Agent skill

Eight-Part Company Deep Dive

by HKUDS in HKUDS/Vibe-Trading

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.

MITAuto-check passedWriting & Content

Install Eight-Part Company Deep Dive

skills CLI
$ npx skills add HKUDS/Vibe-Trading --skill deep-company-series -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/Vibe-Trading deep-company-series --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/deep-company-series .claude/skills/deep-company-series && 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
deep-company-series
GitHub stars
35k
Token cost
~2.4k tokens
SKILL.md length
1,059 words
Files
1
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 7 steps: When to Use → Series Template (8 Parts) → Writing Style → …
  • Writing a publication-length, multi-part analysis of a single public company
  • SKILL.md covers 1. When to Use, 2. Series Template (8 Parts), 3. Writing Style and 4. Strict Fact-Check Checklist…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Lays out a fixed eight-part structure for a single company, moving from a cognitive-reset opener through the moat, the main profit engine, hidden balance-sheet assets, an era variable such as AI, Buffett-style financial reading, a management-integrity test, and a closing valuation piece with buy and sell signals. Each part can be read on its own but all eight share one valuation, management and pricing framework, so judgments stay consistent across the series.

States plainly that the hard part is not prose but revision: articles get checked against a list of common finance-writing failures, among them probability-weighted guesses dressed up as precision, mismatched third-party usage figures, straight-line extrapolation, absolute claims, and numbers that contradict each other across the eight parts. The voice is direct and data-first, shows the counterargument to every core judgment, and is written so the opening words work on a mobile preview. An unpublished `00-series-overview.md` file indexes the parts.

This skill is explicitly not for a single research note or earnings update; those belong to other, narrower skills. It fits a reader willing to spend roughly 90 minutes on one company, not a quick take.

When your agent uses it

  • Writing a publication-length, multi-part analysis of a single public company
  • Producing a textbook-depth series meant to be shared article by article
  • Fact-checking a finance long-form for pseudo-precision and inconsistent numbers
  • Building a company write-up around one shared valuation and management framework

Example prompts

  • “Start the eight-part deep-dive series on this semiconductor company, beginning with the cognitive-reset piece.”
  • “Draft part four of the series: the hidden asset on this company's balance sheet.”
  • “Fact-check this financials article against the series' pseudo-precision checklist before I publish it.”

Workflow steps

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

  1. When to Use
  2. Series Template (8 Parts)
  3. Writing Style
  4. Strict Fact-Check Checklist (the Core IP)
  5. Execution
  6. Revision-Feedback Handling
  7. What This Skill Does NOT Do

What it can do on your machine

Read from SKILL.md and the folder at commit 8e43007. 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

Eight-Part Company Deep Dive loads about 2.4k tokens when it runs. Until then it costs about 201 tokens; SKILL.md has 1,059 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~201
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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 8e43007, republished under its MIT licence (© HKUDS). 1,059 words, ~2,433 tokens.

Download SKILL.mdSave it as .claude/skills/deep-company-series/SKILL.md (or your agent's skills folder).
name
deep-company-series
description
Write a publication-grade 8-part deep-dive series on a single company (~120k words total): cognitive reset / moat / profit engine / hidden assets / era variable (e.g. AI) / financials Buffett-style / management / valuation+redlines. The core IP is NOT writing but REVISING — a strict fact-check checklist catches pseudo-precision (probability-weighted expectations, third-party MAU discrepancies, linear extrapolation), absolute language, and cross-article number inconsistencies that most finance long-forms violate. Each piece stands alone but shares one valuation/management/price framework. Use when the user wants textbook-level depth on one company for public publishing (a single research report or earnings note is NOT this — use investment-research / earnings-review instead).
category
analysis

Deep-Company Series: An 8-Part Deep Dive on One Company

Write an 8-part deep-dive series (~120k words total) on a single company, from cognitive reset to a decision framework. The core IP is not "writing well" but "revising strictly" — most finance long-form violates this skill's fact-check standard.

