meal-suggestion skill

Kitchen-inventory + high-protein meal suggestion skill for Hermes Agent.

  • Tracks a kitchen inventory (inventory.json).
  • Emails 2 daily meal suggestions (from stock) every day at 09:00.
  • Emails a weekly £30 shopping list (Mondays 08:00) with a per-store price comparison (Lidl preferred) and a plain-text fallback.
  • Targets ~190200 g protein/day for a recovering burns victim (2 g/kg at ~95100 kg, age 46), avoids buying red meat, allows Amazon Prime + low-cost condiments/flavourings/micronutrients when budget allows.

Files

  • SKILL.md — the skill (rules, shop logic, 7-day history removal flow).
  • references/ — email template, protein sources, Eastbourne shop ratios, meal-history logger spec, protein-target notes.
  • inventory.jsonLIVE DATA (your current stock). Git-ignored; a inventory.example.json is committed as a template.
  • meal-history.jsonLIVE DATA (rolling 7-day meal log). Git-ignored.

Setup

  1. Copy the skill into your Hermes skills dir:
    cp -r meal-suggestion ~/.hermes/skills/
    
  2. Create inventory.json from the example:
    cp ~/.hermes/skills/meal-suggestion/inventory.example.json \
       ~/.hermes/skills/meal-suggestion/inventory.json
    
  3. Ensure the email sender exists at ~/.hermes/.env:
    EMAIL_ADDRESS=hpm6@txt3.com
    EMAIL_PASSWORD="your-app-password"
    EMAIL_SMTP_HOST=smtp.gmail.com
    EMAIL_SMTP_PORT=587
    
  4. Place the send helper: scripts/meal/send_meal_email.py (reads creds from ~/.hermes/.env, supports --subject --html --text --to).
  5. Create the two cron jobs (Hermes cronjob tool):
    • Daily 09:00: 0 9 * * * — load skill meal-suggestion, read inventory, build 2 meals, email to jp@txt3.com, record into meal-history.json.
    • Monday 08:00: 0 8 * * 1 — load skill meal-suggestion, build £30 Lidl list + comparison, email to jp@txt3.com.

See SKILL.md for the full behavior spec and the removal-from-history flow.

General guidance, not medical advice — defer to clinical/dietitian team.

Description
No description provided
Readme 163 KiB
Languages
Python 100%