CEO Review
A structured, leadership-level review of one plan, proposal or roadmap item.
Core principle: choose a stance before reading the plan in detail. A review
that tries to expand, hold and cut at once produces confused output. The stance
governs every dimension that follows, so it is declared first and never mixed
within one review.
When to use
- Setting or revisiting roadmap priorities for a quarter.
- Reviewing a significant new bet, a pivot, or an investment proposal.
- A resourcing call large enough that getting it wrong costs weeks, not hours.
- A plan has been presented and needs a rigorous, structured response.
When not to use
- Tactical execution feedback: comment on the work directly.
- Demand is still unproven and nothing is drafted:
strategic-brief first, then
this review.
- Several candidates need ordering:
rice-prioritization.
- A marketing campaign:
campaign-brief. Finished creative: brand-review.
Where the company context comes from
Strategic Fit and Competitive Moat are judged against what the company is
betting on, so the review needs that context and must not invent it.
This repository's agent configuration should have been provided to you (the
## Agent skills block pointing at docs/agents/). If it is missing, use the
defaults below and suggest the user run the setup-aclarify-skills skill.
- Strategy source. In order: a strategy, positioning or roadmap document the
user names; one in the conventions folder named in
docs/agents/workspace.md
(default: none); what the user pasted into the conversation.
- With none of these, ask the user for the minimum: the two or three core
bets the company is making now, and its current stage or constraint. Ask the
user, using your structured-question tool if you have one; otherwise list the
questions numbered in plain text and stop until they reply. If they would
rather you proceed, run on the plan alone and mark Strategic Fit and
Competitive Moat as not checked against stated strategy.
- Issue tracker (
docs/agents/issue-tracker.md): where the summary is posted
when the plan lives in an issue. Default: none configured.
Step 1: select the stance
| Stance |
Strategic context |
What it asks |
| EXPAND |
Growth mode |
What is the 10x version? What would we add with 3x the resources? |
| CHERRY-PICK |
Constrained resources |
Which 20% of this delivers 80% of the value? |
| HOLD |
Execution rigour |
Add nothing; pressure-test everything already in scope. |
| CUT |
Over-committed |
What do we kill without losing the core bet? |
The stance is a strategic choice, so it belongs to the user. If they named one,
use it. If not, propose the one the context points to, with a one-line reason,
and ask them to confirm or pick another before you continue.
Declare it at the top of the review:
Stance: HOLD. We are executing the current roadmap without additions. This
review pressure-tests execution quality, not scope.
Step 2: review across eight dimensions
Write two to five sentences per dimension. Be direct: what is strong, what is
weak, what is missing. Where a judgment rests on context you could not check,
say so in that dimension.
- Strategic fit. Does this advance the core bets, or is it adjacent or a
distraction? Is it agreed as a priority, or driven by recency or a single
voice?
- Market timing. Why now? What happens if it ships six months later? What
is the window, and is there evidence it is real (competitor moves, customer
pressure, regulatory change)?
- Resource requirement. The realistic cost in people's time, cash and
attention. Is the estimate anchored to comparable past work, or optimistic?
What are the hidden costs: maintenance, iteration, dependencies?
- Competitive moat. Does this create a durable advantage, or is it easily
copied? If a well-funded competitor launched the same thing next quarter,
what would we have that they would not?
- Reversibility. A two-way door can be undone cheaply; a one-way door
(architecture, public commitments, vendor lock-in) cannot. One-way doors
demand more rigour up front.
- Measurability. The specific metric and threshold at 30 and 90 days. With
no metric the initiative cannot be evaluated, and that is a blocking concern.
- Dependencies. Everything else that must be true: other teams, third-party
tools, data, a change in customer behaviour. Which is most likely to slip,
and what happens to the initiative if it does?
- Risk concentration. The single most likely failure mode. Not a list:
name the one thing the post-mortem would blame.
