agentsclimarketplace
Sign in

Product review

Skill jpoindexter/product-management-skills/skills/product-review

Run a structured review of a product bet, initiative, roadmap, launch, or evidence packet and return a decision with gaps and next actions. Use when the user asks for critique, a product review, a go/no-go decision, an executive review, or an audit across value, usability, feasibility, viability, evidence, and operations.From its SKILL.md

Install
npx -y skills add jpoindexter/product-management-skills --skill product-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 24 days oldThe repository was created 24 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.

SKILL.md

2.6 KB, 465 tokens by cl100k_base, as published. Nobody here has run it

Product Review

Review a product decision against its declared outcome and evidence, then identify the smallest set of gaps that block a responsible decision.

Inputs

  • Artifact or proposal under review
  • Decision requested and decision owner
  • Target customer, outcome, and strategy
  • Evidence and source dates
  • Constraints, dependencies, and launch horizon
  • Known dissent and open risks

Workflow

  1. State the requested decision and falsifiable success criterion.
  2. Reconstruct the product bet: customer, problem, intervention, mechanism, outcome, and business value.
  3. Audit evidence provenance and separate observed, reported, inferred, and assumed claims.
  4. Review value, usability, feasibility, and business viability.
  5. Review strategy fit, alternatives, non-goals, and opportunity cost.
  6. Review metrics, experiment logic, instrumentation, guardrails, and stop rules.
  7. Review operational readiness, ownership, dependencies, failure recovery, and stakeholder alignment.
  8. Rank gaps as blocker, important, or monitor.
  9. Decide: proceed, proceed with conditions, run a targeted test, rework, pause, or stop.

Output contract

Return executive decision, reconstructed bet, evidence ledger, four-risk assessment, strategic fit, measurement review, readiness review, ranked gaps, required actions with owners, and next review trigger.

Quality gate

  • The decision is explicit and owned.
  • Blockers are tied to consequence, not preference.
  • Positive evidence receives the same provenance scrutiny as negative evidence.
  • Conditions are observable and time-bounded.
  • The review names what was not verified.

Avoid

  • Vague “looks good” feedback
  • Reviewing polish while ignoring the decision
  • Treating stakeholder agreement as customer evidence
  • Adding a long wish list unrelated to launch risk
  • Approving plumbing, plans, or prototypes as proof of real behavior

Source grounding

Operational synthesis combining the four product risks from Inspired, evidence and assumption practices from Continuous Discovery Habits and The Mom Test, strategy coherence from Good Strategy/Bad Strategy, outcome discipline from Escaping the Build Trap, lifecycle metrics from Lean Analytics, and AI-system readiness principles from Building AI-Powered Products and Designing Machine Learning Systems.

What ships with it: 1 file

203 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 326,401. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.