Product brief
Skill denelwu-GH/exocrew/plugins/exocrew/skills/product-brief
Zero coding experience? Give Codex an AI delivery crew that turns ideas into working, tested, releasable software with guardrails, browser QA, rollback, and production closure.
npx -y skills add denelwu-GH/exocrew --skill product-briefAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 22 days oldThe repository was created 22 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Turn an idea, feature request, workflow problem, or vague AI-building prompt into a concise, value-led product brief with users, current state, scope, non-goals, page or process logic, abnormal cases, measurable acceptance criteria, alternatives, and ROI. Use before implementation when the desired outcome or business rules are incomplete, contradictory, or likely to cause rework.
SKILL.md
3.6 KB, 667 tokens by cl100k_base, as published. Nobody here has run it
ExoCrew Product Brief
Purpose
Convert intent into an implementable product contract. Optimize for clarity and decision quality, not document length.
Establish value first
Answer:
- Who has the problem?
- What job are they trying to complete?
- What happens today?
- Why is the gap costly or risky?
- What measurable outcome should change?
If the motivation is weak or the proposed path is not the shortest route to value, say so before designing the feature.
If the object being changed, the business consequence, or the decision owner is still unknown, produce a decision brief and stop before implementation. Do not turn a convenient assumption into a durable product rule.
For an existing system, also identify whether the desired outcome is a behavior-preserving port, internal refactor, technical modernization, production replacement, or reusable/public extraction. These modes have different compatibility, cost, and evidence requirements. Route the accepted choice to $system-modernization.
Build the brief
Use this order:
Outcome and value
Users and permissions
Current state
Gap
Scope
Non-goals
Workflow or page logic
Actions and state transitions
Abnormal and boundary cases
Data and field semantics
User-facing copy
Acceptance criteria
Dependencies and rollout
Alternative and tradeoff
Modernization mode and maintenance horizon, when applicable
Load references/brief-template.md when producing a reusable artifact.
Design the complete path
For each page, process, or action, define:
- entry condition
- information shown
- primary and secondary actions
- disabled or blocked reasons
- success feedback
- visible failure feedback
- recovery path
- state before and after
- authorization and audit needs
Do not stop at the happy path. Use references/risk-prompts.md to expose common omissions.
Keep rules testable
Replace vague words such as “fast,” “large,” “recent,” “complete,” or “enterprise-ready” with observable rules. Define dates, thresholds, ownership, ordering, idempotency, and conflict behavior where they matter.
Each acceptance criterion should identify:
- starting state
- user action or event
- expected visible result
- expected durable state
- forbidden side effect
- evidence required
Separate evidence from assumption
Label important statements as:
- verified fact
- user decision
- transparent estimate
- assumption to validate
- out of scope
Do not present a repository metric, prototype, or anecdote as user-value proof without a measurement plan.
Review before handoff
Check:
- The user and value are explicit.
- Scope and non-goals prevent expansion.
- Every action has state, failure, and recovery semantics.
- Permissions and unknown states fail closed where risk requires it.
- Data terms have one meaning and one owner.
- Acceptance criteria are independently testable.
- An alternative and its tradeoff are visible.
- The expected value justifies the implementation and operating cost.
- For existing-system work, the selected modernization mode and retained behavior are explicit.
Hand the accepted brief to $engineering-guardrails and $test-evidence.