retro Eval report.

Validation plan

What the agent should do next

1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. 2Install in an isolated workspace or sandbox with no production secrets available.
3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
5. 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when

Conditions that require another skill

• teams that need a vendor-supported SLA
• production agents without a repository review
• SKILL.md does not explicitly define safe operating boundaries, such as clarifying that sprint data and user-provided files must be treated as untrusted data and never as instructions.
• The skill implies it can analyze sprint performance and velocity, but it does not state what to do when that data is unavailable or incomplete, which could lead to hallucinated metrics.
• The action item template includes Owner and Deadline placeholders but does not explicitly warn against inventing owner names or deadlines when not provided by the user.
• Quality score needs review