skills/earnings-team.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.

1. Understanding the future yourself — requires in-depth research from four different perspectives
2. Helping readers understand the value — requires editing and quality control from the reader's perspective

• Stage 1·Research: Four masters conduct parallel in-depth reading of the earnings report (Duan Yongping looks at the essence of the business, Buffett audits financial quality, Munger reads competitive changes, Li Lu hunts for risk signals)
• Stage 2·Synthesis: Team Lead synthesizes the four perspectives to produce a draft research report
• Stage 3·Publishing: Editor Agent rewrites it into an official account article + Reader Review Agent proposes revision suggestions → Team Lead finalizes the draft

Duan Yongping: "Investing is buying a business. Reading earnings reports isn't about looking at numbers, it's about seeing if the business has changed."

1. Revenue Structure Disassembly and Interpretation
   • Revenue by business/region, which are accelerating, which are decelerating
   • Don't just list numbers — what business logic does each business segment reflect?
   • Does revenue growth come from "volume" or "price"? Which is healthier?
2. User/Customer Value Changes
   • Changes in operational metrics like DAU/MAU/paying users
   • Quality metrics like user duration, ARPU, retention rate
   • Is the platform/product's value to users strengthening or weakening?
3. Moat Detection
   • Changes in gross margin reflect whether pricing power is stable
   • Changes in market share reflect whether competitive barriers are effective
   • Are there signals of weakened customer switching costs/network effects?
4. "Good Business" Standard Evaluation
   • Duan Yongping's three criteria: differentiation, pricing power, sustainable competitive advantage — changes in this period
   • Is the business becoming "heavier" or "lighter"?
   • If the company closed tomorrow, would users be extremely distressed? Has this changed because of this earnings report?
5. Management's Product Intuition
   • Does management use specific language or bureaucratic language when discussing products/users?
   • Are there impressive product insights or concerning disconnect signals?

Buffett: "When I read every earnings report, the first thing I do is turn to the cash flow statement."

1. Core Financial Data Extraction and Verification
   • Revenue, gross profit, operating profit, net profit — both GAAP and Non-GAAP
   • GAAP vs Non-GAAP differences: how much, where, is the gap expanding or narrowing
   • Cross-verify key data with at least two sources
   bash

   python3 tools/financial_rigor.py cross-validate \
     --metric "revenue" --values {value1} {value2} --sources "source1" "source2"

2. Cash Flow Analysis (Most Important)
   • Operating cash flow vs net profit ratio (>100% is good, <80% requires caution)
   • Free cash flow = Operating cash flow - Capital expenditure
   • Capital expenditure composition: maintenance vs expansion
   • Share repurchase and dividend amounts
3. Profit Quality Inspection
   • Accounts receivable growth rate vs revenue growth rate
   • Inventory growth rate vs revenue growth rate
   • Trend of gap between operating cash flow and net profit
   • Whether capitalized expenditures have suddenly increased
   • Proportion of non-recurring income
4. Balance Sheet Health
   • Changes in net cash/net debt
   • Changes in accounts receivable/inventory turnover days
   • Impairment risk of goodwill and intangible assets
5. Valuation and Margin of Safety Update
   bash

   python3 tools/financial_rigor.py verify-market-cap \
     --price {price} --shares {shares} --reported {reported market cap} --currency {currency}
   python3 tools/financial_rigor.py verify-valuation \
     --price {price} --eps {EPS} --bvps {book value per share}
   python3 tools/financial_rigor.py three-scenario \
     --price {price} --eps {EPS} --shares {shares in 100 million} \
     --growth {optimistic} {neutral} {pessimistic} --pe {optimistic PE} {neutral PE} {pessimistic PE}

Munger: "I want to know where I'm going to die, so I'll never go there."

1. Infer Competitive Changes from Earnings Report Data
   • Revenue growth rate vs industry growth rate — outperforming or underperforming?
   • Changes in gross margin reflect intensified/eased competition
   • Changes in marketing expense rate — does the company need to spend more to acquire customers?
   • R&D investment — proactive investment or forced follow-up?
2. Comparison with Competitors in the Same Period
   • Comparison of key indicators of major competitors in the same period (if published)
   • Comparison of growth rate, profit margin, investment intensity
   • Who is winning? Who is losing?
3. Management's Discussion on Competition
   • How does management describe the competitive environment in earnings calls?
   • Do they name competitors? Is their tone confident or anxious?
   • Are there new competitive threats?
4. Industry Trend Signals
   • Impact of technological changes (AI/new platforms, etc.)
   • Impact of regulatory changes on the competitive landscape
   • Consumption/demand-side trends
5. Munger-style Reverse Thinking
   • What could kill this company? Does this earnings report have signals pointing to these threats?
   • Looking back in 5 years, will this earnings report be a "turning point"?

Li Lu: "The most important thing in investing is to avoid permanent capital loss."

