Initial meal-suggestion skill (logic + template; live data git-ignored)

2026-08-26 02:55:33 +01:00
commit 72ce56edeb
10 changed files with 464 additions and 0 deletions
--- a/.gitignore
+++ b/.gitignore
@ -0,0 +1,4 @@
+# Live data — keep out of version control.
+# Your current stock and 7-day meal log drift as you eat / the daily job runs.
+inventory.json
+meal-history.json
--- a/README.md
+++ b/README.md
@ -0,0 +1,49 @@
+# 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 ~190–200 g protein/day for a recovering burns victim (2 g/kg at
+  ~95–100 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.json` — **LIVE DATA** (your current stock). Git-ignored; a
+  `inventory.example.json` is committed as a template.
+- `meal-history.json` — **LIVE 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.
--- a/SKILL.md
+++ b/SKILL.md
@ -0,0 +1,190 @@
+---
+name: meal-suggestion
+description: "Kitchen inventory + high-protein meal suggestions. Tracks ingredients, suggests 2 daily meals from stock, and a weekly £30 shopping list. Emails jp@txt3.com from hpm6@txt3.com. For a recovering burns victim on a high-protein diet avoiding red meat."
+version: 1.0.0
+author: agent
+license: MIT
+---
+
+# Meal Suggestion
+
+## Context
+User **jp** is a recovering burns victim who must eat a **high-protein diet** and wants to
+**avoid red meat**. This skill keeps a running kitchen inventory and produces:
+
+- **2 daily meal suggestions** (from what's in stock) — emailed every day at 09:00.
+- **A weekly shopping list** on a **£30 budget** — emailed Mondays.
+
+- **Sender:** `hpm6@txt3.com` (the agent's Gmail, via smtp.gmail.com:587).
+- **Recipient:** `jp@txt3.com`.
+
+## Inventory
+File: `/home/jp/.hermes/skills/meal-suggestion/inventory.json`
+
+Schema:
+```json
+{
+  "updated": "YYYY-MM-DD",
+  "diet": { "goal": "high-protein", "avoid": ["red meat"] },
+  "items": [
+    { "name": "Eggs", "qty": 12, "unit": "count", "category": "protein", "notes": "" }
+  ]
+}
+```
+- `category` is one of: `protein`, `veg`, `fruit`, `dairy`, `grain`, `tinned`,
+  `frozen`, `condiment`, `other`.
+- Keep `qty` as a number with a `unit` (`count`, `g`, `ml`, `pack`, `can`, `tbsp`, etc.).
+
+### Updating the inventory (you own this)
+- When the user says they **used/consumed** ingredients, decrement or remove the
+  matching item(s) with the `patch` tool, then bump `updated` to today.
+- When the user **bought** items, add or increase them.
+- Do **NOT** auto-consume on a daily suggestion — the user tells you what was
+  actually eaten. The daily email only *proposes* meals.
+
+## Meal suggestion rules
+- Suggest **two meals** per day (e.g. lunch + dinner) using only items currently in the inventory.
+- **Maximize protein** per meal; lead with a protein source.
+- **Avoid red meat for PURCHASES** (beef, lamb, pork, venison, bacon, gammon) — the
+  weekly shopping list must NEVER suggest red meat to buy.
+- **If red meat is already in the inventory, it stays usable** in daily meal
+  suggestions so it isn't wasted. Deprioritize it behind the high-protein
+  non-red-meat options, but do NOT exclude it just because it's red meat.
+- Preferred proteins (lead with these): eggs, chicken, turkey, fish, prawns, tofu,
+  tempeh, lentils, beans, chickpeas, Greek yogurt, cottage cheese, quark, skim milk,
+  whey, tinned tuna/salmon, edamame, halloumi.
+- **Protein target:** ~**190–200 g/day** (user ~95–100 kg × 2 g/kg — burns recovery +
+  preserving lean mass while losing ~15 kg fat). Aim each meal at **~90–100 g protein**
+  and **STATE the per-meal and daily protein totals** in the email. If 2 meals can't
+  reach ~190 g with current stock, say so and suggest a third hit (whey shake, extra
+  eggs, Greek yogurt) to close the gap.