1. When to Use

The user wants "textbook-level" deep research on a company, published as a series of long-form articles. Distinct from a single research report:

  • 8 parts, ~120k words, full loop from cognitive reset to a decision framework
  • Each part stands alone (shareable singly) but shares one valuation / management / price framework
  • Written for readers willing to spend 90 minutes understanding one company

Not for: a single research report, earnings note, sector study — use other skills (fundamentals / earnings / sector).

2. Series Template (8 Parts)

#Title templateCore questionWords
01You think you understand X — you don'tCognitive reset: break 3 common illusions4,000-5,000
02X's moat — {one-line business essence}Is the moat deep; will it be there in 5/10 years6,000-8,000
03X's biggest profit engine — {most profitable business}What is the core business; why it persists6,000-8,000
04The other company hidden on X's balance sheet — {hidden asset}Investment portfolio / subsidiary / hidden value8,000-10,000
05In the AI (or current narrative) era, is X a winner or loserEra variable: decompose the impact by business8,000-10,000
06Reading X's financials the Buffett wayFinancial depth: gross margin / FCF / ROE / SBC8,000-10,000
07{management quote} — is X's management worth entrustingCapital-allocation discipline + integrity test + succession8,000-10,000
08At what price to buy, what signal to sell (finale)DCF 3-scenario + red lines + position framework10,000-12,000

Plus 00-series-overview.md as an index (unpublished).

3. Writing Style

Voice
  • Direct, sharp, no filler — open with a number or a counterintuitive claim
  • Value-investing frame — Buffett/Munger/Duan Yongping/Li Lu lenses woven in (no name-dropping)
  • No preset stance — data first, logic next, conclusion last
  • Show both sides — every core judgment carries a "but on the other hand..."
  • Mobile preview — the first 18-20 characters must stand alone
Banned Words
BannedWhyReplace with
obviously / inevitably / certainlySubjective absolutism"the data shows" / "evidence suggests"
I think / I feelSubjective tonecut, or "under this framework"
textbook-level / brilliantHype adjectivesdescribe the concrete fact
severely mismatched / severely undervaluedStrong subjectivegive the specific discount %
perfect / flawlessOne-sidedadd the counter-observation
Title Style
  • Hook with a contrast number or a counter-consensus claim ("15 years, 7 failed challenges"; "salary 42.92M = 0.0017% of profit")
  • Neutral subtitle summarizing content
  • Avoid hype metaphors: "the next Buffett", "the X of China", "GOAT" — all banned

4. Strict Fact-Check Checklist (the Core IP)

"Pseudo-precision" traps to watch for before writing
  1. Probability-weighted expected value: 30% × A + 50% × B + 20% × C = expected +X% is almost always garbage — the probabilities are pure subjective, giving readers false precision. List scenarios + triggers + direction only; do not compute a weighted expectation.
  2. Third-party MAU/share estimates: QuestMobile / 七麦 / CBNData differ hugely (2-3× at the same point). Use only the two most-credible as anchors; describe the rest qualitatively.
  3. Linear extrapolation of historical growth: 2025 +33% × 5y CAGR → 2030 X is financial illiteracy. Use scenario assumptions + high/low ranges; never a promise.
  4. Undisclosed shareholding: unlisted-company stakes are never publicly disclosed. Give a range, mark "unknowable".
  5. Strong attribution: "competitor failed because of X." List multiple causes; this article does no single attribution.
The 7 mandatory revision checks
□ 1. Cross-article number consistency: market cap, Non-IFRS net income, key holding % aligned across the series
□ 2. Caliber labeling: Non-IFRS / GAAP / Non-IFRS-SBC / FCF — which is used, clear throughout
□ 3. Double-counting scan: consolidated subs are NOT in the "investment portfolio"; SOTP doesn't count them twice
□ 4. Peer-comparison fairness: don't compare "core-business PE (cash + portfolio stripped)" with "peer PE (not stripped)"
□ 5. Probability-weighted expectations deleted (see above)
□ 6. Absolute language softened: grep "obviously|inevitably|severely|textbook|perfect"
□ 7. Third-party data sourced: every non-filing data point followed by "(source: X)"
Known hard-error risks (list before writing)
  • Historical return multiples: use cumulative-invested basis (e.g. Riot 33×, not 58×)
  • Shareholding %: use the latest filing/financial-app basis (e.g. Tencent's Meituan stake changes with disposals)
  • "Distribution accounting": treated as disposal gain under IFRIC 17, recognized on declaration date
  • Share count rebounds: SBC granted in clusters at year-start can lift share count short-term

