agentleFS
ScinoScino/fstack/skills/ceo-review/SKILL.md

ceo-review

Skill18 starsChanged 53 days agoMITView on GitHub

Founder/CEO strategic plan review. Calibrates scope across 4 modes (Scope Expansion, Selective Expansion, Hold Scope, Scope Reduction) to challenge premises, eliminate bloat, or discover the 10-star product experience. Use for /ceo-review, "review scope", or strategic plan review.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before committing weeks of engineering effort to an implementation plan, the founder must ask: Are we building the right scope?

    line 9
  2. Very specific:

    When invoking /ceo-review [mode], select one of the following postures:

    line 27
  3. Distinctive:

    No new features, no scope creep.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CEO Review (Strategic Scope Calibration)

Before committing weeks of engineering effort to an implementation plan, the founder must ask: Are we building the right scope?

Are we thinking too small and missing the breakthrough product experience? Or are we overcomplicating an MVP that should ship by Friday?

ceo-review evaluates an implementation plan or feature proposal across 4 distinct strategic postures.


When to Invoke

  • You have an engineering implementation plan or RFC ready to build.
  • You feel unsure whether the scope is too broad or too conservative.
  • You want to pressure-test the user experience before writing code.

The 4 Scope Modes

When invoking /ceo-review [mode], select one of the following postures:

1. SCOPE_EXPANSION (The 10-Star Product)

Inspired by Brian Chesky's Airbnb product design framework.

  • Question: "What would make a customer tell 10 friends about this?"
  • Ignores conventional constraints for a moment to imagine the magical version:
    • A 5-star experience: It works and doesn't crash.
    • A 7-star experience: It anticipates what the user needs before they click.
    • A 10-star experience: The problem is solved automatically with zero manual effort.
  • Identifies which pieces of the 10-star vision can be built today with AI agent leverage.

2. SELECTIVE_EXPANSION (Hold the Core, Elevate the Key Detail)

  • Holds 90% of the scope fixed to ensure speed.
  • Cherry-picks the single high-leverage delight factor that turns a boring utility into a beloved product (e.g. instant keyboard shortcut, zero-latency optimistic update, beautiful CLI progress display).

3. HOLD_SCOPE (Maximum Execution Rigor)

  • Freezes the boundaries.
  • No new features, no scope creep.
  • Focuses 100% on bulletproof edge cases, rock-solid tests, error boundaries, and unslop.

4. SCOPE_REDUCTION (The Friday Ship)

  • Question: "What can we cut so this ships by tomorrow afternoon?"
  • Identifies unnecessary tables, secondary settings, complex configuration options, and premature generalizations.
  • Strips the plan to its irreducible core: 1 input, 1 action, 1 output.

The Review Deliverable

# 🏛️ CEO Strategic Review: [Project / Feature Name]
**Selected Posture**: [SCOPE_EXPANSION | SELECTIVE_EXPANSION | HOLD_SCOPE | SCOPE_REDUCTION]

### 🎯 Strategic Assessment
[2-3 sentences diagnosing whether the current plan is over-engineered or under-ambitious]

### ✂️ Scope Adjustments
- **Cut**: [Feature / complexity to remove immediately]
- **Keep**: [Core non-negotiables]
- **Add / Elevate**: [The single detail that makes it remarkable]

### ⚖️ Tradeoff Matrix
| Dimension | Current Plan | Recommended Plan | Business Impact |
|---|---|---|---|
| Time to Ship | 2 Weeks | 3 Days | 4x faster feedback loop |
| Complexity | 4 Models, 6 Tables | 1 File, 1 SQLite Table | Zero migration overhead |
| User Delight | 6/10 (Functional) | 9/10 (Magical) | High word-of-mouth potential |

### 🚀 Next Action
Hand the calibrated plan to `/engineer-mode` for flawless engineering execution.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.