gilde

← All craftbooks

Executive-Level Review

Review and QAevalv2.0.8released 2026-09-05

A strategic, executive-level review of a plan or scope: challenge the premise, weigh alternatives, and score each dimension before committing — the 'should we even build this' p...

Steps

Entry step: evidence. Each step names the specialist role it wants; the full working prompt is expandable.

  1. Build the executive evidence basestrategy analystentry

    Extract the proposal, intended outcome, proof, assumptions, constraints, and missing decisions.

    Show working prompt
    Read the plan and the workspace material it cites. Restate the decision being requested, target user and outcome, timing, constraints, dependencies, and claimed evidence. Verify cited project facts directly. Separate evidence, inference, and unsupported assumption. Identify the decision owner, irreversible choices, and the cost of waiting. Do not score or recommend yet.

Observable handoff: write the completed result to `reviews/executive-evidence.md` in the project's artifacts drawer with `write_artifact`. Do not merely describe what the file would contain. Re-read it with `read_artifact` before finishing this phase and repair any incomplete sections.
  2. Challenge the premise and optionsexecutive strategist

    Compare the proposal with materially different ways to reach the outcome.

    Show working prompt
    Use `reviews/executive-evidence.md` to test whether the problem deserves action now and whether the proposal is the best vehicle. Develop at least three alternatives, including doing less or waiting. Compare value, confidence, time to learning, opportunity cost, reversibility, operating burden, security or compliance exposure, and failure mode. Identify which choice each key assumption favors and the cheapest evidence that would flip the ranking. Before working, open `reviews/executive-evidence.md` with `read_artifact`.

Observable handoff: write the completed result to `reviews/executive-options.md` in the project's artifacts drawer with `write_artifact`. Do not merely describe what the file would contain. Re-read it with `read_artifact` before finishing this phase and repair any incomplete sections.
  3. Write the executive reviewexecutive reviewer

    Deliver an evidence-anchored scorecard, verdict, and decision conditions.

    Show working prompt
    Write a decision-ready review using the evidence and options files. Score user value, strategic fit, evidence strength, feasibility, sequencing, reversibility, operating cost, and downside from 0 to 10; for each score cite the basis and say what would make it a 10. Choose exactly one mode verdict and explain the two or three decisive reasons. Recommend what to approve now, what to cut or defer, near-term validation, owners, and explicit go, pause, or stop conditions.

Observable handoff: write the completed result to `reviews/executive-level-review.md` in the project's artifacts drawer with `write_artifact`. Do not merely describe what the file would contain. Re-read it with `read_artifact` before finishing this phase and repair any incomplete sections.
  4. Evaluate the deliverablestrategy reviewer

    Independently grade the observable deliverable and route it to finish, repair, or user escalation.

    Show working prompt
    Review `reviews/executive-level-review.md`, `reviews/executive-evidence.md`, `reviews/executive-options.md` against every criterion below. Inspect the underlying evidence files named by the workflow; do not grade from the author's summary alone.

1. The review tests whether action is warranted, not merely how to execute the supplied plan.
2. Scores are individually justified by evidence and state what would improve them.
3. At least three materially different alternatives, including doing less or waiting, are compared.
4. Opportunity cost, reversibility, operating burden, and credible failure modes influence the recommendation.
5. The allowed verdict follows from the scorecard and has explicit approval, deferral, and stop conditions.
6. Unknowns remain visible and no unsupported fact is presented as evidence.

Open `reviews/executive-level-review.md`, `reviews/executive-evidence.md`, `reviews/executive-options.md` with `read_artifact`. Write the evidence-backed review to `reviews/executive-level-review-evaluation.md` in the artifacts drawer with `write_artifact`. Give each criterion a PASS or FAIL with a concrete path, excerpt, measurement, or observed behavior. End with exactly `Verdict: PASS` or `Verdict: REVISE`. Then use `advance_task_step` for the active task: PASS routes to `finish`; REVISE routes to `repair` for review rounds 1 through 2, and the 3th REVISE routes to `needs-user`. Never route to finish while a criterion is unmet.
  5. Repair the deliverableexecutive reviewer

    Fix only the concrete gaps from the latest independent review.

    Show working prompt
    Read `reviews/executive-level-review-evaluation.md` with `read_artifact` and repair every failed criterion in `reviews/executive-level-review.md`, `reviews/executive-evidence.md`, `reviews/executive-options.md`. Make changes on each file's declared surface (`write_artifact` for artifact inputs, `write_file` for workspace inputs), not in task notes or a reply. Preserve evidence that already passed. Re-run or re-check anything the reviewer found unproven. Ensure `reviews/executive-level-review.md` is genuinely updated this turn so the repair is observable, then hand it back for independent evaluation.
  6. Finishproject lead

    All deterministic and reviewer criteria passed.

    Show working prompt
    The independent review passed. Read `reviews/executive-level-review-evaluation.md` with `read_artifact`, then use `write_task_note` to record a concise DONE summary with the final deliverable paths (`reviews/executive-level-review.md`, `reviews/executive-evidence.md`, `reviews/executive-options.md`) and the evidence that each acceptance criterion passed. Report DONE without starting new work.
  7. Escalate unresolved concernsproject lead

    The bounded repair loop ended without a defensible pass.

    Show working prompt
    The deliverable did not pass after 3 review rounds. Do not claim success. Read `reviews/executive-level-review-evaluation.md` with `read_artifact`, then use `write_task_note` to record DONE_WITH_CONCERNS: the unmet criteria, what was attempted, the affected paths, and the smallest user decision or missing input needed to continue.

Triggers

Phrases that suggest this craftbook to a crew.

Source

View this craftbook on GitHub · MIT license