Menu
Use when an engineering plan needs pressure-testing for architecture, complexity, data, risk, and operability.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Agent Brain /brain-brief: after intake, research, and grill have enough signal.
Agent Brain /brain-build: an implementation plan has a selected task and validation method.
Agent Brain /brain-design: a product brief needs ux or interaction design before planning.
Agent Brain /brain-eval: changing Agent Brain behavior or checking quality.
Agent Brain /brain-grill: the idea, brief, design, or plan has unresolved assumptions.
Agent Brain /brain-learn: after repeated success/failure, a tricky fix, or a shipped workflow.
| name | engineering-grill |
| description | Use when an engineering plan needs pressure-testing for architecture, complexity, data, risk, and operability. |
Lifecycle stage: CHALLENGE
Use before committing to implementation approach.
Do not use when this trigger is absent; choose the command or skill that owns the requested state, artifact, and verification gate.
| Shortcut | Rebuttal |
|---|---|
| "This is obvious." | Write the assumption and evidence. If you cannot, it is not obvious. |
| "We can do this later." | If the missing step changes the decision, do it now or state the risk. |
| "The user wants speed." | Reduce scope; do not skip the quality bar. |
| "This does not need verification." | Every important claim or behavior needs proof. |
Engineering Grill Report
Use templates/grill-report.md for a concise, auditable artifact with evidence, blockers, and next action so another agent can resume.
Trigger: an engineering plan needs pressure-testing before implementation. Action: compare scripts, checklists, human review, and agent workflows; require file scope, rollback, and validation proof. Output artifact: templates/grill-report.md with blockers and next action. Verification: cite architecture risks, data risks, operability checks, and smallest safe path.
A request says, "Add recurring workspace cleanup." The skill should compare a scheduled script, manual checklist, and agent-run cleanup; require file-scope, dry-run, rollback, and validation proof; then produce an engineering grill report that recommends the smallest safe implementation path instead of jumping straight to code.