Step 3: stance-specific output
EXPAND
- The top three additions that would multiply the initiative's value.
- The resources each needs.
- Which fit the current timeline and which belong to a later phase.
CHERRY-PICK
- The highest-return 20% of scope, named as specific deliverables, not
categories.
- What to defer to a second version, and why.
- The effort this saves against the full scope.
HOLD
- The three highest-risk execution assumptions in the current scope.
- The pressure-test questions the team must answer before proceeding.
- Leading indicators to watch in the first two weeks.
CUT
- What to eliminate, named as specific features or workstreams.
- The initiative restated at its minimal scope.
- Confirmation that the core bet survives the cuts.
Step 4: prioritized open questions
Close with at most five questions that must be resolved before proceeding,
ranked by urgency. Each names who must answer and by when.
## Open questions (prioritized)
1. [Question] - Owner: [name or role] - Needed by: [date or milestone]
2. [Question] - Owner: [name or role] - Needed by: [date or milestone]
Step 5: deliver the review
Write the full review where the plan lives, or where the user asks: beside the
planning document, or as a file in the scratch folder (docs/agents/workspace.md;
default .scratchpad/, git-ignored) if they want it kept out of tracked files.
If the plan lives in an issue in the configured tracker, also post a short
summary there: the stance, the top concern from each dimension, and the first
open question. With no tracker configured, give the user that summary to send
to whoever needs it.
1---2name: ceo-review3description: >-4 Executive review of a drafted plan, proposal or roadmap item: commits to one stance5 (EXPAND, CHERRY-PICK, HOLD or CUT), judges the plan on eight business dimensions, and6 returns stance-specific scope changes plus at most five ranked open questions. Use when7 a plan is on the table and needs a hard leadership read: quarterly roadmap priorities,8 a significant new bet, a pivot, or a large resourcing call. Do NOT use to test whether9 demand exists before anything is drafted (use `strategic-brief`), to rank several10 initiatives against each other (use `rice-prioritization`), to review a marketing11 campaign (use `campaign-brief`), or to audit finished creative (use `brand-review`).12license: MIT13argument-hint: '[the plan to review] [EXPAND | CHERRY-PICK | HOLD | CUT]'14metadata:15 source: https://skillmd.com/skills/spencermarx/ceo-review16---1718# CEO Review1920A structured, leadership-level review of one plan, proposal or roadmap item.2122**Core principle:** choose a stance before reading the plan in detail. A review23that tries to expand, hold and cut at once produces confused output. The stance24governs every dimension that follows, so it is declared first and never mixed25within one review.2627## When to use2829- Setting or revisiting roadmap priorities for a quarter.30- Reviewing a significant new bet, a pivot, or an investment proposal.31- A resourcing call large enough that getting it wrong costs weeks, not hours.32- A plan has been presented and needs a rigorous, structured response.3334## When not to use3536- Tactical execution feedback: comment on the work directly.37- Demand is still unproven and nothing is drafted: `strategic-brief` first, then38 this review.39- Several candidates need ordering: `rice-prioritization`.40- A marketing campaign: `campaign-brief`. Finished creative: `brand-review`.4142## Where the company context comes from4344Strategic Fit and Competitive Moat are judged against what the company is45betting on, so the review needs that context and must not invent it.4647This repository's agent configuration should have been provided to you (the48`## Agent skills` block pointing at `docs/agents/`). If it is missing, use the49defaults below and suggest the user run the `setup-aclarify-skills` skill.5051- **Strategy source.