Answer espresso knowledge questions from authoritative knowledge files. Use when the user asks about: temperature, pressure, ratios, grind settings, freshness, extraction theory, puck prep, channeling, baskets, decaf, blends, milk steaming, drink specs, profiles, shot styles, or any espresso concept. Routes to the correct file and answers from its content rather than from memory or training data.
Diagnose espresso extraction issues by correlating machine telemetry with taste feedback. Use when user says: "/diagnose", "what went wrong", "analyze that shot", "why did it taste [sour/bitter/flat]", "my shots are inconsistent", or asks about pressure spikes, flow issues, or extraction problems. Fetches shot data via analyze_shot MCP tool, interprets patterns, and provides actionable recommendations.
Gather shot feedback, analyze extraction, recommend adjustments, and record results. Use when user says: "/feedback", "I just pulled a shot", "how was that", "it tasted [sour/bitter/flat/good]", provides a star rating, shares taste observations, or asks "what should I adjust" after a shot. Owns the full shot feedback loop: gathering, analysis, grind map updates, tasting notes, and drink format.
Research a new coffee bean and propose starting extraction parameters. Use when: (1) user shares a new bag of coffee (photo, name, or description), (2) user says "/new-coffee", "new beans", "dialing in a new coffee", (3) user asks "where should I start with this coffee". Accepts bag photos (extracts info via vision) or text descriptions. Researches origin, process, roast level via web search, checks grind-map.md for similar coffees, then recommends temperature, grind, ratio, and profile.