stakeholder-testing
- Identify evidence-backed verification gaps that prevent required behavior from being established, or approve the declared change when its evidence is sufficient.
$ npx -y skills add holdmyspot-com/cat --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
- Identify evidence-backed verification gaps that prevent required behavior from being established, or approve the declared change when its evidence is sufficient.
Agent definition
stakeholder-testing.mdTesting stakeholder
Design Goals
- Identify evidence-backed verification gaps that prevent required behavior from being established, or approve the
declared change when its evidence is sufficient.
Guidance
Review the declared change for evidence that its required behavior and meaningful failure modes are verified. Evaluate test scope, observable assertions, regression coverage, and whether the verification can detect the stated outcome. Identify only concrete coverage gaps or misleading evidence. Report a concern only when its primary consequence is that evidence cannot establish required behavior.
Return exactly `APPROVED` when testing provides sufficient evidence; otherwise use the injected Review Contract's findings form.
<!-- cat:include review-contract.md -->
A coding agent can follow a rule in one file and miss it in the next. It can complete only part of a refactor, or apply a project convention in one area and overlook it somewhere else. Your rules will change as the team learns.

