From great-operators
Dispatch one or more operator personas to review an existing process, system, operating plan, or post-mortem. Default panel for parallel review — Tim Cook (supply chain discipline), Andy Grove (output multiplier check), W. Edwards Deming (system vs. people). Override with --personas. Reads the project specification + the target file/directory + relevant adjacent context, produces a consolidated review with per-persona verdicts and a single highest-leverage recommendation. Output saves to operations/reviews/<slug>.md.
How this skill is triggered — by the user, by Claude, or both
Slash command
/great-operators:operators-ops-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Review an existing process, system, operating plan, or operating function.
Review an existing process, system, operating plan, or operating function.
Dispatches operator personas to review the artifact at <path>. Default panel runs three personas in parallel (Cook, Grove, Deming), each with a different lens. Output is a consolidated review — per-persona verdicts marked up, then a single recommended highest-leverage change.
Not for: individual performance reviews (use /operators-channel mccord instead — McCord has views on whether you should be doing them at all); tactical line-level metric tweaks; auto-generated documentation.
When this skill is invoked with a <path> argument and optional --personas:
Resolve the project root the same way /operators-project-init does. Verify CLAUDE.md exists or warn that the operations bible is missing.
Read the project specification:
CLAUDE.md, README.md, prior plans at operations/plans/, prior reviews at operations/reviews/, SOPs at operations/systems/.great-authors/project.md if cross-craft projectRead the target. <path> may be:
operations/plans/*.md)Read the target file(s) in full. Read adjacent context — sibling files, the operating data the plan references, the prior reviews that motivated the current plan. The reviewer can't review what they can't see.
Resolve the panel. If --personas is given (comma-separated), use those. Otherwise default panel:
tim-cook-operator — supply chain discipline, end-to-end execution, restraintandy-grove-operator — output multiplier, where is the leverage, OKR honestyw-edwards-deming-operator — system vs. worker, where the variation livesCommon alternative panels:
w-edwards-deming-operator + taiichi-ohno-operator — variation and flowcharlie-munger-operator + andy-grove-operator — invert and inflection pointpatty-mccord-operator + andy-grove-operator — adults and leverageben-horowitz-operator + andy-grove-operator — the struggle and the metricsam-walton-operator + herb-kelleher-operator — the customer and the culturetim-cook-operator + taiichi-ohno-operator — scale and flowDispatch the panel in parallel via the Agent tool. Each persona gets:
[→ replacement] for substitutions), Hand-off (if a different persona would serve better).Consolidate the parallel returns. The output is a single review file:
---
title: Operations review of <path>
slug: <slug>
panel: [<persona-1>, <persona-2>, <persona-3>]
created: YYYY-MM-DD
target: <path>
target_lines: <N>
---
# Operations review: <path>
## Per-persona verdicts
### <persona-1>
**Verdict:** <one sentence top-line reaction>
**Marked passages:**
- <quoted excerpt 1>
- <quoted excerpt 2>
- ...
**Hand-off:** <if a different persona would serve better; or omit>
### <persona-2>
[same structure]
### <persona-3>
[same structure]
## Where they agree
<1-3 points where the panel converges. The strongest signal — when independent reviewers with different lenses flag the same thing, it's almost certainly real.>
## Where they disagree
<1-2 points where the panel diverges. Often the most useful section — disagreement reveals the genuine trade-off the operator is making.>
## Highest-leverage change
<ONE recommendation. The single change that, if made, would make the operation meaningfully better. Not a list. The orchestrator's job is to pick the highest-leverage move; this skill picks it for them.>
## Suggested next step
<One of: implement the change, escalate to leadership, request a v2 from the plan author, run /operators-debate <topic> <persona-A> <persona-B> if the disagreement is structural, cross-dispatch great-minds:warren-buffett-persona if the question is strategic capital rather than execution.>
Save the review to operations/reviews/<slug>.md. Slug derived from the target path or from CLAUDE.md's Current plan: field.
Report:
📝 Saved to operations/reviews/<slug>.md (review of <path>, <word-count> words).
Panel: <persona-1>, <persona-2>, <persona-3>
Convergence: <one-line summary of the agreement>
Highest-leverage change: <one-line summary>
Next:
- Address the highest-leverage change
- Or run /operators-debate <topic> <a> <b> if the disagreement is structural
- Or cross-dispatch great-minds:warren-buffett-persona if the question is strategic capital
/agency-execute in great-minds.)/operators-ops-review on every weekly plan; use it for non-trivial changes where the consolidated lens is worth the dispatch cost.npx claudepluginhub sethshoultes/great-operators-plugin --plugin great-operatorsProvides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.