** In order: a strategy, positioning or roadmap document the52 user names; one in the conventions folder named in `docs/agents/workspace.md`53 (default: none); what the user pasted into the conversation.54- **With none of these,** ask the user for the minimum: the two or three core55 bets the company is making now, and its current stage or constraint. Ask the56 user, using your structured-question tool if you have one; otherwise list the57 questions numbered in plain text and stop until they reply. If they would58 rather you proceed, run on the plan alone and mark Strategic Fit and59 Competitive Moat as **not checked against stated strategy**.60- **Issue tracker** (`docs/agents/issue-tracker.md`): where the summary is posted61 when the plan lives in an issue. Default: none configured.6263## Step 1: select the stance6465| Stance | Strategic context | What it asks |66|---|---|---|67| **EXPAND** | Growth mode | What is the 10x version? What would we add with 3x the resources? |68| **CHERRY-PICK** | Constrained resources | Which 20% of this delivers 80% of the value? |69| **HOLD** | Execution rigour | Add nothing; pressure-test everything already in scope. |70| **CUT** | Over-committed | What do we kill without losing the core bet? |7172The stance is a strategic choice, so it belongs to the user. If they named one,73use it. If not, propose the one the context points to, with a one-line reason,74and ask them to confirm or pick another before you continue.7576Declare it at the top of the review:7778> Stance: HOLD. We are executing the current roadmap without additions. This79> review pressure-tests execution quality, not scope.8081## Step 2: review across eight dimensions8283Write two to five sentences per dimension. Be direct: what is strong, what is84weak, what is missing. Where a judgment rests on context you could not check,85say so in that dimension.86871. **Strategic fit.** Does this advance the core bets, or is it adjacent or a88 distraction? Is it agreed as a priority, or driven by recency or a single89 voice?902. **Market timing.** Why now? What happens if it ships six months later? What91 is the window, and is there evidence it is real (competitor moves, customer92 pressure, regulatory change)?933. **Resource requirement.** The realistic cost in people's time, cash and94 attention. Is the estimate anchored to comparable past work, or optimistic?95 What are the hidden costs: maintenance, iteration, dependencies?964. **Competitive moat.** Does this create a durable advantage, or is it easily97 copied? If a well-funded competitor launched the same thing next quarter,98 what would we have that they would not?995. **Reversibility.** A two-way door can be undone cheaply; a one-way door100 (architecture, public commitments, vendor lock-in) cannot. One-way doors101 demand more rigour up front.1026. **Measurability.** The specific metric and threshold at 30 and 90 days. With103 no metric the initiative cannot be evaluated, and that is a blocking concern.1047. **Dependencies.** Everything else that must be true: other teams, third-party105 tools, data, a change in customer behaviour. Which is most likely to slip,106 and what happens to the initiative if it does?1078. **Risk concentration.** The single most likely failure mode. Not a list:108 name the one thing the post-mortem would blame.109110## Step 3: stance-specific output111112**EXPAND**113- The top three additions that would multiply the initiative's value.114- The resources each needs.115- Which fit the current timeline and which belong to a later phase.116117**CHERRY-PICK**118- The highest-return 20% of scope, named as specific deliverables, not119 categories.120- What to defer to a second version, and why.121- The effort this saves against the full scope.122123**HOLD**124- The three highest-risk execution assumptions in the current scope.125- The pressure-test questions the team must answer before proceeding.126- Leading indicators to watch in the first two weeks.127128**CUT**129- What to eliminate, named as specific features or workstreams.130- The initiative restated at its minimal scope.131- Confirmation that the core bet survives the cuts.132133## Step 4: prioritized open questions134135Close with at most five questions that must be resolved before proceeding,136ranked by urgency. Each names who must answer and by when.137138```markdown139## Open questions (prioritized)1401411. [Question] - Owner: [name or role] - Needed by: [date or milestone]1422. [Question] - Owner: [name or role] - Needed by: [date or milestone]143```144145## Step 5: deliver the review146147Write the full review where the plan lives, or where the user asks: beside the148planning document, or as a file in the scratch folder (`docs/agents/workspace.md`;149default `.scratchpad/`, git-ignored) if they want it kept out of tracked files.150151If the plan lives in an issue in the configured tracker, also post a short152summary there: the stance, the top concern from each dimension, and the first153open question. With no tracker configured, give the user that summary to send154to whoever needs it.