After this, the AI stops generating plausible-looking code against assumptions you never made — and starts asking the right question with a recommended answer, until every load-bearing decision is resolved. For developers tired of ripping out code the AI built against unstated assumptions. Before: "Add OAuth login" [Writes 300 lines: Google OAuth, JWT tokens, refresh logic, session middleware. Doesn't ask which providers, which token strategy, or whether you want SSO.] After: "Add OAuth login" Q: Which providers? (Google / GitHub / Apple / all three) Q: Token strategy? (JWT [recommended] / session cookies) Q: SSO at the org level? (yes / no [recommended for early stage]) Q: Refresh token rotation? (default / strict) [three more questions, then writes the integration] Use when a plan feels vague the user says "grill me" you're about to start non-trivial work without resolving every decision Three ways to use this Paste it (any AI, 30 seconds, no install)Open the .md file, copy contents, paste into Claude / ChatGPT / Cursor / Perplexity with: "Read this and apply it whenever the task it describes comes up in our conversation." Done. Install it (Claude Code / Cursor users)Drop the unzipped folder into ~/.claude/skills/ (Claude Code), .cursor/skills/ (Cursor), or your IDE's equivalent. Auto-loads next session. New to AI assistants? Get Claude free at claude.ai, then use Option 1. €7
