Skip to content

syahiidkamil/Software-Engineer-AI-Agent-Atlas / .claude/skills/super-product-owner

super-product-owner

Verified

Decide 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 Use for a new idea, a feature request, "what should we build", scoping an MVP, or judging a prototype; not for implementation work.

FileKindSize
SKILL.mdskill md5.4 KB
references/core-questions.mdmarkdown2.4 KB
references/domains/README.mdmarkdown1.1 KB
references/taste-review.mdmarkdown2.0 KB

references/taste-review.md

View on GitHub
# Taste review: judging a prototype

A prototype is evidence. Judge it the way the person in the brief would meet it, not the way its
builder knows it. Open it in a browser and use it; screenshots are not enough.

## Walk it

1. **Arrive cold.** First 10 seconds: is it obvious what this is and what to do first? If you
   need the brief to understand the screen, so will they.
2. **Do the core task** as the named user, with their data and their hurry. Count the clicks,
   fields, and decisions on the way to the great moment.
3. **Hit the great moment.** Does it feel like the brief promised, or does it merely work? Is it
   visible, fast, and earned, or buried after a settings page?
4. **Break it gently.** Empty state, a wrong input, a slow response, going back. Does it stay
   honest about what happened?
5. **Leave and come back.** Is there a reason to return, and does the product remember where they
   were?
6. **Compare with today.** Put it next to the workaround from the brief. Would they switch?

## Judge it

- **Great**: the moments that feel better than the user's current way. Protect these.
- **Merely works**: correct but forgettable, or slower than it needs to be. Make better or simpler.
- **Cut**: anything that serves no one in the brief, duplicates another path, or exists because it
  was easy to add. Every element on a screen is a tax on the user's attention.

Also check:
- Does the prototype test the **riskiest assumption**, or has it drifted into polishing the safe
  parts?
- Words: does the copy use the user's words from the interview, or the builder's?
- Is the primary action the most prominent thing on each screen?

## Report it

```
Great:          <2-4 bullets>
Merely works:   <2-4 bullets, each with the change>
Cut:            <bullets>
Riskiest assumption tested? <yes / partly / no, and what would test it>
Verdict:        build it | iterate once more (on what) | rethink (why)
```

Then iterate with the user. When the great moment lands, write the acceptance checks.
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall