Agent skill

Management Deep Dive

by HKUDS in HKUDS/Vibe-Trading

Assesses a company's management on integrity, ability, capital allocation and governance from public information, producing a weighted score and a final trust verdict.

MITAuto-check passedBusiness, Finance & HR

Install Management Deep Dive

skills CLI
$ npx skills add HKUDS/Vibe-Trading --skill management-deep-dive -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUDS/Vibe-Trading management-deep-dive --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent/src/skills/management-deep-dive .claude/skills/management-deep-dive && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
management-deep-dive
GitHub stars
35k
Token cost
~2.2k tokens
SKILL.md length
941 words
Files
1
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

Assesses a company's management on integrity, ability, capital allocation and governance from public information, producing a weighted score and a final trust verdict.

  • Works in 9 steps: Identify Key People → CEO Circle of Competence → Integrity Assessment (most important) → …
  • Standard research leaves management quality uncertain
  • SKILL.md covers Design Philosophy, Step 1: Identify Key People, Step 2: CEO Circle of Competence and Step 3: Integrity Assessment…, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Built on the idea that buying a stock means buying a person, the skill goes beyond résumés and shareholdings. From public sources the agent tracks whether executives' words match what they delivered, reviews the return on each major capital-allocation decision, infers character from choices made in hard times and cross-checks with employee, customer and industry feedback. It applies to a company or to a named executive.

Work starts by identifying the key people, such as the CEO, CFO, founder and actual controller, then collects statements, capital-allocation decisions, governance and compensation details and outside validation using search, stock profile, filings, news and financial statement tools. A table compares the CEO's past predictions with outcomes to judge foresight. The result is a weighted score across integrity, ability, capital allocation and governance plus a three-question verdict about trusting this person with your money for 10 years.

When your agent uses it

  • Standard research leaves management quality uncertain
  • Management is the core of the investment thesis
  • Checking an executive's track record of promises against results
  • Reviewing governance, compensation and related-party dealings

Example prompts

  • “Run a management deep dive on the CEO of this company.”
  • “Compare the founder's past predictions with what actually happened.”
  • “Review this company's M&A and buyback decisions and score its capital allocation.”
  • “Check governance: equity structure, executive pay and related-party deals.”

Requirements

  • Web search and financial data tools such as web_search, get_stock_profile and get_sec_filings

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Identify Key People
  2. CEO Circle of Competence
  3. Integrity Assessment (most important)
  4. Capital Allocation
  5. Governance
  6. Side Validation
  7. Post-CEO Scenario
  8. Output
  9. Save

What it can do on your machine

Read from SKILL.md and the folder at commit e532650. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Management Deep Dive loads about 2.2k tokens when it runs. Until then it costs about 163 tokens; SKILL.md has 941 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~163
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/Vibe-Trading at commit e532650, republished under its MIT licence (© HKUDS). 941 words, ~2,242 tokens.

Download SKILL.mdSave it as .claude/skills/management-deep-dive/SKILL.md (or your agent's skills folder).
name
management-deep-dive
description
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.
category
analysis

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)

Show full SKILL.md (382 more words)Show less
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 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.

© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agent/src/skills/management-deep-dive of HKUDS/Vibe-Trading.

Open the folder on GitHubat commit e532650

Compare with similar skills

Management Deep Dive next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Management Deep Dive compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Management Deep Dive this skillHKUDS/Vibe-Trading35k—~2.2kAutomated safety check: PassMIT
AI-Trader Market IntelHKUDS/AI-Trader23k—~1.1kAutomated safety check: PassNone
Stock Deep Analysis Workflowwbh604/UZI-Skill7.1k—~9.1kAutomated safety check: NotesMIT
Zhengxi Fund Manager Views Librarylyra81604/zhengxi-views1.8k—~1.6kAutomated safety check: PassMIT
Supply Chain Bottleneck Hunterxbtlin/ai-berkshire17k—~2.6kAutomated safety check: PassMIT
Deep Company Article Seriesxbtlin/ai-berkshire17k—~2kAutomated safety check: PassMIT

Similar skills

  • AI-Trader Market Intel

    HKUDS/AI-Trader

    Reads AI-Trader's read-only market snapshots, grouped financial news and events board through its market-intel endpoints, for context before trading or posting.

    23k GitHub stars~1.1k tokensUpdated 4 mo ago
    Business, Finance & HRAuto-check passed
  • Runs a staged deep analysis of a single stock on China A-share, Hong Kong and US markets, ending in an HTML report with valuation models and investor-panel scores.

