Repository navigation
fix: ask which user experience to implement when it is not clear - #50
Merged
Merged
Conversation
✅ Deploy Preview for fullstack-promptable-app-example ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
✅ Deploy Preview for fullstack-promptable-prompt-first ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
✅ Deploy Preview for fullstack-promptable-agentic ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Stop defaulting new chrome to prompt-first. Choose a UX now waits for side, prompt-first, or agentic. Co-authored-by: carlosvin <carlosvin@gmail.com>
cursor
Bot
force-pushed
the
cursor/ask-ux-when-unclear-384d
branch
from
October 6, 2026 18:57
434041a to
69ca5e4
Compare
carlosvin
marked this pull request as ready for review
October 6, 2026 20:29
There was a problem hiding this comment.
Copilot review overview
🟡 Changes recommended
The regression check does not validate ask-and-wait behavior across both UX companion skills.
Review effort: Balanced
Findings: 1
What changed in this PR
Removes the implicit prompt-first fallback and requires explicit UX selection when undeclared.
Changes:
- Updates architecture, side/prompt-first, and agentic UX guidance.
- Preserves existing
PROMPT_CONCEPTdeclarations. - Adds static evaluation coverage, though companion checks remain incomplete.
| File | Description |
|---|---|
AGENTS.md |
Documents three UX options and selection behavior. |
.agents/skills/tanstack-promptable-fullstack-app-template/SKILL.md |
Defines explicit UX selection contract. |
.agents/skills/promptable-ux/SKILL.md |
Removes prompt-first fallback. |
.agents/skills/agentic-ux/SKILL.md |
Prevents agentic fallback. |
scripts/skills/runSkillEvals.mjs |
Adds incomplete regression checks. |
skills/README.md |
Updates example UX prompt. |
skills/evals/README.md |
Documents new evaluation expectation. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Add choose-ux-asks-when-unclear so a silent prompt-first default fails CI. Co-authored-by: carlosvin <carlosvin@gmail.com>
Drop the second node runner. pnpm test:skill-evals now reports one Vitest test per check. Co-authored-by: carlosvin <carlosvin@gmail.com>
Fixture failures now target one check, and the real workspace is covered once. Co-authored-by: carlosvin <carlosvin@gmail.com>
The check looks at the sentence, not four old phrasings. Co-authored-by: carlosvin <carlosvin@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
When a new app has not declared a user experience, the architecture skill and the UX companions now ask which of the three to implement and wait:
promptable-ux)agentic-ux)They no longer fall back to prompt-first. An app that already sets
PROMPT_CONCEPT, including this template's three Netlify sites, keeps that declaration.choose-ux-asks-when-unclearchecks that contract on all three skills. It fails if a skill names prompt-first as the default, picks an experience when the preference is unclear, or drops the ask-and-wait rule.Skill checks run once, through Vitest. Each check is its own test. Fixture regressions call that one check instead of an aggregate runner. Waza on pull requests stays
waza check,waza spec verify, and the mockwaza run. The Copilot SDK is not part of that job.Test plan
pnpm test:skill-evals(35 tests)pnpm skills:wazain CI (localwazabinary is not installed)