pua-en — Skills — getagentictools

What it does

"Think Big, but execute small": You've got the architecture astronaut disease. Zoom out for strategy, zoom in for execution. Where are the concrete next steps?

[ ] Has the fix been verified? (run tests, curl verification, actual execution) — not "I think it's fine" but "I ran the command, here's the output"

[ ] Are there similar issues in the same file/module?

[ ] Are upstream/downstream dependencies affected?

[ ] Are there uncovered edge cases?

[ ] Is there a better approach I overlooked?

[ ] For anything the user didn't explicitly mention, did I proactively address it?

Requirements & configuration

| Insufficient info | Ask user "please tell me X" | Use tools to investigate first, exhaust what you can find, only ask what truly requires user confirmation |

| "I need more context" | You have search, file reading, and command execution tools. Dive Deep first, ask later. | L2 |

If this pattern continues, I'll need to have a different conversation with you. One that involves HR. And I won't be able to go to bat for you this time.

🔵 Google Flavor (Perf Review — "Needs Improvement")

If you want to move up, I need to see sustained, measurable improvement starting this sprint. Not promises. Not plans. Diffs that pass CI and features that users actually use.

pua en

Source

Repository: https://github.com/tanweai/pua

pua-en FAQ

What does the pua-en skill do?

Performance-coaching mode for repeated failures, passive behavior, completion-quality issues, or explicit try-harder requests. Uses structured troubleshooting and evidence-first delivery habits. "Think Big, but execute small": You've got the architecture astronaut disease. Zoom out for strategy, zoom in for execution. Where are the concrete next steps? [ ] Has the fix been verified? (run tests, curl verification, actual execution) — not "I think it's fine" but "I ran the command, here's the output"

What does pua-en require?

| Insufficient info | Ask user "please tell me X" | Use tools to investigate first, exhaust what you can find, only ask what truly requires user confirmation | | "I need more context" | You have search, file reading, and command execution tools. Dive Deep first, ask later. | L2 | If this pattern continues, I'll need to have a different conversation with you. One that involves HR. And I won't be able to go to bat for you this time. 🔵 Google Flavor (Perf Review — "Needs Improvement") If you want to move up, I need to see sustained, measurable improvement starting this sprint. Not promises. Not plans. Diffs that pass CI and features that users actually use.

How do I install pua-en?

Run: npx -y skills add https://github.com/tanweai/pua --skill pua-en --agent claude-code — the source lives at github.com/tanweai/pua.

Maintain pua-en?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[pua-en on getagentictools](https://getagentictools.com/skills/tanweai-pua-pua-en?ref=badge)

npx agentictools info skills/tanweai-pua-pua-en

The second line is the CLI lookup for this page — handy in READMEs and docs.