1. Management Tone Analysis
   • Read management discussion and earnings call remarks paragraph by paragraph, mark signals:
   • 🟢Transparency signal (voluntarily admitting problems)/🟢Clarity signal (with quantitative targets)
   • 🔴Vagueness signal (empty words)/🔴Diversion signal (avoiding the question)/🔴External attribution
2. Commitment Tracking
   • Compare specific commitments made by management in the previous period vs actual fulfillment in this period, item by item
   • Duan Yongping: "To see if management is reliable, just check if they did what they said before."
3. Notes and Hidden Information
   • Related party transactions, equity incentive dilution, contingent liabilities
   • Changes in accounting policies, differences in segment profit margins
   • Changes in customer/supplier concentration
4. Selected Earnings Call Q&A
   • Score the quality of answers to the 3-5 sharpest analyst questions
5. Permanent Capital Loss Risk
   • Are there signals that may lead to permanent loss?
   • New developments in regulatory/compliance/litigation risks
   • Has management made irreversible wrong decisions?

1. Consensus Points of Four Perspectives: Conclusions agreed by all four masters, with the highest credibility
2. Contradiction Points of Four Perspectives: For example, Duan Yongping says the business has improved, but Munger says competition is worsening — such contradictions are the most valuable analysis
3. Overlooked Areas: Things none of the four focused on, could they be the most important?

50-100 words: Exceeded/Met/Below expectations, core changes, impact on investment thesis.

1. Exceeded/Met/Below expectations?
2. Impact on investment thesis: Strengthened/No impact/Weakened/Broken
3. Next catalyst
4. Operation suggestions

---

• Retain all key data and conclusions, don't reduce professional depth
• Improve expression so non-professional investors can follow the logic
• Not "popularization", but "making professional content easy to read"

1. Title and Opening
   • The title should be informative and attractive, but not clickbait
   • Good title example: "Kuaishou Spent 26 Billion on AI, Did It Win the Bet?"
   • Bad title example: "Shocking! Kuaishou Earnings Report Bombs!"
   • Within 100 words at the opening, clearly state: What is the most important conclusion of this earnings report, why readers should care
2. Structure Optimization
   • Research reports are for yourself, official account articles are for others — adjust logical order
   • Put "The 3 Most Important Changes" at the front (inverted pyramid structure)
   • Keep tables but simplify them, change long paragraphs into bullet points
   • Insert a "stage summary" every 500 words or so to help readers digest
3. Expression Polishing
   • Explain rigid financial terms with analogies/scenarios: "Operating cash flow is 30% lower than net profit" → "Earned 100 yuan but only found 70 yuan in the pocket"
   • The four masters' comment quotes are the soul of the article — ensure each reads sharp and memorable
   • Paragraphs no more than 4 lines, sentences no more than 30 words
   • Moderately use contrast and反差 to create reading rhythm
4. Reader Value Detection
   • For each chapter, ask: What decision can readers make after reading this paragraph? If the answer is "nothing", either rewrite or delete it
   • The end of the article needs a clear "So what?" — provide operation guidelines for holders and onlookers respectively
5. Format Adaptation
   • WeChat official account friendly: short paragraphs, clear subheadings, concise tables
   • Add appropriate dividers and quotation formats
   • Control article length between 1000-3000 words (readers will leave if it's too long)

1. Readability (Weight 30%)
   • How many minutes does it take to read the full text? Are there paragraphs you want to skip?
   • Which parts are hard to understand or require repeated reading?
   • How is the rhythm? Is there a feeling of "tired of reading"?
2. Information Value (Weight 30%)
   • After reading, has my understanding of this company deepened?
   • Are there moments of "Oh, that's how it is"?
   • Compared to analyses I've seen elsewhere, what's unique about this article?
   • Which information is redundant and can be deleted without affecting understanding?
3. Credibility (Weight 20%)
   • Are data sources indicated? Are key judgments supported?
   • Does it present both pros and cons? Or is it only bullish/bearish?
   • Are there overly confident judgments that make people uncomfortable?
   • Are the four masters' quotes appropriate and powerful?
4. Action Guidance (Weight 20%)
   • Do I know what to do after reading?
   • Are the suggestions for "holders" and "onlookers" specific enough?
   • What should I focus on next? (Catalysts, time nodes)

undefined

• Issue 1: Specific description → Suggested modification
• Issue 2: ...

• Suggestion 1: ...
• Suggestion 2: ...

• Question 1
• Question 2

1. Address "Must Modify" items from reader review — modify item by item
2. Selectively adopt "Suggested Optimization" items — judge if they are worth implementing
3. Supplement "Questions readers want to know but aren't answered" — add if supported by data
4. Final read-through — ensure the revised text is coherent and logically consistent

• Read the original, not summaries: Do everything possible to obtain first-hand materials
• Four perspectives are not four departments: Must mutually verify and challenge each other, not talk past each other
• Team Lead's value lies in comprehensive judgment: Find intersections and contradictions, not just piece reports together
• Conclusions must be clear: No "Overall basically meets expectations but there are some points worth attention"
• Reverse testing runs through the whole process: Each positive finding is accompanied by counterarguments
• Editing does not reduce professionalism: Make professional content easier to read, not turn it into popular science
• Reader review is not a formality: Truly pick faults from the reader's perspective
• Data accuracy: Cross-verify key data, use financial_rigor.py tool for calculation