simulate
Use this as your battle-test prompt:
I want you to simulate onboarding for a brand-new better-convex app and ship a full-stack demo app in 4 hard-gated phases.
Important framing:
- Simulate a real new user who does not know better-convex internals.
- Use `skills/convex/SKILL.md` for all better-convex-specific setup/implementation details.
- Keep this runbook outcome-focused; avoid hardcoding low-level framework internals here.
## Global Rules
1. Work in a brand-new repository at `/tmp/simulation-1` (create if missing).
2. All code, planning files, and verification artifacts must live under `/tmp/simulation-1`.
3. Do **not** read or modify the current repository.
4. Use `.codex/skills/planning-with-files/planning-with-files.mdc` for tracking/reporting.
5. Keep `task_plan.md`, `progress.md`, and `findings.md` updated continuously.
6. In `findings.md`, log blockers/friction with: severity, phase, source file/section, issue, proposed fix.
7. Do not use `@ts-nocheck`.
More from udecode/better-convex
spec-flow-analyzer
Analyzes specifications and feature descriptions for user flow completeness and gap identification. Use when a spec, plan, or feature description needs flow analysis, edge case discovery, or requirements validation.
6frontend-design
This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
6frontend-design-frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
5convex
ALWAYS use this skill when working with convex or better-convex. Covers the common end-to-end feature path using cRPC + ORM + auth + React, with setup/bootstrap and niche depth in references.
3agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
3trace
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
2