+- **Weight-loss framing:** keep meals calorie-moderate — bulk with veg, go easy on oven
+  chips, white bread, and oil; lead with lean protein. Fat loss comes from a mild calorie
+  deficit, NOT from cutting protein.
+- **Note:** this is general guidance, not medical advice — defer to the user's
+  clinical/dietitian team and keep hydration up on a high-protein intake.
+- Each meal block: **name**, the **ingredients + approx amounts** used, a short
+  **2–3 step method**, and the **protein total (g)**.
+- If the inventory is too sparse for a real meal, say so and list the top 2–3
+  things to buy.
+
+## Email format
+Send via the helper (it reads SMTP creds from `~/.hermes/.env`):
+```bash
+python3 /home/jp/.hermes/scripts/meal/send_meal_email.py \
+  --subject "Your Meals for Today — <date>" \
+  --html /tmp/meal_today.html \
+  --to jp@txt3.com
+```
+HTML must be self-contained (inline CSS), mobile-friendly, dark-on-light, with a
+header, the two meal cards, and a footer note
+("Reply to tell me what you used and I'll update the inventory").
+Use the scaffold in `references/email-template.md`.
+
+## Weekly shopping list (Mondays)
+- Budget **£30** total. Use realistic UK supermarket prices (Tesco/Asda/Sainsbury's).
+- Prioritize protein, then veg/fruit, then staples. Show item, est. price, and a
+  running total that lands in range.
+- Email subject: `Weekly Shopping List — <date>`.
+- This does **not** modify the inventory.
+- **Micronutrients & vitamins (user is 46):** you MAY include 1–2 low-price
+  health-support items on the weekly shop when budget allows under £30, to support
+  overall health alongside the high-protein diet. Sensible, evidence-aware picks for a
+  46-year-old on high protein with limited red meat: vitamin D (low sun exposure risk),
+  omega-3 (fish-oil or flax/chia), magnesium (recovery/sleep), and a B12 source if
+  relying on eggs/dairy over meat. Prefer food-first (oily fish, leafy greens, seeds);
+  only add a supplement line (e.g. "Vitamin D3 1000–2000 IU", "Omega-3 caps") when
+  budget permits and label it clearly as a general-health suggestion, NOT medical advice.
+  Keep each low-cost and behind protein + veg + staples in priority.
+- **Condiments & flavourings:** you MAY include a small item or two from the
+  spice/sauce/condiment aisle (e.g. fresh herbs, lemon, soy, spices, stock cubes,
+  passata, a hot sauce) so meals are more interesting — keep each low-price and only
+  if budget allows under £30. These are optional "interest" buys; protein + veg +
+  staples come first.
+
+## Where to shop (Eastbourne) — single-shop, per-store totals
+User is in **Eastbourne**. Local options: **Lidl, Sainsbury's, Co-op, Tesco Express,
+and a local Londis** (good deal on milk: 2L £1.40). Memberships: Tesco Clubcard, Co-op member.
+
+**User preference (confirmed): Lidl is the PREFERRED shop.** It's a weekly trip so the
+extra distance is acceptable; Lidl gives the best value AND leaves budget for essential
+micronutrients and the occasional treat. The other stores (Tesco Express, Sainsbury's,
+Co-op, Londis) are shown ONLY for comparison, and as the fallback for days he doesn't
+want to make the longer journey.
+
+Grounded in Which? 2026 monthly price index (93-item basket; Lidl £160.70 baseline):
+- Lidl ≈ 1.00x — **CHEAPEST, preferred** (whey, eggs, chicken, lentils, frozen veg, milk, tuna, bananas, plus fruit/veg for micronutrients + a treat)
+- Tesco superstore w/ Clubcard ≈ 1.17x; **Tesco Express** adds convenience premium → ~1.22x WITH Clubcard
+- Sainsbury's w/ Nectar ≈ 1.17x
+- Co-op ≈ 1.30x nominal — membership = annual dividend, not instant discount
+- Londis ≈ 1.25–1.35x indicative; milk cheap but full basket pricier → top-up only
+
+**Weekly email MUST:**
+1) Build ONE single-shop basket available at **Lidl** (the default recommended shop).
