New Coffee Research Skill

Systematically research a coffee and propose starting extraction parameters.

Adapted from gaggimate-barista by Charlie Hall.

Workflow

1. GATHER Coffee Info

If photo provided:

•Extract from label: roaster, coffee name, origin, roast date, tasting notes
•Note any visible processing info (washed, natural, etc.)

If text provided:

•Parse roaster and coffee name
•Ask for roast date if not mentioned

2. RESEARCH via Web Search

Search for the specific coffee to find:

•Processing method (washed, natural, honey, anaerobic)
•Origin details (country, region, altitude if available)
•Variety (Bourbon, Gesha, Caturra, etc.)
•Roast level (light, medium, dark) — infer from tasting notes if not stated
•Roaster's tasting notes

See: references/RESEARCH_CHECKLIST.md for detailed research patterns, origin profiles, and variety extraction guidance.

3. SYNTHESIZE Recommendations

Build recommendations using:

•Temperature: From ESPRESSO_BREWING_BASICS.md roast guidelines
•Pressure: From PRESSURE_GUIDE.md roast × processing matrix
•Ratio: From processing method patterns (washed: 1:2, natural: 1:2-2.5, etc.)
•Profile: From PROFILE_LIBRARY.md by roast/process, adjusted for correct pressure
•Dose: Based on user's basket size. Dose = basket size (e.g., 18g basket → 18g dose). Don't underdose.

4. CONFIRM with User

Before finalizing, ask:

"This [process] [origin] typically shines with [approach]. Would you like to start there, or prefer a more conservative/adventurous approach?"

Options to offer:

•Conservative: Classic profile, standard ratio
•Recommended: Profile matched to bean characteristics
•Adventurous: Bloom profile or turbo shot if appropriate

5. UPLOAD Profile (if requested)

Use MCP tool to upload:

code

manage_profile(action="create", profile_name="[Coffee Name] [AI]", temperature=X, phases=[...])

Always add [AI] suffix to profile names.

6. UPDATE Coffee Tracking

After researching and setting up a new coffee, offer to create or update the user's Coffee Tracking document — a markdown artifact they can save and re-upload to the project as a knowledge file. Include:

•Bean profile (roaster, origin, process, roast level, variety, tasting notes, roast date)
•Starting parameters (temp, grind, ratio, profile, dose)
•Space for tasting notes table

Output Format

code

## Coffee Research: [Name]

### Bean Profile
- **Roaster:** [roaster]
- **Origin:** [country, region]
- **Process:** [washed/natural/honey/anaerobic]
- **Roast Level:** [light/medium/dark]
- **Variety:** [if known]
- **Tasting Notes:** [from roaster]
- **Days Off Roast:** [X days, or "unknown"]

### Recommended Starting Parameters
| Parameter | Value | Reasoning |
|-----------|-------|-----------|
| Temperature | X°C | [roast level rationale] |
| Grind | Start at [general guidance] | [reasoning] |
| Ratio | 1:X | [process rationale] |
| Profile | [name] | [why this profile] |
| Dose | Xg in → Xg out | [basket size rationale] |

### What to Watch For
- [Specific guidance for first shot based on bean characteristics]
- [What taste outcomes to expect]
- [When to adjust and in which direction]

Quick Reference

User says: "I got a new bag of [coffee]" Action: Extract info → research → recommend → confirm → upload profile

User shares photo: Action: Vision extract → research → recommend → confirm → upload profile