customers-yachts-wall-street-schwed
This Claude Code skill applies Fred Schwed Jr.'s framework for identifying conflicts of interest in financial advice, forecasts, and complex products. It routes user questions about advisor trustworthiness, forecast reliability, and incentive alignment to specialized diagnostic modules that examine who profits from recommendations, separate investment from speculation, compare complex strategies against simpler alternatives, and assess whether advice is aligned with the user's interests rather than the advisor's commission structure.
git clone --depth 1 https://github.com/simbajigege/book2skills /tmp/customers-yachts-wall-street-schwed && cp -r /tmp/customers-yachts-wall-street-schwed/skills/customers-yachts-wall-street-schwed ~/.claude/skills/customers-yachts-wall-street-schwedSKILL.md
# Where Are the Customers' Yachts? Conflict Orchestrator ## Skill Purpose Apply Fred Schwed Jr.'s Wall Street conflict framework to financial advice, forecasts, complex products, speculation, and broker incentives. This is a modular skill because the major user questions have distinct triggers, checks, and output formats. ## Routing Rules | User intent | Route to | |---|---| | Advisor, broker, planner, fund salesperson, fiduciary conflict | `subskills/conflict-diagnostic.md` | | Market forecast, analyst target, newsletter call, macro prediction | `subskills/forecasting-illusion.md` | | Structured product, annuity, hedge fund, complex strategy, high fees | `subskills/complexity-racket.md` | | Hot tip, meme stock, crypto group, momentum trade, panic selling | `subskills/speculator-psychology.md` | | High turnover, excessive trading, commission incentives | `subskills/broker-activity.md` | ## Execution Rules 1. Ask who earns money if the user acts. 2. Separate investment from speculation before giving advice. 3. Prefer simple, low-cost alternatives unless complexity has a clear job. 4. Treat confident forecasts as sales artifacts until track record and accountability are shown. 5. Do not provide personalized financial advice; frame outputs as analytical checks. ## Multi-Module Output Format - Conflict identification: who earns what. - Schwed test applied: relevant module and checklist. - Simple alternative: lower-conflict path. - Verdict: aligned, partially aligned, or misaligned. ## Subskill Status All subskills are required and present in `subskills/`. ## CITATION RULES Use quotes only when the user asks for source grounding or when a claim needs attribution. Reference quote anchors by topic file and anchor. Keep quoted excerpts short. - `conflicts-incentives-quotes.md`: `#customers-yachts-question`, `#prophecy-commissions`, `#broker-influences-customer`, `#securities-created-to-sell`, `#investment-counsel-fees`, `#not-paid-in-commissions`, `#advice-given-received`, `#choosing-investments-competence` - `forecasting-speculation-quotes.md`: `#difficult-answer-dont-know`, `#prediction-loses-savings`, `#just-a-croupier`, `#charts-useful-accuracy`, `#probability-and-risk`, `#buy-boom-sell-depression`, `#panic-buy-stocks`, `#dying-rich` ## Critical Reminders - The first question is always incentive alignment. - Confidence is not accuracy. - Complexity often prevents comparison. - Do not reproduce long source passages.
Restructures a chaotic or overgrown MEMORY.md into a clean 2-layer architecture based on how Claude Code's autoDream system organizes memory — a lightweight pointer index (always loaded) and topic files (loaded on demand). Stale or superseded memories are deleted or corrected in place — not archived. Use this skill whenever the user says \"clean up MEMORY.md\", \"reorganize my memory files\", \"MEMORY.md is getting too long\", \"fix my memory structure\", or when you observe that MEMORY.md exceeds 200 lines, contains full paragraphs instead of pointers, or mixes index entries with topic content.
Define agent tools using the fail-closed design pattern — unified name/schema/security/execution in one class, with three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new agent tool, add permission or validation logic to an existing tool, or asks about 'build a tool', '定义一个工具', 'create a tool for X', '工具定义'. Framework-agnostic: works with hermes-agent, LangChain, or any Python agent framework.
Analyzes Chinese public company financial statements (balance sheet, income statement, cash flow) to assess asset quality, profit authenticity, cash flow health, solvency, and overall investment value. Use when the user provides financial data or a company name and asks whether financials are healthy, whether profits are real, whether there are red flags, or whether the company is a good investment. Based on the book "一本书读懂财报" by Xiao Xing (Tsinghua University).
>
Use Business Adventures for "why did this fail?", "analyze this crisis", "what pattern applies?", or "what would Brooks notice?
Apply John Bogle stewardship capitalism logic to separate investing from
Apply John Bogle index investing rules for low-cost funds, asset allocation,
Developer implementation guide for adding compact memory to an Agent — covers fork agent pattern for compaction, trigger strategy, summary format design, and memory restoration in subsequent sessions. Use when a developer asks how to implement compact memory, context compression, or memory persistence in their agent built with Claude Agent SDK or Anthropic API.