/tags/author/version/dates).

[Copilot]

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated no new comments.

[Adriana Trujillo (adrianatruji)]

Thanks for the thinking here, Tim (@Timziito). The "ask vs. proceed" judgment is a real one and and the preference for concrete options over open questions is a good way of thinking about it.
However, we will hold this one for now as this is mostly conversational conduct with no discrete trigger, which puts it in system-behaviour territory rather than agent skills. We have steered away from these general agent-quality skills, as these make more sense baked into the agent instructions and expected overall behaviour.
A different angle worth considering: Is there a specific business process where clarification is high stakes, or the direction of the multi-turn conversation affects significantly the output? That logic makes sense to be baked into a skill.
This actually makes great material for agent-authoring guidance! Thanks again.