Codex adapter note

skills/investment-checklist.md

• Treat

  $ARGUMENTS

  as the user's request in the current Codex thread.
• When the source mentions Claude-only surfaces such as Task, Agent, WebSearch, Bash, Read, or Write, use the closest Codex capability available in this session: subagents when available, web search when needed, shell commands for local tools, and normal file edits for workspace files.
• Use shared project tools from

  tools/

  in this repository. Prefer running commands from the repository root with paths like

  python3 tools/financial_rigor.py ...

  ; if the current thread starts outside the repo, locate the actual checkout path first instead of assuming a fixed home-directory path.
• Before starting research, run the

  date

  command to confirm today's date; treat it as the baseline for "latest" data and state the data cutoff date in the report header. Never assume the current date from training data.
• Preserve the research quality rules from

  AGENTS.md

  : cross-check financial data, use exact arithmetic tools for valuation/math, and clearly label uncertainty and source gaps.

Buffett Value Investment Pre-Purchase Checklist

Tencent, Moutai, NVIDIA

NVDA AAPL MSFT

Execution Process

Step 1: Parse Input and Identify All Companies to Analyze

• Full company name, stock code, listing exchange
• If the company is unlisted, mark it as "Unlisted" and provide a brief explanation (whether there are indirect investment channels), then skip the complete Checklist

Step 1.5: AI Research Bias Warning

Step 2: Parallel Data Collection

1. Profitability: ROE (5-10 year trend), gross profit margin, net profit margin, free cash flow
2. Valuation Data: Current stock price, market capitalization, PE(TTM), forward PE, PB, dividend yield
3. Growth Trend: Revenue/profit growth rate in the past 3 years
4. Financial Health: Debt level, capital expenditure requirements, cash reserves, net cash/net debt
5. Competitive Landscape: Market share, main competitors, share change trend
6. Moat Evidence: Specific evidence of brand/switching cost/network effect/scale effect/technical barrier
7. Management Track Record: CEO resume, key decisions, shareholding, capital allocation record
8. Latest Developments: Major events in the past 6 months (performance, mergers and acquisitions, regulation, management changes, etc.)

Step 3: Execute Six-Check Checklist for Each Company

Check 1: Can I Understand This Business? (Circle of Competence)

• Can you explain in one sentence how this company makes money?
• What business is it likely to be doing in 10 years?
• Which key variables determine success or failure?
• Is your understanding of this industry from in-depth research or hearsay?

• ★★★★★: Extremely simple and clear business model, high certainty in 10 years (e.g., Moutai: brewing and selling liquor)
• ★★★★☆: Clear model but with technical thresholds, requiring certain professional knowledge to understand
• ★★★☆☆: Understandable model but low certainty in 10 years, fast-changing industry
• ★★☆☆☆: Complex business lines or industry in upheaval, difficult to predict the future
• ★☆☆☆☆: Completely outside the circle of competence

Check 2: Is This a Good Business? (Economic Characteristics)

python3 tools/financial_rigor.py verify-valuation \
  --price {stock price} --eps {EPS} --bvps {book value per share} --fcf-per-share {FCF per share} --dividend {dividend per share}

• ★★★★★: ROE>25%, high gross profit margin, strong FCF, light asset, low debt (all criteria met)
• ★★★★☆: 4 criteria met
• ★★★☆☆: 3 criteria met
• ★★☆☆☆: 2 criteria met or deteriorating trend
• ★☆☆☆☆: Most criteria not met or sustained negative FCF

Check 3: Is the Moat Deep Enough? (Competitive Advantage)

• ★★★★★: Multiple moats overlapping and widening
• ★★★★☆: At least one strong moat and stable
• ★★★☆☆: Has moat but not deep enough, or unclear trend
• ★★☆☆☆: Moat is being eroded
• ★☆☆☆☆: No obvious moat

Check 4: Is Management Trustworthy? (Human Factor)

• ★★★★★: Founder-led, excellent capital allocation, fully aligned interests
• ★★★★☆: Excellent management with minor flaws
• ★★★☆☆: Qualified management with governance risks
• ★★☆☆☆: Integrity or governance issues
• ★☆☆☆☆: Severe integrity issues (→ Hard Rejection)

Check 5: Is the Price Cheap Enough? (Margin of Safety)

python3 tools/financial_rigor.py three-scenario \
  --price {stock price} --eps {EPS} --shares {shares in billions} \
  --growth {optimistic} {neutral} {pessimistic} --pe {optimistic PE} {neutral PE} {pessimistic PE} --currency {currency}

• Valuation range under three scenarios (take tool output results)
• If judgment is wrong, what's the maximum loss if buying at current price?
• Would you dare to add positions if the stock price is halved?

• ★★★★★: More than 50% discount to intrinsic value, extreme margin of safety
• ★★★★☆: 30% discount, good margin of safety
• ★★★☆☆: Reasonable valuation, average margin of safety
• ★★☆☆☆: Relatively expensive, insufficient margin of safety
• ★☆☆☆☆: Severely overvalued

Check 6: Position and Decision Discipline (Prevent Emotional Out-of-Control)

• Do you want to buy because of FOMO?
• Do you want to buy only because of others' recommendations?
• Can you accept a 5-year trading suspension?
• Can you write down the buying rationale in less than 200 words?

Step 4: Mirror Test

"I buy ___ company at ___ yuan, because:

1. The essence of this business is ___, and I understand it;
2. Its moat is ___, and it is widening/narrowing;
3. The management is ___, trustworthy/untrustworthy;
4. The current price is ___ discount to intrinsic value, with/without sufficient margin of safety;
5. Even if I'm wrong, the downside risk is controllable/uncontrollable, because ___."

Step 5: Quick Rejection Checklist

• Can't explain how the company makes money
• Sustained negative free cash flow for 3 consecutive years with no improvement in sight
• Management has integrity stains
• Competitive advantage is being irreversibly eroded
• Relies on "next buyer paying a higher price" to make money (greater fool theory)
• Can't bear the consequence of this investment becoming worthless
• Main buying reason is "everyone is buying" or "it's been rising recently"
• Can't write down the buying rationale in less than 200 words

Step 6: Output Overview Comparison Table (Mandatory for Multiple Companies)

Step 7: Final Conclusion and Write to File

• ✅ Passed Checklist (X/6 checks) — Can enter in-depth research stage
• ❌ Failed Checklist — Explain which red line was triggered
• ❓ Gray Area — Explain key controversial points, what investors need to judge on their own
• N/A — Unlisted/Unavailable for purchase

~/Buffett-Checklist-[Company Name or "Multi-Company Comparison"].md

Output Format Requirements

1. Each company has an independent chapter, including: six-check score table + core data table + key risks (3-5 items) + mirror test + clear conclusion
2. Attach the overview comparison table at the end when analyzing multiple companies
3. All scores must use ★ symbols (★1-5), no half stars
4. Data must be marked with source time, estimated values must be noted as "Estimated"
5. Attach a conclusion at the end, echoing Buffett's famous quote: "The first rule of investment is not to lose money"
6. Language style: Direct, sharp, no nonsense. Insert comments from Buffett/Munger/Duan Yongping

Key Principles

• Better to miss than to make a mistake: The goal of the Checklist is to eliminate bad choices, not to find the best one
• Be honest about your circle of competence: Admit if you don't understand, don't force analysis
• Margin of safety is the lifeline: Even a good company can lose money if bought at an expensive price
• Mirror test cannot be skipped: Don't buy if you can't explain the reason, no exceptions