Update to august

{
  "name": "august-pricing-check",
  "description": "Run a Van Westendorp-style pricing sensitivity study across August twins for a product, plan, or feature. Ask each twin the four canonical price questions (too cheap = quality suspect, bargain = good deal, expensive = would pause, prohibitively expensive = wouldn't buy) and aggregate into the acceptable price band plus the four inflection points (PMC, PME, OPP, IPP). Better than eyeballing one twin's answer. Use whenever the user wants directional price sensitivity, willingness-to-pay, or a price-band read from twins instead of live shoppers. Triggers on: \"price check with twins\", \"van westendorp\", \"pricing sensitivity\", \"how much would twins pay\", \"what should I charge\", \"price band\", \"/august-pricing-check\".",
  "included_files": [],
  "skill_md_contents": "---\nname: august-pricing-check\ndescription: >\n  Run a Van Westendorp-style pricing sensitivity study across August twins for\n  a product, plan, or feature. Ask each twin the four canonical price questions\n  (too cheap = quality suspect, bargain = good deal, expensive = would pause,\n  prohibitively expensive = wouldn't buy) and aggregate into the acceptable\n  price band plus the four inflection points (PMC, PME, OPP, IPP). Better than\n  eyeballing one twin's answer. Use whenever the user wants directional price\n  sensitivity, willingness-to-pay, or a price-band read from twins instead of\n  live shoppers. Triggers on: \"price check with twins\", \"van westendorp\",\n  \"pricing sensitivity\", \"how much would twins pay\", \"what should I charge\",\n  \"price band\", \"/august-pricing-check\".\n---\n\n# August Pricing Check\n\nVan Westendorp-style pricing sensitivity across N=8–12 August twins. Returns\nthe acceptable price band and its four inflection points, with representative\nquotes for each band. Tools live under the August MCP.\n\n**What Van Westendorp gives you:**\n- **PMC** (Point of Marginal Cheapness) — below this, quality is suspect\n- **PME** (Point of Marginal Expensiveness) — above this, buyers walk\n- **OPP** (Optimal Price Point) — resistance is balanced (too-cheap = too-expensive)\n- **IPP** (Indifference Price Point) — where \"bargain\" = \"expensive\" (typical\n  actual paid price)\n\n**When to use:** setting an anchor price, sanity-checking a plan tier, testing\na promo, comparing two SKUs' willingness-to-pay.\n\n**When NOT to use:** you only have one twin available (use `/august-feedback`\ninstead), the product has no clear price yet (do concept work first), or you\nneed statistical significance (use a real survey — twins are directional).\n\n---\n\n## STEP 1 — Get the artifact and anchor\n\nBefore touching MCP, confirm:\n\n- **What is being priced?** A specific product (name, SKU, description), a\n  subscription plan (features + billing cadence), a bundle, a feature add-on.\n- **Anchor price** (optional but helpful) — the user's current price or\n  candidate range. If none, twins will float; that's fine but noisier.\n- **Currency / market** — default USD unless the user specifies.\n- **Audience org** — which brand's shoppers? If ambiguous, ASK.\n\nIf the artifact is thin (\"what should I charge for a supplement?\"), push back\nonce for a real description — twins price better with concrete material.\n\n---\n\n## STEP 2 — Pick the org\n\nCall `list_organizations`. Match the audience:\n\n- Consumer product / plan / bundle → the relevant **brand org**\n- B2B / dashboard / Fermat platform pricing → **Fermat org** (dashboard-user\n  twins)\n\nIf ambiguous, ASK via a concise question with the top 2–3 orgs as options.