Starlight CEO Review
Purpose
Test whether a proposal deserves to exist and whether its scope serves the intended user without transferring hidden cost, liability, or support burden to the operator.
When it fires
- A material feature, product, partnership, or platform investment needs a decision.
- The plan contains unverified market, cost, or adoption assumptions.
- Scope is either artificially narrow or expanding without evidence.
Inputs
- Target user, job to be done, and desired behavior change.
- Evidence of demand and alternatives already available.
- Revenue or mission hypothesis, operating cost, support owner, and constraints.
- Reversibility, legal/privacy implications, and success thresholds.
Workflow
- State the decision and the evidence required to make it.
- Test the user problem and the proposed mechanism separately.
- Compare build, integrate, partner, defer, and do-nothing options.
- Identify the smallest coherent scope that delivers the full promised outcome.
- Surface lifecycle cost: maintenance, support, security, compliance, and migration.
- Define leading indicators, stop conditions, and the next human decision.
Output contract
Return a verdict of build, revise, defer, or stop, followed by evidence, assumptions, strategic fit, alternatives, scope corrections, operating-owner obligations, metrics, and human gates.
Tools & MCP
Use current product evidence, customer research, financial assumptions, and primary market sources. Do not invent demand, ROI, partner approval, or “zero liability.”
Quality bar
- Ambition is connected to a concrete user outcome.
- Completeness means the promise works end to end, not that every imaginable feature ships.
- Human and agent effort estimates include uncertainty and operating cost.
- Irreversible or public decisions remain human-owned.
Example
Input: “Should we fork an agent runtime?”
Good output: compare a profile/adapter layer against a fork, price the maintenance and support obligations, define the evidence that would justify owning the runtime, and recommend the reversible path until that evidence exists.
Built on SIP — Starlight Intelligence Protocol
Vertical: starlight-agent-skills · portable capability layer
1---2name: starlight-ceo-review3description: Review a proposal from the accountable founder or product-owner perspective: user value, strategic fit, economics, evidence, sequencing, and human responsibility. Use when a plan needs a build/revise/defer decision or when ambition may be obscuring the actual outcome.4---56# Starlight CEO Review78## Purpose910Test whether a proposal deserves to exist and whether its scope serves the intended user without transferring hidden cost, liability, or support burden to the operator.1112## When it fires1314- A material feature, product, partnership, or platform investment needs a decision.15- The plan contains unverified market, cost, or adoption assumptions.16- Scope is either artificially narrow or expanding without evidence.1718## Inputs1920- Target user, job to be done, and desired behavior change.21- Evidence of demand and alternatives already available.22- Revenue or mission hypothesis, operating cost, support owner, and constraints.23- Reversibility, legal/privacy implications, and success thresholds.2425## Workflow26271. State the decision and the evidence required to make it.282. Test the user problem and the proposed mechanism separately.293. Compare build, integrate, partner, defer, and do-nothing options.304. Identify the smallest coherent scope that delivers the full promised outcome.315. Surface lifecycle cost: maintenance, support, security, compliance, and migration.326. Define leading indicators, stop conditions, and the next human decision.3334## Output contract3536Return a verdict of build, revise, defer, or stop, followed by evidence, assumptions, strategic fit, alternatives, scope corrections, operating-owner obligations, metrics, and human gates.3738## Tools & MCP3940Use current product evidence, customer research, financial assumptions, and primary market sources. Do not invent demand, ROI, partner approval, or “zero liability.”4142## Quality bar4344- Ambition is connected to a concrete user outcome.45- Completeness means the promise works end to end, not that every imaginable feature ships.46- Human and agent effort estimates include uncertainty and operating cost.47- Irreversible or public decisions remain human-owned.4849## Example5051Input: “Should we fork an agent runtime?”5253Good output: compare a profile/adapter layer against a fork, price the maintenance and support obligations, define the evidence that would justify owning the runtime, and recommend the reversible path until that evidence exists.5455---5657Built on SIP — Starlight Intelligence Protocol58Vertical: starlight-agent-skills · portable capability layer
frankxai