Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →zzafergok/feature-design-assistant
Turn ideas into fully formed designs and specs through natural collaborative dialogue.
Passed 12 of 22 test cases with the skill, and 4 of 22 without it.
and 13 more in the full report
11 fixed1 passed either way7 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the targeted word count range for each technical section when presenting a feature design incrementally?
| Checked | Without skill | With skill |
|---|---|---|
| The recommended length per section is 300-500 words. | Missed | Passed |
The instructions your model reads when the skill loads.
Shape a feature collaboratively without prematurely converting an idea into a fixed implementation.
Clarify the target user, triggering situation, current behavior or workaround, desired outcome, evidence, business relevance, constraints, and reason for acting now. Distinguish the user problem from the proposed feature.
Ask one focused question at a time only when the answer changes the design. Otherwise, state assumptions and move forward.
Generate a small set of meaningfully different approaches, including a minimal or no-build option when credible. Compare user value, complexity, time to learn, risk, reversibility, dependencies, and fit with the existing product. Recommend one with a concrete rationale.
Describe:
Use a flow or wireframe only when it clarifies sequence or layout.
Write requirements as observable behavior. Include scope, non-goals, business rules, data and integration needs, dependencies, compatibility, rollout, and acceptance criteria. Do not invent repository paths, APIs, metrics, or architecture before inspecting the implementation context.
Identify the riskiest assumptions and the lowest-cost way to test them. Define success, guardrail, and failure signals with baselines or data sources when known. Separate launch criteria from longer-term outcome measurement.
Produce a concise feature specification with problem, users, evidence, selected approach, alternatives, flows, requirements, edge cases, non-goals, metrics, rollout considerations, risks, and open decisions. Stop before implementation planning unless the user requests both.
test cases passed, vs 4 / 22 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.