Write the problem hypothesis
For [specific user], completing [job] is difficult because [missing capability], causing [measurable consequence].
You can name one user, one situation and one measurable consequence without proposing a feature.希望可以支持gemini模型，还有stitch的导入
Evidence observed in ZSeven-W/openpencil, a Design project.
4 comments0 positive reactions216 days openProject Radar 93
enhancement
Start the no-account validation tool4 guided steps · private browser notes · export anytime
REPEATED ACROSS 11 PROJECTS
Related friction appears in 11 independent repositories. This is stronger than one backlog item, but still requires direct user validation.
Project strength and demand confidence are measured separately.SOURCE EVIDENCE
Read original GitHub Issue ↗Start with what users actually said
Reporter context: Problem codex和claude的审美不好，gemini模型的审美要好些 Proposed Solution 支持gemini模型，希望还可以支持google的stitch导入 Alternatives Considered No response Area None Additional Context No responseExcerpted from the public Issue. Read the complete thread before interpreting it.
Recruit: Recruit practitioners with a current brief, asset handoff or revision cycle that can be observed end to end.
Guardrail: Keep a human quality review and measure accepted output, revision count and cycle time.
Interview five designers or creative leads
- When did you last need this?
- What outcome were you trying to reach?
- What did you use instead?
- How often does this occur?
- What commitment would prove it matters?
Run the smallest experiment
Deliver the outcome manually or with a narrow prototype before building a reusable feature.
A user completes the real workflow and commits time, data, distribution or budget to repeat it.Keep a human quality review and measure accepted output, revision count and cycle time.Make a build decision
- Build: repeated pain and active commitment
- Narrow: pain is real but the audience or job differs
- Stop: weak frequency or no behavioral proof
Why this brief exists
Information has value only when it changes action. This page turns one public signal into a bounded validation exercise. It is a research aid, not proof of demand, investment advice or a product recommendation.