agentsclimarketplace

Market recon

Skill meikocho1/alchemy-marketing-skills/skills/market-recon

Rory Sutherland's psycho-logic as Claude skills — solve the human perception, not the metric. Reframing, costly signaling, counterintuitive tests, experience design.

Install
npx -y skills add meikocho1/alchemy-marketing-skills --skill market-recon

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

The live fieldwork layer for psycho-logic — go look at the actual target market NOW instead of reasoning from your training-data stereotype of it. Use when a psycho-logic move needs grounding in a specific place: the user asks 'what do competitors in [region/country] actually do', 'what's the real price band / norm here', 'how do local leaders position themselves', 'research this market before we localise', 'what signals trust to buyers in X', or is about to launch/adapt in a market you haven't studied. Runs structured web research in the local language — local competitors and their signals, price bands, category conventions, review/trust sources, local terminology, taboos and regulations — and synthesises a compact perception profile the four moves consume. Inspired by Rory Sutherland's *Alchemy*. Routed to from psycho-logic; pair with cultural-context (the lens that tells you what to look for). 日本語・中文の相談（「現地の実態を調べて」「调研当地市场」）にも使う。

SKILL.md

6.5 KB, as published. Nobody here has run it

Market Recon — go look, don't assume

cultural-context gives you hypotheses about how a market thinks. This skill checks them against reality by going and looking — because your model's idea of "the German funeral market" or "how Thai buyers judge premium" is a stale average, and the cheap edge is in the specifics only local sources show. Stated stereotype is as unreliable as stated preference: gather revealed, current, sourced data.

The principle

Perception is local and current, so it has to be observed, not recalled. Two failure modes to avoid:

  • Reasoning from the stereotype. "Japanese buyers value quality" is true and useless — it doesn't tell you what this category's leaders actually signal, or what the price band is this year. Go find the specifics.
  • Reading the market in the wrong language. English-language summaries of a non-English market are a translation of a translation. Search in the local language, read local sources, note the words locals actually use.

What to gather (the recon checklist)

Aim each search at a lever the moves will pull:

  • Local players & positioning — who leads this category in this place, how they describe themselves, what promise they lead with. (feeds reframing)
  • Price band & framing — the real range, and how price is shown (per-day, all-in, tiered, hidden until contact). (feeds reframing)
  • Trust signals in use — guarantees, certifications, longevity claims, awards, the local proof-of-credibility everyone leans on. (feeds costly-signaling)
  • Trust locus & reviews — where buyers actually check: which review platforms, forums, associations, or personal/institutional channels. (feeds costly-signaling)
  • Category conventions & taboos — the unwritten "you must / you never" of this category here, plus regulations and sacredness lines. (constrains every move)
  • Felt-moment pain points — what local buyers complain about in the journey (found in reviews, forums, complaints). (feeds experience-design)
  • Local terminology — the exact words buyers and sellers use, for copy that sounds native rather than translated.

How to apply

  1. Fix the target. Market = place (country / region / urban-rural) × segment × category. The narrower, the more useful the recon.
  2. Pull the hypotheses from cultural-context so you know which dials to verify, not just collect trivia.
  3. Run structured web searches, in the local language. Use the web tools (WebSearch / WebFetch — load via ToolSearch if not already available). Query local competitors, price pages, review sites, forums, trade/association pages, and regulator pages. Read local-language sources directly.
  4. Synthesise a perception profile, not a link dump: for this market — what signals trust, what "premium" and "cheap" look like, the anchors on offer, the felt-moment pains, the taboos, and the native vocabulary. A page, sourced.
  5. Stamp recency and cite sources. Note the date of each key fact and flag what's uncertain. Anything still a hypothesis goes to counterintuitive-tests for a cheap behavioural check before you bet on it.
  6. Hand the profile to the moves. reframing / costly-signaling / experience-design now run on local reality, not a guess.

日本語の使用例

  • 「海外(または国内の別地域)で展開したいが、現地の実態を知らない」→ 記憶や一般論で組み立てず、現地語でWeb調査。現地の主要プレイヤー・価格帯・保証や資格などの信頼シグナル・レビューの見られ方を集め、"知覚プロファイル" に落とす。
  • 「競合と横並びで差別化できない」→ まず実際の競合が何をシグナルしているかを現地情報で棚卸し。空白のポジション（誰も出していない正直な弱点開示・全部込み価格など）が見えてから reframing / costly-signaling に渡す。
  • 「現地の相場観がわからない」→ 価格の"範囲"だけでなく見せ方（1日あたり/総額/段階/問い合わせまで非表示）まで調べる。価格フレームは市場ごとに違う。
  • 葬儀/シニア領域：関東/関西など地域単位で慣習と相場が違う。地域の葬儀社の打ち出し、口コミ・紹介・寺や地域評判といった信頼の所在、遺族の不満（journey の痛点）を現地ソースで集め、experience-design と costly-signaling の材料にする。タブー・法規制（表示や許認可）も必ず確認。

Cross-check against the canon

Sanity-check recon findings against these; if one contradicts your read, name it and justify it.

  • Paul Samuelson, revealed preference — weight what local players do (their pages, prices, signals) over what anyone says about the market.
  • Steve Blank, "get out of the building" — the customer-development canon for the same instruction: facts live outside your assumptions.
  • Kahneman, WYSIATI ("what you see is all there is") — the bias this skill exists to counter: a confident market picture built from the few sources you happened to see. Stamp recency, cite sources, flag gaps.

Related skills

  • cultural-context — the lens that tells you which dials to verify here; run it first
  • psycho-logic — the router; recon grounds its moves in the real target market
  • counterintuitive-tests — turn recon's remaining hypotheses into cheap behavioural tests
  • reframing / costly-signaling / experience-design — consume the perception profile this produces

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.