+2) Show a **"Same basket — where else?" comparison table** (Lidl / Tesco Express Clubcard
+   / Sainsbury's Nectar / Co-op member / Londis) with estimated totals + delta vs Lidl.
+   Label as ESTIMATES from Which? 2026 ratios + known local prices (Londis milk £1.40),
+   NOT live scans. Do NOT run a live web search.
+3) **Recommend Lidl** as the primary shop — note it's a weekly trip so distance is fine
+   and it best fits the budget incl. micronutrients/treats. List the others as fallback
+   only ("if you'd rather not make the trip: Tesco Express is closest").
+4) Single-shop the list — don't split across stores UNLESS a specific item's local price
+   is **definitely known** to be lower elsewhere (e.g. Londis milk 2L at £1.40 is a
+   confirmed cheaper line). Estimated basket ratios alone are NOT grounds to split.
+5) You MAY suggest ordering certain items via **Amazon Prime** when it's clearly better
+   value (e.g. whey protein 1 kg is often cheaper per gram on Prime than in-store). If
+   used, show the Prime item separately and note it's a delivery, not a store trip.
+6) Robustness: the comparison table must be clearly visible. ALSO attach a plain-text
+   alternative (send_meal_email.py --text) so the comparison survives even if the mail
+   client strips HTML tables.
+
+## Split-store & Amazon Prime rules
+- **Default: single shop at Lidl.** Do NOT split the basket across stores based only on
+  the estimated Which? 2026 ratios — those are approximations. Splitting is allowed ONLY
+  when a **specific item's local price is definitely known** to be lower elsewhere
+  (e.g. Londis milk 2L at £1.40 is a confirmed cheaper line, so milk could be a Londis
+  top-up). State the known price when you do this.
+- **Amazon Prime:** you MAY suggest ordering specific items via Amazon Prime, but ONLY
+  when it is **genuinely better value or more convenient** — do not assume Prime is
+  automatically cheaper. Reality check (2026): Lidl whey is ~£9.99/500g (≈£20/kg);
+  Prime branded whey (Bulk/Myprotein) is typically £18–£27/kg, so it's roughly comparable
+  and Lidl often wins on a single trip. Suggest Prime for whey ONLY when (a) a confirmed
+  deal drops it below Lidl's per-kg price, or (b) the user prefers delivery over the trip.
+  When suggesting, show both prices side by side and state which is cheaper. Show any
+  Prime item as a separate "delivered via Prime" line, distinct from the in-store Lidl list.
+- When neither applies, keep everything in the one Lidl list.
+
+## 7-day meal history (for inventory removal)
+A rolling log lives at `meal-history.json` (same skill dir). The **daily job UPSERTS**
+its two meal entries each run (replaces any same `date`+`meal`, so re-runs don't
+duplicate) and **prunes entries older than 7 days**. Each entry:
+`{ date, weekday, meal: "lunch"|"dinner", name, items: [{name, qty, unit}] }`.
+Only substantive food items are logged — pure condiments (oil, salt, pepper, spices,
+garlic, soy, etc.) and the optional "third hit" snack are NOT logged. Units match
+`inventory.json` where possible.
+
+**On-demand removal (user says e.g. "remove Wednesday's dinner from inventory"):**
+1) Resolve the weekday/date to the matching entry (weekday is relative to today; if
+   ambiguous, ask). 2) For each `item` in that entry, find the matching inventory entry
+   by name (case-insensitive). 3) Subtract `qty`; if the result is ~0 or negative,
+   remove the inventory entry; else update it. 4) Skip any item NOT present in inventory
+   (e.g. a suggested-but-never-bought item) and say so. 5) Bump `updated` to today.
