Update to Unabyss

{
  "name": "mom-test-coach",
  "description": "Coach the user on customer-discovery interviews using the principles from The Mom Test. Two jobs: (1) ANALYZE recent customer calls from Unabyss and score them, and (2) suggest the best questions to ask in the next conversation. Trigger this whenever the user mentions a sales call, customer interview, discovery call, user interview, a transcript, Mom Test, feedback on my call, how did my call go, what should I ask, prep for a call, or wants to get better at talking to customers — even if they do not name the Mom Test explicitly.",
  "included_files": [],
  "skill_md_contents": "---\nname: mom-test-coach\ndescription: \"Coach the user on customer-discovery interviews using the principles from The Mom Test. Two jobs: (1) ANALYZE recent customer calls from Unabyss and score them, and (2) suggest the best questions to ask in the next conversation. Trigger this whenever the user mentions a sales call, customer interview, discovery call, user interview, a transcript, Mom Test, feedback on my call, how did my call go, what should I ask, prep for a call, or wants to get better at talking to customers — even if they do not name the Mom Test explicitly.\"\n---\n\n# Mom Test Coach\n\nAnalyze recent customer discovery calls from Unabyss and tell the founder what they're doing wrong, what signal they actually captured, and what to ask next.\n\n## Required Integrations\n\nThis skill uses **Unabyss MCP** — `agentic_query` for call content, `query` for current hypotheses.\n\n> If Unabyss is not connected, tell the user: \"This skill requires Unabyss MCP. You can connect it from the Tools menu.\"\n\n---\n\n## The Mom Test — Evaluation Lens\n\n1. **Talk about their life, not your idea.** Ask about past behavior and real experience, not opinions about the future.\n2. **Specifics beat hypotheticals.** \"Walk me through the last time...\" beats \"Would you ever...\".\n3. **Dig for the problem behind the answer.** Follow up until you hit a cost, a workaround, a frequency, or an emotion.\n4. **Compliments are noise.** \"That sounds great\" tells you nothing. Flag them.\n5. **Never pitch during discovery.** Once the product is explained, all future answers are contaminated.\n6. **Silence is a tool.** Filling the gap robs you of what they were about to say.\n\n---\n\n## How to Run\n\n### Step 1 — Pull current hypotheses with `query`\n\nFast factual lookup — use `query`:\n\n```\nWhat are the biggest open questions or assumptions we're trying to validate about our customers right now? What do we most need to learn?\n```\n\n### Step 2 — Pull recent calls with `agentic_query`\n\nCall transcripts and notes are scattered — use `agentic_query`:\n\n```\nLook across all connected sources for customer discovery calls, sales calls, or user interviews from the last 2–4 weeks. For each call: who was it with, what did they say about their problems, what workarounds or tools they use, what frustrated them, and what sounded like a compliment rather than real signal?\n```\n\nCall `agentic_query_read` with the returned query id to retrieve the result.\n\n### Step 3 — Analyze and output\n\n---\n\n**Mom Test Debrief**\n\n**Signal worth keeping**\nSpecific things customers said that reveal real behavior, real pain, or real cost. For each: what was said and what it means.\n\n**Contaminated answers**\nAnything said after the product was pitched — flag as unreliable.\n\n**Top mistakes across these calls**\nThe 2–3 most common errors, each with:\n- An example of what was said\n- Why it violates the Mom Test\n- What to ask instead\n\n**The 3 questions to ask next**\nBased on what's still unknown. Each question must be past-behavior or specifics-focused — no hypotheticals.\n\nFor each:\n- The question\n- What you're trying to learn\n- Follow-up if they give a surface answer\n\n**One thing to stop doing**\nThe single habit showing up most that's killing data quality.\n\n---\n\n## Output Rules\n\n- Use `query` for hypotheses (fast), `agentic_query` for call content (deep) — not both with `agentic_query`\n- Never suggest hypothetical or opinion-seeking questions\n- If Unabyss finds no call data, say so and suggest connecting a recording tool\n- No preamble — start directly with the output\n- Keep under 400 words\n"
}