\n\n---\n\n## STEP 3 — Pick twins (8–12) OR run as focus group\n\nCall `list_twins` for the org. Aim for **8–12 twins** with variety across:\nbuying stage, budget tier, category affinity, demographic slice. Homogeneous\npanels produce narrow bands; diverse panels surface the real spread.\n\n**Two execution paths — pick one:**\n\n- **Fan-out interviews** (default, more control): for each twin, call\n  `start_interview(twin_id)` and then `ask_question(interview_id)` with the\n  four VW questions bundled. Faster to parse, cleaner attribution.\n- **Focus group** (use when the user wants cross-talk / disagreement signal):\n  use `list_focus_groups` to select an existing ready group, then\n  `start_focus_group` → optionally `add_focus_group_stimuli` for Figma URLs\n  → `run_focus_group_round` with the artifact context and four VW questions\n  → `end_focus_group` → `get_focus_group_results`. If no suitable ready group\n  exists, ask the user to configure one in August or use fan-out interviews.\n\nIf you can't find 8+ suitable twins in the org, note the sample size in the\noutput and continue — don't fabricate.\n\n---\n\n## STEP 4 — Ask the four Van Westendorp questions\n\nFor each twin, ask (adapt phrasing to the artifact):\n\n1. **Too cheap** — \"At what price would you think this is so cheap that you'd\n   doubt its quality?\"\n2. **Bargain** — \"At what price would you think this is a bargain — a great\n   deal for the money?\"\n3. **Expensive** — \"At what price would you think this is starting to get\n   expensive, so that it's not out of the question, but you'd have to think\n   about it?\"\n4. **Prohibitively expensive** — \"At what price would you think this is so\n   expensive that you would not consider buying it?\"\n\nAlways pass the full artifact context in the question payload. Ask for a\none-line rationale per price so you have quotable material.\n\n---\n\n## STEP 5 — Aggregate\n\nParse each twin's four dollar values into a table. Then compute:\n\n- **PMC** — intersection of \"too cheap\" (descending cumulative) and\n  \"not cheap = bargain-or-higher\" (ascending cumulative). Below this,\n  more people say \"too cheap\" than \"acceptable.\"\n- **PME** — intersection of \"expensive\" (ascending cumulative) and \"not\n  expensive\" (descending cumulative). Above this, more people say \"too\n  expensive\" than \"acceptable.\"\n- **OPP** — intersection of \"too cheap\" and \"prohibitively expensive\"\n  cumulative curves. Balance point of extreme resistance.\n- **IPP** — intersection of \"bargain\" and \"expensive\" cumulative curves.\n  Median indifference price.\n\nThe **acceptable band** is PMC → PME. OPP and IPP sit inside that band.\n\nIf a twin gave nonsense answers (all four the same, non-monotonic), drop\nthem from the aggregate but note it.\n\n---\n\n## STEP 6 — Return the output\n\nUse this template. Don't dump raw transcripts.\n\n```\n## Pricing Check — {artifact name}\nOrg: {org}  |  Twins: N={count}  |  Anchor: {price or \"none\"}\n\n### Acceptable band: ${PMC} – ${PME}\n- OPP (optimal): ${OPP}\n- IPP (typical paid): ${IPP}\n\n### Price bands with rationale\n- **Too cheap (< ${PMC})** — \"{one representative twin quote}\"\n- **Bargain (${PMC} – ${IPP})** — \"{quote}\"\n- **Acceptable / thinking about it (${IPP} – ${PME})** — \"{quote}\"\n- **Prohibitive (> ${PME})** — \"{quote}\"\n\n### Notable spread\n{1–2 lines on twin variance — e.g. \"budget-tier twins capped ${PME} $10 lower\nthan premium-tier twins\"}\n\n### Caveat\nN={count} twins is directional, not statistically significant. Validate the\nband with a real survey or A/B before locking a price.\n\n### Source\nOrg: {org}  |  Twins: {twin_1}, {twin_2}, ... {twin_N}\n```\n\nIf the bands overlap weirdly (e.g., PMC > PME, or IPP outside the band), say\nso plainly — that's a signal the twins disagree wildly and the product may\nnot have a clear price point yet.\n"
}