    7.1k GitHub stars~9.1k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check: notes
  • Zhengxi Fund Manager Views Library

    lyra81604/zhengxi-views

    Answers questions with sourced quotes from one Chinese fund manager's public writings, applies his stated investment method and compares his words with real fund holdings.

    1.8k GitHub stars~1.6k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Scans a long-running industry trend for supply chain chokepoints, aiming to find second- and third-layer suppliers that the market has not yet priced in.

    17k GitHub stars~2.6k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Deep Company Article Series

    xbtlin/ai-berkshire

    Plans and writes a three-to-eight-part long-form article series that breaks down one company, built on fact-checked financials, valuation and management analysis.

    17k GitHub stars~2k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Longbridge Earnings

    helsome/folio

    Earnings analysis — pre- and post-earnings. An agent skill from helsome/folio.

    270 GitHub starsUsed in 1 repo~2.5k tokens
    Business, Finance & HRAuto-check passed

More from HKUDS/Vibe-Trading

All 89 skills in this repo
  • Eastmoney Market Data

    HKUDS/Vibe-Trading

    Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.

    35k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • OKX Market Data

    HKUDS/Vibe-Trading

    Retrieves public OKX cryptocurrency market data such as spot prices, candlesticks, funding rates and open interest through the OKX V5 REST API, with no authentication.

    35k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • SEC EDGAR Filings Fetcher

    HKUDS/Vibe-Trading

    Fetches U.S. SEC EDGAR data: resolves tickers to CIK numbers, lists recent 10-K, 10-Q and 8-K filings with document URLs, and pulls XBRL financial series.

    35k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • A-Share ST Risk Screener

    HKUDS/Vibe-Trading

    Predicts whether a mainland China A-share company risks an ST or *ST warning after its next annual report, using financial thresholds and Sina penalty records.

    35k GitHub stars~4.9k tokensUpdated today
    Auto-check passed
  • Breaks a structural trend such as AI infrastructure into its physical supply chain and ranks lesser-known listed companies sitting on each bottleneck.

    35k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Plans and drafts an eight-part, roughly 120k-word investigative series on one company, built around a strict fact-check pass rather than fast drafting.

    35k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

Questions about Management Deep Dive

What does Management Deep Dive do?

Assesses a company's management on integrity, ability, capital allocation and governance from public information, producing a weighted score and a final trust verdict. Built on the idea that buying a stock means buying a person, the skill goes beyond résumés and shareholdings. From public sources the agent tracks whether executives' words match what they delivered, reviews the return on each major capital-allocation decision, infers character from choices made in hard times and cross-checks with employee, customer and industry feedback.

When should I use Management Deep Dive?

Management Deep Dive fits situations like: standard research leaves management quality uncertain; management is the core of the investment thesis; checking an executive's track record of promises against results; reviewing governance, compensation and related-party dealings.

How do I install Management Deep Dive in Claude Code?

Run `npx skills add HKUDS/Vibe-Trading --skill management-deep-dive -a claude-code`. Or copy the skill folder (agent/src/skills/management-deep-dive in HKUDS/Vibe-Trading) into .claude/skills/management-deep-dive in your project. Claude Code loads it when a task matches its description.

How do I install Management Deep Dive in Codex?

Run `npx skills add HKUDS/Vibe-Trading --skill management-deep-dive -a codex`. Or copy the skill folder (agent/src/skills/management-deep-dive in HKUDS/Vibe-Trading) into .agents/skills/management-deep-dive in your project. Codex loads it when a task matches its description.

Can I use Management Deep Dive in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/Vibe-Trading --skill management-deep-dive -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/management-deep-dive, .gemini/skills/management-deep-dive, .github/skills/management-deep-dive and .opencode/skills/management-deep-dive in your project.

What does Management Deep Dive need to run?

SKILL.md names no scripts, command-line tools or credentials: Management Deep Dive is instructions for the agent only. Our summary lists: Web search and financial data tools such as web_search, get_stock_profile and get_sec_filings.

Does Management Deep Dive access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Management Deep Dive safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Management Deep Dive use?

Management Deep Dive is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Management Deep Dive use?

About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Management Deep Dive?

Skills that share tags, products or a category with Management Deep Dive: AI-Trader Market Intel (HKUDS/AI-Trader, 23k stars), Stock Deep Analysis Workflow (wbh604/UZI-Skill, 7.1k stars), Zhengxi Fund Manager Views Library (lyra81604/zhengxi-views, 1.8k stars) and Supply Chain Bottleneck Hunter (xbtlin/ai-berkshire, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Management Deep Dive?

HKUDS (a GitHub organization) maintains it in HKUDS/Vibe-Trading, which has 35,043 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 8, 2026.

Source: HKUDS/Vibe-Trading on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.