+6) Confirm what was removed. The user can also say "remove all of <day>" to drop both
+   meals, or name a specific item to override.
+
+## On-demand (chat)
+If the user lists ingredients in chat, add them to the inventory and optionally
+give an immediate 2-meal suggestion. If they ask "what should I eat today?", read
+the inventory and suggest now (and offer to email it).
+
+## Automation
+Two cron jobs (created via the `cronjob` tool), both loading this skill:
+- Daily 09:00 — `0 9 * * *` — 2 meal suggestions.
+- Monday 08:00 — `0 8 * * 1` — weekly £30 shopping list.
+
+Delivery is `local` because the email itself is the deliverable; check
+`cronjob action=list` / logs if a send ever seems missing.
+
+## References
+- `references/protein-sources.md` — allowed proteins + example pairings.
+- `references/email-template.md` — HTML email scaffold.
--- a/inventory.example.json
+++ b/inventory.example.json
@ -0,0 +1,30 @@
+{
+  "updated": "YYYY-MM-DD",
+  "diet": {
+    "goal": "high-protein",
+    "reason": "recovering burns victim — healing well, preserving lean mass",
+    "avoid_purchase": ["red meat"],
+    "age_years": 46,
+    "bodyweight_kg": "95-100",
+    "protein_per_kg": 2,
+    "protein_target_g_per_day": "190-200",
+    "weight_loss_goal_kg": 15,
+    "notes": "2g/kg for burns recovery + lean-mass preservation during ~15kg fat loss. Fat-loss comes from a mild calorie deficit (bulk with veg, limit chips/bread/bread/oil), NOT from cutting protein. Red meat already in stock is usable but never re-bought. General guidance, not medical advice — defer to clinical/dietitian team; keep hydrated."
+  },
+  "items": [
+    { "name": "Eggs", "qty": 14, "unit": "count", "category": "protein", "notes": "" },
+    { "name": "Chicken breast", "qty": 1, "unit": "count", "category": "protein", "notes": "whole breast, ~120-150g" },
+    { "name": "Whey protein powder", "qty": 1000, "unit": "g", "category": "protein", "notes": "high-protein staple; ~25g protein per scoop" },
+    { "name": "Tinned tuna in veg oil", "qty": 1, "unit": "can", "category": "tinned", "notes": "protein" },
+    { "name": "Milk", "qty": 1, "unit": "litre", "category": "dairy", "notes": "" },
+    { "name": "Greek yogurt", "qty": 1, "unit": "pot", "category": "dairy", "notes": "high protein" },
+    { "name": "Cottage cheese", "qty": 1, "unit": "pot", "category": "dairy", "notes": "high protein" },
+    { "name": "Red lentils", "qty": 500, "unit": "g", "category": "grain", "notes": "protein-rich" },
+    { "name": "Frozen mixed veg", "qty": 1000, "unit": "g", "category": "frozen", "notes": "calorie bulk, cheap" },
+    { "name": "Broccoli", "qty": 2, "unit": "count", "category": "veg", "notes": "small heads" },
+    { "name": "Carrots", "qty": 800, "unit": "g", "category": "veg", "notes": "" },
+    { "name": "Sweet potatoes", "qty": 3, "unit": "count", "category": "veg", "notes": "" },
+    { "name": "Onions", "qty": 6, "unit": "count", "category": "veg", "notes": "" },
+    { "name": "Bananas", "qty": 5, "unit": "count", "category": "fruit", "notes": "" }
+  ]
+}
--- a/meal-history.example.json
+++ b/meal-history.example.json
@ -0,0 +1,4 @@
+{
+  "note": "Rolling 7-day log of suggested meals. See SKILL.md / references/meal-history.md. This is an example/empty template — the live file is git-ignored.",
+  "entries": []
+}
--- a/references/eastbourne-shops.md
+++ b/references/eastbourne-shops.md
@ -0,0 +1,32 @@
+# Where to Shop — Eastbourne (value research, 2026)
+
+User is in Eastbourne. Local options: Lidl, Sainsbury's, Co-op, Tesco Express
+(closest), and a local Londis (milk 2L £1.40). Memberships: Tesco Clubcard, Co-op member.
