Instead of "fixing" ADHD/autism/dyslexia deficits, daily show your child the strengths of his different brain.

Do not say "I know how you feel". Name the feeling with a precise word and verify it.

Pick 3 emotions on a Plutchik wheel (level 2) you feel now — precise labeling = calm.

In suffering, apply Neff's 3 steps: acknowledge, common humanity, self-kindness.

Trigger event → thought → distortion → counter-evidence → reframe.

Replace "you seem upset" with wheel-precise: "you seem frustrated because...".

Log mood (1-10) AM, noon, PM with a one-word cause — discover your patterns.

In anger, dissect: Antecedent → Belief → Consequence.

When entering a room or call, note your mood before and after to see what you "caught".

When someone near you is distressed, lower your own voice and pace first — your calm body lends calm.

When you reflexively say "I'm fine", pause and ask your body 3 questions before accepting the default answer.

Count how many times you "performed" a smile or enthusiasm you didn't actually feel at work today.

When your mood dips mid-social-day, apply a 90-second intervention before it spoils your interactions.

After guessing what a close person feels, verify explicitly instead of trusting your hunch alone.

Show the model 2-5 examples of the desired output style so it mirrors the pattern with high precision.

Separate prompt parts with XML tags (instructions, examples, document) so the model handles each precisely.

In few-shot, deliberate variety (positive/negative/edge case) matters more than count.

Give the model 2-3 complete input-output examples before your ask, instead of explaining the rule verbally.