跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
浏览器与自动化

investing-from-darwin

Apply Pulak Prasad evolutionary investing rules for avoiding big losses,

simbajigege · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add simbajigege/book2skills --skill investing-from-darwin

技能说明


name: investing-from-darwin description: Apply Pulak Prasad evolutionary investing rules for avoiding big losses, buying resilient quality, rejecting fragile forecasts, and being very lazy. license: Skill distillation for personal/educational use. Do not reproduce source passages verbatim.

What I Learned About Investing from Darwin — Evolutionary Investing Skill

Knowledge source: What I Learned About Investing from Darwin by Pulak Prasad.

Overview

Use this skill to evaluate investments through evolutionary survival logic: avoid big risks, buy high-quality resilient businesses at fair prices, and stay very patient. It supports investors who want to avoid permanent capital loss, resist over-trading, and prefer robustness over fragile forecasting.

When to Use This Skill

Use this skill when the user asks:

  • "Is this business resilient enough to own?"
  • "What big risks could permanently hurt this investment?"
  • "Is this cheap stock a trap?"
  • "Should I rely on this DCF?"
  • "How patient should I be?"
  • "How would Darwin-inspired investing judge this company?"

Core Principle

Investment survival comes before investment brilliance. Like evolution, investing rewards robustness, adaptation, and patience more reliably than precision forecasts, frequent action, or bargain-hunting in fragile businesses.

Workflow Inventory

WorkflowUser question patternInputsStepsOutputIndependent trigger?Distinct references?Triage scoreShould be subskill?Reason
Big-risk screen"What could kill this investment?"Business model, debt, disruption, governance, valuationIdentify permanent-loss scenariosAvoid/continue risk verdictYesYes3NoFirst rule of the same investing framework.
Quality-at-fair-price review"Is this a quality company?"Moat, returns, industry, price, scenariosTest resilience, causation, robustnessQuality verdictYesYes3NoMust follow risk screen.
Forecast skepticism"Does this DCF justify buying?"Model assumptions, horizon, uncertaintyStress precision and replay-the-tape fragilityForecast reliability ratingYesYes3NoSame robustness lens.
Very-lazy holding policy"Should I trade or wait?"Current holding, thesis, new data, opportunity setCheck rare-opportunity thresholdHold/wait/act ruleYesYes3NoSame three-rule framework.

Architecture Justification

The three sections form a sequential framework: avoid big risks, buy quality at a fair price, then be very lazy. Since each later judgment depends on survival and quality screens, a single-file architecture keeps the dependency explicit.

DIMENSION 1: Avoid Big Risks

The Rule: The first job is to avoid permanent capital loss.

Key questions to ask:

  • What could cause a large, unrecoverable loss?
  • Is the business exposed to debt, disruption, fraud, regulation, customer concentration, or obsolescence?
  • Would a 50% loss require unrealistic recovery?
  • Is the investor underestimating extinction risk?

Decision criteria / Checklist:

  • Identify existential business risks.
  • Test balance-sheet resilience.
  • Avoid situations where one adverse event can permanently impair capital.
  • Prefer adaptable businesses over fragile strength.

Warning signals:

  • Leverage plus uncertain cash flows.
  • Cheap valuation masking structural decline.
  • Single-product, single-customer, or single-regulation dependence.

Agent instruction:

Before discussing upside, produce a big-risk screen and reject investments that fail survival tests.

DIMENSION 2: Buy Quality at a Fair Price

The Rule: Resilient quality beats apparent cheapness.

Key questions to ask:

  • What durable advantage helps the company survive changing environments?
  • Is quality natural and embedded, or dependent on constant restructuring?
  • Are high returns caused by real advantages or merely correlated indicators?
  • Is the price fair enough for quality without requiring heroic forecasts?

Decision criteria / Checklist:

  • Durable moat or adaptive advantage.
  • Simple focused business.
  • Robust economics across multiple scenarios.
  • Fair price, not necessarily bargain-basement price.

Warning signals:

  • Turnaround stories requiring continuous consultant intervention.
  • Confusing correlation with causation.
  • Low multiple used as substitute for business quality.

Agent instruction:

When evaluating cheapness, force the user to prove business resilience before calling the opportunity attractive.

DIMENSION 3: Robustness Over Forecast Precision

The Rule: Long-term precision forecasts are fragile; prefer businesses that can survive many futures.

Key questions to ask:

  • Which DCF assumptions drive most of the valuation?
  • Would the thesis survive if growth, margins, or terminal value were wrong?
  • If history replayed differently, would the business still do well?
  • What scenarios break the thesis?

Decision criteria / Checklist:

  • Stress test key assumptions.
  • Prefer qualitative robustness over point-estimate precision.
  • Avoid investments that need a narrow future path.
  • Treat DCF as a discipline, not proof.

Warning signals:

  • Purchase thesis depends on precise terminal growth.
  • Model hides uncertainty behind decimal-point accuracy.
  • Bull case requires everything to go right.

Agent instruction:

For model-based pitches, critique forecast fragility and replace false precision with scenario robustness.

DIMENSION 4: Be Very Lazy

The Rule: Trade rarely; most good investing is waiting.

Key questions to ask:

  • Has the thesis changed or is the user reacting to noise?
  • Is this a rare opportunity or routine market movement?
  • Would action improve expected outcome after costs and errors?
  • Is patience being confused with laziness, or laziness with discipline?

Decision criteria / Checklist:

  • Low turnover by default
阅读完整来源 ↗