+
+## Price index (Which? 2026, ~93-item standard basket; Lidl = £160.70 baseline)
+| Supermarket | Basket | vs Lidl | Notes |
+|---|---|---|---|
+| Lidl | £160.70 | 1.00x | Cheapest discounter; furthest from user |
+| Tesco (Clubcard) | £188.45 | 1.17x | Clubcard Prices = real discount |
+| Sainsbury's (Nectar) | £187.86 | 1.17x | Mid; Nectar needed for this price |
+| Tesco Express | ~£196–203 | ~1.22–1.26x | Superstore + convenience premium; Clubcard applies |
+| Co-op | ~£209+ | ~1.30x | Membership = annual dividend, not instant |
+| Londis | varies | ~1.25–1.35x | Milk cheap (£1.40/2L); full basket pricier |
+
+## Multipliers used for per-store estimates in the weekly email
+- Lidl: 1.00
+- Tesco Express (Clubcard): 1.22
+- Sainsbury's (Nectar): 1.17
+- Co-op (member): 1.30  (dividend softens over the year, not at till)
+- Londis: 1.30 indicative, flagged rough
+
+## Recommendation logic (single shop)
+- Default: **Tesco Express** — closest to user + Clubcard Prices narrow the gap.
+  Pragmatic given limited mobility during burns recovery.
+- If user prioritises price over proximity: **Lidl** (~£6 cheaper on a ~£28 list).
+- Co-op only if already there for something else; Londis for milk/top-ups.
+
+## Why proximity matters here
+User is a recovering burns victim — a long trip to Lidl may not be feasible daily/weekly.
+The ~17–22% price premium of Tesco Express is often worth the saved trip. The email
+states this trade-off explicitly so he can choose.
--- a/references/email-template.md
+++ b/references/email-template.md
@ -0,0 +1,44 @@
+# HTML Email Template (inline CSS, mobile-friendly)
+
+Copy this scaffold, fill the meal sections, and save to `/tmp/meal_today.html`
+(or `/tmp/meal_shop.html` for the weekly list) before sending.
+
+```html
+<!DOCTYPE html>
+<html lang="en">
+<head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"></head>
+<body style="margin:0;padding:0;background:#f4f6f8;font-family:-apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;color:#1f2933;">
+  <table role="presentation" width="100%" cellpadding="0" cellspacing="0" style="background:#f4f6f8;padding:16px 0;">
+    <tr><td align="center">
+      <table role="presentation" width="100%" cellpadding="0" cellspacing="0" style="max-width:600px;background:#ffffff;border-radius:12px;overflow:hidden;box-shadow:0 1px 4px rgba(0,0,0,0.08);">
+        <tr><td style="background:#0f766e;padding:20px 24px;color:#ffffff;">
+          <h1 style="margin:0;font-size:20px;">Your Meals for Today</h1>
+          <p style="margin:4px 0 0;font-size:13px;opacity:0.9;">Tuesday, 25 August 2026 · high-protein · no red meat</p>
+        </td></tr>
+        <tr><td style="padding:20px 24px;">
+          <!-- MEAL 1 -->
+          <div style="border:1px solid #e4e7eb;border-radius:10px;padding:16px;margin-bottom:16px;">
+            <h2 style="margin:0 0 6px;font-size:17px;color:#0f766e;">🍽 Lunch — Meal Name</h2>
+            <p style="margin:0 0 8px;font-size:14px;color:#52606d;"><strong>Ingredients:</strong> 3 eggs, 100g spinach, 1 tbsp olive oil</p>
+            <p style="margin:0;font-size:14px;color:#3e4c59;line-height:1.5;"><strong>Method:</strong> 1) … 2) … 3) …</p>
+          </div>
+          <!-- MEAL 2 -->
+          <div style="border:1px solid #e4e7eb;border-radius:10px;padding:16px;margin-bottom:16px;">
+            <h2 style="margin:0 0 6px;font-size:17px;color:#0f766e;">🍽 Dinner — Meal Name</h2>
+            <p style="margin:0 0 8px;font-size:14px;color:#52606d;"><strong>Ingredients:</strong> …</p>
+            <p style="margin:0;font-size:14px;color:#3e4c59;line-height:1.5;"><strong>Method:</strong> 1) … 2) …</p>
+          </div>
+        </td></tr>
+        <tr><td style="background:#fafbfc;padding:14px 24px;border-top:1px solid #e4e7eb;font-size:12px;color:#7b8794;">
+          Reply to tell me what you used and I'll update the inventory. — your meal agent
+        </td></tr>
+      </table>
+    </td></tr>
+  </table>
+</body>
+</html>
+```
+
+For the **weekly shopping list**, replace the meal cards with a table:
+`Item | Est. price | Running total`, a `Total: £XX.XX` row, and a one-line note on
+what it covers (protein-first). Keep the same header/footer style.
