- Add [[app_ext:...]] tag format and rewrite extractApps() for reliable app extraction - Wire AppsGrid and RecipeGrid into ContentGridView (was missing on wide desktop) - Add mock Archy node data for standalone dev testing (VITE_MOCK_ARCHY=true) - Fix PromptPalette: z-50 + opaque bg so slash menu renders above chat content - Fix detail banner not updating: add :key to all detail components in ContentPanel - Guide page moved to /guide, chat is now root route, guide auto-selected on first load - Code browser: click opens file in viewer, separate checkbox for chat context selection - Restore folder context selector (round checkbox on hover) in FileTreeNode - Demo projects for prod deployment instead of hardcoded personal paths - Improve Archy context injection with media breakdown and better error logging - Add 11 Claude Code skills for efficient development workflows Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.2 KiB
1.2 KiB
name, description, allowed-tools
| name | description | allowed-tools |
|---|---|---|
| test-prompts | Test AI prompt quality by simulating queries and checking extraction results | Bash(*), Read, Edit, Glob, Grep, Agent |
Test the AIUI AI prompt and content extraction pipeline end-to-end. This skill does NOT call the actual AI — it uses the seed prompts and extraction functions directly.
Steps
-
Read seed prompts: Read
packages/app/src/__tests__/fixtures/seedPrompts.tsto get all test cases. -
Run extraction tests: For each seed prompt, run the test via
pnpm --filter @aiui/app test -- --run -t "seed"and report results. -
Test edge cases: Create and test these additional scenarios by calling extraction functions in a test:
- Mixed content response (films + songs + books in one response)
- App recommendation response (should trigger app tab)
- News query with web search results
- Place/restaurant recommendations
- Code response with 3+ code blocks
- Nostr-related query
- Empty/minimal response
-
Verify tab routing: For each scenario, check that
filterTabsByContext()returns the expected tabs in the expected order. -
Report: Summary of what works, what's broken, and what's missing. Include specific test cases that fail.