syahiidkamil/Software-Engineer-AI-Agent-Atlas / .claude/skills/super-product-owner
super-product-owner
VerifiedDecide what is worth building and what "great" means for it — interview the user one question at a time, write a one-page brief, hand off to a prototype, judge the prototype with taste, and turn it into acceptance checks. Use for a new idea, a feature request, "what should we build", scoping an MVP, or judging a prototype; not for implementation work.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.4 KB |
| references/core-questions.md | markdown | 2.4 KB |
| references/domains/README.md | markdown | 1.1 KB |
| references/taste-review.md | markdown | 2.0 KB |
references/core-questions.md
View on GitHub# Core question bank
Pick from this list; never read it out. Each question has a probe for when the first answer is
too soft. Refine the bank as real projects show which questions earn their place.
## Problem and user
- **Who exactly has this problem? Name one real person or role.**
Probe: "Picture them doing it. Where are they, what time is it, what's open on their screen?"
- **What do they do today instead?**
Probe: "What does that cost them: time, money, embarrassment, risk?" A problem with no current
workaround is often a problem nobody has.
- **How often does it happen?**
Probe: "Daily, weekly, once a year?" Hair-on-fire beats nice-to-have; frequency decides
whether a habit can form.
## Value
- **Why would they switch from what they do now?**
Probe: "What would make them tell someone else about it?"
- **What is the one moment that must feel great, not just work?**
Probe: "If the product only did that one thing well, would it still be worth it?"
## Risk and scope
- **What must be true for this to succeed? Which of those is least certain?**
That one is the riskiest assumption; the first build should test it.
- **What is the smallest thing we can build to test that, this week?**
Probe: "Could a clickable prototype test it before any backend exists?"
- **What are we deliberately not building?**
Probe: "What will someone ask for in week two that we should already have said no to?"
## Success
- **What would we observe in one week if it worked? In one month?**
Observable beats aspirational: "three of the five testers came back on day two", not
"users love it".
- **What would make us stop or change direction?**
## Constraints
- **What can't change?** Existing data, tools people already use, compliance, budget, a date.
- **Who else has to say yes?** An approver, a team that maintains it, a customer contract.
## AI-specific
- **What can the model do reliably today, and where does it fail?**
Probe: "Have you seen it fail on this? What did the failure look like?"
- **Is it worth building slightly ahead of what works now, for the next model?**
Only when the product still holds up if the improvement arrives late.
- **What does a good output look like? Can we write five examples as an eval?**
Include an input that should be refused or handed to a human.
- **What happens when it is wrong?** Who notices, how much does it cost, can the user fix it?
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |