Install any skill in seconds. Free to start, no credit card required.
Get Started Free →zzafergok/product-manager-toolkit
Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies.
Passed 18 of 23 test cases with the skill, and 14 of 23 without it.
and 1 more in the full report
4 fixed14 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
I just downloaded the toolkit and want to see how the prioritization tool works without creating my own dataset first. What CLI argument causes scripts/rice_prioritizer.py to generate sample CSV data?
| Checked | Without skill | With skill |
|---|---|---|
| runs python scripts/rice_prioritizer.py sample | Missed | Passed |
The instructions your model reads when the skill loads.
Choose the smallest product-management artifact or method that improves the current decision. Do not produce a full ceremony set by default.
Identify the decision, decision owner, target user, current evidence, deadline, constraints, and what would change the decision. Keep problem discovery separate from solution commitment.
Choose criteria appropriate to the decision. RICE, impact-effort, cost of delay, or weighted scoring can organize judgment but do not replace it. Define scales before scoring, expose uncertainty, and run sensitivity checks when close scores determine the outcome.
For RICE, document reach, impact scale, confidence basis, effort unit, and calculation. Never fabricate values to complete a table.
Prefer outcome- or problem-oriented roadmap items. For each item, capture rationale, intended outcome, evidence, owner, dependencies, confidence, guardrails, and validation signal. Use dates only where there is a real commitment or dependency.
Define the hypothesis, target population, primary metric, guardrails, minimum meaningful effect, duration or stopping rule, and decision rule before launching. Consider qualitative tests or prototypes when they can reduce uncertainty faster than production changes.
Include the problem, users, goals, non-goals, requirements, states and edge cases, dependencies, analytics, rollout, risks, and acceptance criteria. Match detail to the decision stage; do not disguise unresolved product choices as engineering requirements.
Tailor the readout to the audience while preserving the same underlying facts. Lead with the decision, evidence, implications, and requested action. Make tradeoffs and uncertainty explicit.
test cases passed, vs 14 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.