Get more out of GPT-6 Astra by revisiting your skills, AGENTS.md, and task prompts. Make skill triggers specific, load guidance when it's relevant, and define what done looks like. https://t.co/UGF0AC8Z5Y
As models change, prompt and setups tuned for a prior model degrade; this gives specific levers (trigger specificity, guidance timing, done-criteria) to re-tune configs for a new model.
Checking sign-in…
Loading comments…