--- a/references/meal-history.md
+++ b/references/meal-history.md
@ -0,0 +1,38 @@
+# Meal-history logger (used by the daily job)
+
+After composing the two meals (lunch + dinner) and BEFORE sending the email, the daily
+job must record them into `meal-history.json` (same skill dir) so the user can later say
+"remove <day>'s <meal> from inventory" and have precise items deducted.
+
+## Entry shape
+```json
+{
+  "date": "2026-08-27",
+  "weekday": "Thursday",
+  "meal": "lunch" | "dinner",
+  "name": "Human-readable meal name",
+  "items": [ { "name": "Name as in inventory.json", "qty": 1, "unit": "count" }, ... ]
+}
+```
+
+## Rules
+- UPSERT: if an entry with the same `date`+`meal` already exists, replace it (don't
+  duplicate on re-runs).
+- PRUNE: drop any entry whose `date` is more than 7 days before today (keep a true
+  rolling 7-day window).
+- Log ONLY substantive food items actually used in that meal — enough to decrement
+  inventory accurately. Do NOT log pure condiments (olive oil, salt, pepper, spices,
+  garlic, soy sauce, miso, honey, etc.) and do NOT log the optional "third hit" snack.
+- Item `name` values should match `inventory.json` names closely (case-insensitive match
+  on removal) so removal works: e.g. "Chicken breast", "Eggs", "Tinned tuna in veg oil",
+  "Dried red lentils", "Sweet potatoes", "Aubergine", "Red cabbage", "Green pesto",
+  "Leeks", "Orange bell pepper", "Cooked beetroot", "Microwave rice", "Cheese", etc.
+- Use units consistent with inventory.json (count / g / can / portion / pieces / jar).
+  For a half-item use 0.5 (e.g. half a sweet potato = qty 0.5 unit "count").
+- Bump the top-level file with no extra schema — keep the `entries` array only.
+- This does NOT modify inventory.json (that only happens on explicit user removal).
+
+## Example
+Composed lunch "Chicken & Pesto Roast Veg Bowl" using chicken breast (1), sweet potato
+(½), aubergine (½), red cabbage (150 g), green pesto (1 tbsp ≈ 0.1 jar) → record those
+five items under meal "lunch" for today's date/weekday.
--- a/references/protein-sources.md
+++ b/references/protein-sources.md
@ -0,0 +1,43 @@
+# Allowed Protein Sources (no red meat)
+
+High-protein foods to favor, with rough protein density and typical cheap UK buys.
+Use these when suggesting meals and when building the weekly shopping list.
+
+## Animal (non-red-meat)
+- Eggs — ~13g protein each; cheapest protein there is. Buy 12–15 packs.
+- Chicken breast / thigh — ~30g per 100g raw. Buy 500g–1kg trays.
+- Turkey breast / mince — lean, ~29g per 100g.
+- White fish (cod, haddock, basa) — ~20g per 100g; frozen fillets are cheap.
+- Salmon (fresh or tinned) — ~20–25g per 100g; tinned in spring water is budget-friendly.
