CtrlK
BlogDocsLog inGet started
Tessl Logo

management-deep-dive

Deep management assessment — the 'buying a stock is buying a person' layer. For a company or a named executive, evaluate integrity (promise-vs-delivery tracking, crisis behavior, stakeholder treatment), ability (strategic foresight, execution, capital-allocation record) and governance (equity structure, compensation, related-party deals). Outputs a weighted score across integrity / ability / capital-allocation / governance plus Duan Yongping's 3-question verdict ('would you hand this person your money for 10 years'). Use when standard research leaves management quality uncertain, or when management IS the investment thesis.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Management Deep Dive: Buying a Stock Is Buying a Person

Deep management research on a company (or person company).

"Buying a stock is buying a person. Find someone you trust, then hold long-term." — Duan Yongping

"To judge management, look at what they do when no one is watching." — Buffett

Design Philosophy

Most analysis stops at the surface: résumé, shareholding, compensation. But Buffett spends time talking with management, Li Lu says investing is fundamentally investing in people, Duan Yongping says buying a stock is buying a person.

AI can't have dinner with management, but it can via public information: ① track whether words match deeds (promises vs delivery); ② analyze the return of every major capital-allocation decision; ③ infer character from decisions made in hard times; ④ cross-check via employee / merchant / customer feedback.

Use when: standard research leaves management score uncertain (★★★ or below), or when management is the core investment logic.

Step 1: Identify Key People

Use web_search / get_stock_profile / get_sec_filings:

RoleNameTenureBackgroundShareholding/options
CEO/Chairman
CFO
Founder (if not in role)
Actual controller (if different from CEO)
Other key executives

Distinguish "who decides" from "whose name is on the title" — some founders remain the soul even after stepping down.

Then gather four data categories (sequentially via web_search + get_stock_news + get_financial_statements + get_sec_filings, or run_swarm): ① CEO public statements and prediction record; ② capital-allocation decisions (M&A / buybacks / dividends / new business); ③ governance and compensation; ④ side validation (employee / customer / industry reputation).

Step 2: CEO Circle of Competence

Strategic Foresight

Use web_search to collect the CEO's public statements over the past 5 years (shareholder letters, calls, interviews, social media); extract their judgments:

TimeCEO's judgment/predictionActual outcomeAccuracy
"We believe market X will..."X actually...✅/❌

Key questions: Has the CEO made correct calls ahead of the market? Stayed calm when everyone was bullish? Is their industry understanding independent or following the crowd?

Execution

DimensionAssessmentEvidence
Strategy-to-executionDid they do what they said?
OrganizationCan they attract and retain talent?
Crisis handlingHow do they respond to difficulty?
Iteration speedHow fast do they correct mistakes?

Step 3: Integrity Assessment (most important)

Buffett: "We look for three qualities: integrity, intelligence, and energy. Without the first, the other two will kill you."

Promise-vs-Delivery Tracking

Extract specific commitments from the past 3 years (calls, letters, interviews) via get_sec_filings / web_search / get_stock_news:

#TimeCommitmentOccasionDeliveryRating
1"X business profitable in 2025"2024 annual call✅/⚠️/❌
Delivery rateRating
>80%Excellent — does what it says
60-80%Acceptable — right direction, execution gaps
40-60%Concerning — over-promises, under-delivers
<40%Serious problem — untrustworthy

Behavior in Hard Times

Search for major crises (price crash, earnings miss, regulatory shock, competition); analyze management's response: proactive comms or hiding? Internal attribution or blaming external? Used the crisis to do the hard right thing or to pander short-term?

Treatment of Stakeholders

StakeholderAttitudeEvidenceRating
ShareholdersRespect/ignore/exploit
EmployeesTreat well/exploit/ignore
Customers/usersCustomer-first/short-term extract
Merchants/suppliersFair/extreme price pressure
Regulator/societyCompliant/corner-cutting

Step 4: Capital Allocation

Buffett's most-valued ability — for every dollar earned, how much does management turn it into?

Search past 5 years of capital decisions (web_search / get_financial_statements); score each:

M&A record: time / target / amount / strategic logic / after-the-fact return / score(1-5)

Buybacks (use financial_rigor command=verify_valuation to check PE at buyback time vs now): time / amount / avg price / PE then / retrospective / score(1-5)

Dividends: year / amount / payout ratio / vs FCF / sustainable

New business investment: time / area / cumulative spend / status / return / score(1-5)

Capital Allocation Score

DimensionScore(1-5)Notes
M&A disciplineRight price? Integration?
Buyback timingBuy low, stop high?
Dividend rationalityPayout vs FCF?
New businessSuccess rate? Stop-loss discipline?
Cash managementReasonable reserves? Hoarding?
Overall

Step 5: Governance

Equity Structure

ItemDetailRisk
Dual-class / super-voting?
Founder/controller stake?
VIE structure?
Independent directors truly independent?
Recent major-holder changes?

Compensation

ExecutiveTotal annual comp% of net incomevs peersReasonable?

Is incentive aligned with long-term shareholders or encouraging short-term behavior?

Related-Party Transactions

Related partyTransactionAmountArm's length?Risk

Step 6: Side Validation

AI can't meet face-to-face, but cross-check via public channels:

  • Employee view: web_search for Glassdoor ratings, discussions (mark platforms requiring login as "user can supplement") — culture, management rating, intensity, compensation, growth.
  • Customer/merchant view: App Store ratings, complaints, merchant forums.
  • Industry reputation: peer and insider views on this management.

Step 7: Post-CEO Scenario

Buffett: "A great company should be one that a fool can run — because eventually one will."

  • If the CEO left tomorrow, would the company run normally?
  • How deep is the management team? A clear successor?
  • Is the competitive advantage dependent on the CEO personally or on organization/system?
  • Have past management transitions been smooth?

Step 8: Output

Structure: ① Key people overview; ② Integrity (delivery rate + hard times + stakeholders); ③ Ability (foresight + execution + capital allocation); ④ Governance; ⑤ Side validation; ⑥ Overall score and verdict.

Overall Score

DimensionWeightScore(1-5)Weighted
Integrity35%
Strategy & execution25%
Capital allocation25%
Governance15%
Total100%

Duan Yongping's 3 Questions

  1. Is this person honest? (truthful, doesn't take advantage of shareholders)
  2. Is this person capable? (strategic foresight + execution + capital allocation)
  3. Would you hand this person your money for 10 years?

All three "yes" = ★★★★★; first two "yes" = ★★★★; only the first "yes" = ★★★; first is "no" = ★ (don't invest).

Step 9: Save

Use write_file to reports/{company}-management-{YYYYMMDD}.md. Then report_audit (extract → verify → verdict) as a quality gate on the numbers.

Key Principles

  • Integrity is a veto — ability can be learned; character can't be fixed.
  • Watch behavior, not words — what they say doesn't matter; what they do does.
  • Truth shows in hard times — everyone's a good CEO in a tailwind.
  • Capital allocation is the ultimate exam — making money is easy; allocating it well is hard.
  • Don't fall in love with management — stay objective; even someone you admire can make big mistakes.
Repository
HKUDS/Vibe-Trading
Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.