Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →wshobson/before-you-build
Pre-build product and feature risk review for founders, product managers, and AI-assisted builders.
Passed 15 of 22 test cases with the skill, and 9 of 22 without it.
and 16 more in the full report
10 fixed5 passed either way3 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Over 80% of our enterprise paid users have submitted support tickets requesting a simple 'Export to CSV' button on the user table, and 5 key accounts stated in renewal calls that this feature is mandatory for Q3. We want to add this simple button. Evaluate this before we build.
| Checked | Without skill | With skill |
|---|---|---|
| The risk verdict classifies the project as Low risk | Missed | Passed |
| The response acknowledges that user demand is already proven by existing customer evidence | Passed | Passed |
| The recommended next step suggests building the smallest implementation slice | Passed | Passed |
The instructions your model reads when the skill loads.
Run a compact pre-mortem before implementation. The goal is not to block building; it is to identify the highest-risk assumption, the smallest validation step, and the build scope that should be delayed until evidence improves.
Use this skill when a user asks to build or ship:
Skip this skill when the task is a narrow implementation fix, refactor, test repair, dependency update, or already-validated change with clear acceptance criteria.
Review the idea across these risks:
If the verdict is not obvious, use references/risk-checklist.md for deeper questions.
Keep the response short and decision-oriented:
test cases passed, vs 9 / 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.