+- Tinned tuna — ~25g per 100g drained; ~£1/can.
+- Prawns — ~20g per 100g; frozen raw prawns often <£3/300g.
+- Quark / cottage cheese — ~12–14g per 100g; very cheap per gram.
+- Greek yogurt (0%/low fat) — ~10g per 100g; buy large tubs.
+- Skim milk / semi-skimmed — ~3.4g per 100ml.
+- Whey protein powder — ~25g per scoop; good staple for hitting targets.
+
+## Plant
+- Tofu (firm) — ~12–17g per 100g; ~£1.50/block.
+- Tempeh — ~19g per 100g.
+- Edamame (frozen) — ~11g per 100g.
+- Lentils (dry or tinned) — ~9g per 100g cooked; very cheap.
+- Chickpeas (tinned) — ~8g per 100g; ~50p/can.
+- Beans (kidney/black/butter) — ~8g per 100g; ~50p/can.
+- Peanut butter (no added sugar) — ~25g per 100g; cheap calorie+protein.
+
+## Example pairings (per meal)
+- Eggs + Greek yogurt + spinach/peppers (omelette + side).
+- Chicken + lentils + veg (stir-fry / bowl).
+- Tofu + edamame + rice/quinoa (buddha bowl).
+- Tinned tuna + cottage cheese + salad.
+- Salmon + boiled eggs + greens.
+- Whey shake + banana + peanut butter (snack/breakfast).
+- Prawns + chickpeas + tomato (stew).
+- Turkey mince + beans + tinned tomatoes (chilli).
+
+## Rough UK prices (guide for the £30 list)
+Eggs (12) ~£2.20 · Chicken 1kg ~£4.50 · Greek yogurt 500g ~£1.50 ·
+Cottage cheese 300g ~£1.20 · Tofu 396g ~£1.50 · Lentils 500g ~£1.00 ·
+Tinned tuna x2 ~£2.00 · Frozen veg 1kg ~£1.20 · Eggs, milk 2L ~£1.50 ·
+Whey 1kg ~£12 (occasional) · Bananas ~£0.90 · Chickpeas x2 ~£1.00 ·
+Quark 250g ~£1.10 · Frozen edamame 300g ~£1.80.
--- a/references/protein-targets.md
+++ b/references/protein-targets.md
@ -0,0 +1,30 @@
+# Protein Targets — Burns Recovery & Fat Loss
+
+User profile this skill was tuned for: recovering burns victim, healing well,
+~95–100 kg, wants to lose ~15 kg fat while **preserving lean mass**.
+
+## Target math
+- Burns recovery + lean-mass preservation during a deficit: **2 g protein per kg
+  bodyweight per day**.
+- At 95–100 kg → **~190–200 g/day**.
+- Split across 2 main meals: aim **~90–100 g per meal**; any remainder comes from a
+  third hit.
+- **Recompute whenever the user reports a new weight:** target = weight_kg × 2.
+  Keep `diet.bodyweight_kg`, `diet.protein_per_kg`, and
+  `diet.protein_target_g_per_day` in inventory.json in sync with that.
+
+## Fat-loss lever
+- Fat loss = a MILD calorie deficit, NOT protein cutting. Bulk meals with veg; limit
+  oven chips / white bread / added oil; lead with lean protein.
+
+## Closing the gap (third hit)
+When 2 cooked meals fall short of the daily target, name one cheap, fast hit:
+- Whey protein shake (1 scoop ≈ 25 g) — most cost-efficient per gram; ideal staple.
+- Extra eggs (1 egg ≈ 13 g).
+- Greek yogurt 150 g (≈ 15 g) or cottage cheese / quark.
+- Tinned tuna (≈ 25 g) or skim milk.
+
+## Why red meat is excluded from BUY lists
+User prefers to stop buying red meat (lamb / pork / beef / bacon / gammon). Red meat
+ALREADY in stock is still cooked and suggested so it isn't wasted — it is never
+re-purchased. Encode this as: usable-if-in-stock, never-re-buy.