Update to Unabyss

{
  "name": "value-proposition-extractor",
  "description": "Extract and organize all value propositions from across the user's connected sources — website, sales calls, customer wins, founder writing, and approved messaging — into a structured inventory mapped to personas and use cases. Use this skill whenever the user wants to know what their product's value props are, needs to brief a copywriter or agency, wants to improve their messaging, or asks what they should be highlighting in outreach, on their site, or in sales conversations.",
  "included_files": [],
  "skill_md_contents": "---\nname: value-proposition-extractor\ndescription: \"Extract and organize all value propositions from across the user's connected sources — website, sales calls, customer wins, founder writing, and approved messaging — into a structured inventory mapped to personas and use cases. Use this skill whenever the user wants to know what their product's value props are, needs to brief a copywriter or agency, wants to improve their messaging, or asks what they should be highlighting in outreach, on their site, or in sales conversations.\"\n---\n\n# Value Proposition Extractor\n\nExtract every meaningful value proposition from across all connected sources — not just the website, but sales calls, customer wins, founder writing, and approved messaging — and organize them into a structured inventory the user can act on immediately.\n\nThe difference from generic extraction: Unabyss surfaces what actually resonates with real customers, not just what the founder thinks is the headline.\n\n## Required Integrations\n\nThis skill uses **Unabyss MCP** and **web search**.\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## How to Run\n\n### Step 1 — Check for an existing export\n\nCall `export_list` first. If a value proposition or messaging export already exists and is fresh, call `export_read` — no need to regenerate.\n\n### Step 2 — Pull internal signals with `agentic_query`\n\nValue props are scattered across many sources — use `agentic_query`:\n\n```\nLook across all connected sources for every claim, benefit, outcome, or advantage associated with our product. Find:\n\n- Claims made on the website or landing pages\n- Benefits mentioned in sales calls — what the founder or team said the product does\n- Outcomes customers reported — specific results, metrics, or improvements they mentioned\n- Phrases or framings that consistently appeared in positive customer responses\n- Language used in launch copy, Product Hunt posts, or public announcements\n- Any \"aha moment\" descriptions — what customers said when they first got value\n- Objections that were overcome — what benefit convinced a skeptical prospect\n\nReturn the actual language used, not paraphrases. Include the source and context for each.\n```\n\nCall `agentic_query_read` to retrieve results.\n\n### Step 3 — Web research\n\nSearch the product's live website and any public launch posts to capture official positioning. Prioritize the founder's own words.\n\n### Step 4 — Organize into the inventory\n\nDeduplicate, cluster by theme, and structure as:\n\n---\n\n**Value Proposition Inventory — [Product Name]**\n*[Date] · [N] value props extracted*\n\n---\n\n**Core value props** *(the 3–5 that appear most consistently and resonate most)*\n\nFor each:\n- **The claim:** One clear sentence\n- **The evidence:** Where it came from — customer quote, sales call outcome, website copy\n- **Best for:** Which persona or situation this lands hardest with\n- **In outreach:** How to frame it in a cold email or sales conversation\n\n---\n\n**Supporting value props** *(real but less universal)*\n\nListed with source and best use context.\n\n---\n\n**Untested claims** *(mentioned internally but not yet validated by customers)*\n\nFlag these — they're hypotheses, not proven props.\n\n---\n\n**What customers actually say** *(their words, not yours)*\n\nDirect quotes from customers describing the value. These are the most powerful — exact language for testimonials, case studies, and website copy.\n\n---\n\n### Step 5 — Save the inventory\n\nCall `export_create_from_text` to save the inventory as an export — so it can be loaded instantly by other skills (content-engine, launch-context-brief, investor-outreach) without regenerating.\n\n---\n\n## Output Rules\n\n- Use `agentic_query` for internal signals, web search for public positioning\n- Always check `export_list` first — regenerating an existing inventory wastes credits\n- Distinguish between proven props (customer-validated) and internal claims (not yet validated)\n- Customer language takes priority over founder language — their words are more credible\n- No preamble before the inventory header\n- Save with `export_create_from_text` after generating\n"
}