/Coffee

name: Coffee
metadata:
  short-description: "Recommend and log coffee matched to the user's written taste profile and brewing gear; advise on brewing. Use Restaurants for cafe visits; excludes purchases."
version: 1.1.0
evals:
  manual:
    reason: "Coffee recommendations depend on the user's current corpus, brewing gear, and taste feedback rather than a deterministic fixture."
    falsifier: "A recommendation conflicts with a hard rule in the corpus Taste Profile or with the available gear, omits a material preparation constraint, or is rejected after the specified brew feedback."
description: Learns the user's coffee taste as a written corpus plus their brewing gear, and uses both to recommend coffees, discover new ones that fit, answer brew questions, and log what they drink. USE WHEN my coffee, coffee taste, what coffee do I like, recommend a coffee, coffee like X, what should I drink, find a coffee, new coffee, discover coffees, beyond my usual roaster, my coffee gear, my grinder, my brewer, my brew setup, how should I brew, brew ratio, add a coffee, log this coffee, update my coffee list. NOT FOR ordering coffee or cafes (Restaurants), audio or studio gear.

Coffee

Holds the user's coffee taste as a durable corpus, plus their brewing gear, and uses both to recommend coffees that fit, discover new coffees next to the ones they love, answer gear and brew questions, and grow the corpus as they feed in more coffees. Roasters describe beans in language that buries whether a coffee fits a particular palate, so picks are screened against the written profile instead of guessed from memory.

Ideal State

• Every pick, find and gear answer is screened against the corpus and the gear notes read for that request, never against taste recalled from memory.
• Nothing that breaks a hard rule in the corpus Taste Profile (roast range, rejected flavors, brew methods the user does not use) is ever offered as a fit, and every suggestion says in one line why it fits the profile.
• Confirmed favorites (⭐) and unconfirmed candidates (👂) never blur: only the user's own word makes a coffee ⭐.
• The corpus grows only with what the user stated, so it stays ground truth.

Intent Routing

| Intent | Trigger | File | |--------|---------|------| | **Recommend** | "recommend a coffee", "what coffee should I get", "coffee like X", "what should I drink" | `Intents/Recommend.md` | | **DiscoverCoffees** | "new coffees I'd like", "discover coffees", "what else fits my taste", "beyond my usual roaster", "broaden my coffee" | `Intents/DiscoverCoffees.md` | | **AddCoffee** | "add to my coffee", "log this coffee", "I love X now", "update my coffee list" | `Intents/AddCoffee.md` |

| File | Read when | |------|-----------| | `Setup.md` | first-time setup: the config file, the taste corpus format, and a read-only proof |

For a plain "what do I like?" or "what's my gear?" lookup, read the corpus or the gear notes and answer; no intent needed.

Data & Config

Read `<configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Coffee/Config.md` first (`configRoot` is `$CLAUDE_CONFIG_DIR` when set, else `~/.claude`). It names two files, and both are ground truth:

• **Taste corpus** (Config.md `Corpus:` line; default `<configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Coffee/CoffeeReference.md`). Human-editable markdown. Its `## Taste Profile` section holds the user's own words and the screening rules every intent applies, hard rules marked as such. Rows grow in `### Batch N` sections with two source tags: **⭐ favorite** (they love it) and **👂 candidate** (fits the profile or was recommended, unconfirmed).
• **Gear notes** (Config.md `Gear:` line; default the `## Coffee` section of `<configRoot>/LIFEOS/USER/GEAR.md`). Grinders, brewers and the brew defaults tuned to the profile. Read it before any brew or gear answer, and write gear updates back there, never into this skill.

Neither file holds secrets, and the skill needs no account. When Config.md or the corpus is missing, say so, answer from what the request states, and point to [Setup.md](Setup.md).

Gotchas

• **Brew method outranks a flavor match.** A coffee the user cannot brew the way they brew is out, however well the tasting notes match: an espresso blend for someone who only brews filter, or a light filter roast for someone who only pulls shots. The Taste Profile or the gear notes say which methods count.
• **A spoken name can differ from the roaster's listed name.** Treat a near-match as the same coffee, and record the alias in the corpus Notes column so the next lookup finds it.
• **Only ⭐ rows are confirmed favorites.** Other coffees from a favorite roaster stay 👂 candidates: say they "fit your profile," never that the user loves them, until the user says so.
• **Recommend is request-driven** (a pick for now or a mood); **DiscoverCoffees is profile-driven** (broaden beyond what they have). Don't collapse them.

Examples

**Example 1: Recommend a coffee**

User: "what coffee should I order?"
→ Recommend intent
→ A ranked pick (a confirmed ⭐ first when it fits the ask, then fitting candidates), each with one line on why it fits

**Example 2: Discover new coffees**

User: "what other coffees would I like besides my usual?"
→ DiscoverCoffees intent
→ A few finds not yet in the corpus, as "Because you like <anchor> → <roaster blend>" lines tagged safe fit or stretch

**Example 3: Gear / brew question**

User: "how should I brew for the taste I like?"
→ Reads the gear notes (no intent)
→ The brewer, ratio and grind the gear notes give for that profile, with one line tying each to the profile

**Example 4: Grow the corpus**

User: "add Example Roasters' Harbor Blend to my coffee list — I loved it"
→ AddCoffee intent
→ A dated ⭐ row in the corpus with what the user stated, counts updated, and a one-line confirmation