5. Execution

Show full SKILL.md (443 more words)Show less
Phase 1: Research (before writing 01-02)
  1. get_financial_statements — last 5 years of annuals, latest quarterly
  2. get_research_reports / web_search — at least 3 independent sell-side reports (find consensus + dissent)
  3. Optional: run_swarm (e.g. equity_research_team or value_investing_committee) to generate an internal research draft
  4. Confirm the 8-part core theses with the user (avoid writing the wrong direction)
Phase 2: Writing (01→08 in order, no skipping)
  • After each part, write_file to reports/{company}/《Understanding {company}》/0X-XX.md
  • Don't publish immediately — wait for user review
  • Revise on feedback
Phase 3: Cross-Article Consistency Scan (after all 8)

This is the key differentiator. Use tools to scan:

  1. read_file each part + report_audit (command=extract) to pull numbers (market cap, net income, holding %, PE) from each
  2. Cross-check the same number across parts — use financial_rigor (command=cross_validate) to cross-validate the same metric's values across articles; flag >1% deviation as a caliber mismatch
  3. read_file checks: is each term (FBS, SBC, Non-IFRS) defined at first use; do "see part 06" references actually resolve; do recaps match body numbers
  4. Absolute-language scan: grep "obviously|inevitably|severely|perfect" and soften each
Phase 4: Pre-publish Final Check
  • report_audit (command=verdict) as a gate on each part: extract numbers → verify → PASS/FAIL
  • Confirm all numbers are traceable, no pseudo-precision, no absolutism

6. Revision-Feedback Handling

1. Verify facts first (don't just change)

If the user says "X is wrong", use get_financial_statements / web_search to cross-check the original; present "user's number vs what I found vs what I used".

2. Grade the revision
GradeTypeHandle
🔥 Hard errorwrong number / attribution / caliberMust fix
⚠️ Subjectivestrong subjective word / hype metaphorSoften or cut
🔬 Granularitysource label, caliber refinementBalance against readability
❓ Unreliablelarge third-party discrepanciesDeleting is safer than editing
3. Cascade check after a fix

Before fixing one spot, think "where else is this number/concept referenced":

  • Market cap changed → cascade to PE / core-business PE / discount / FCF yield
  • Holding % changed → fix TOP-10 sort + historical holding table + disposal list
  • Caliber changed → fix first definition + later references + recap

7. What This Skill Does NOT Do

  • Does not make investment decisions for the reader — every part ends with "not investment advice"
  • Does not predict prices — only "scenarios + triggers"
  • Does not compute a weighted "expected annualized return" — subjective probability misleads
  • Does not write "famous investor X also holds" — using someone else's holding to back your judgment is anti-value-investing
  • Does not force all 8 parts — if a part lacks enough standalone content (e.g. management isn't distinctive), merge it or reduce the count

One-liner: writing an "Understanding X" series is about revising strictly, not writing well — most finance long-form dies from pseudo-precise numbers, subjective weighted expectations, and absolute language. This skill exists to flag all those traps before writing and sweep them clean after (report_audit + financial_rigor.cross_validate).

© 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/deep-company-series of HKUDS/Vibe-Trading.

Open the folder on GitHubat commit 8e43007

Compare with similar skills

Eight-Part Company 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.

Eight-Part Company Deep Dive compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Eight-Part Company Deep Dive this skillHKUDS/Vibe-Trading35k—~2.4kAutomated safety check: PassMIT
Aboutsecurity Content Ingestionwgpsec/AboutSecurity1.8k—~1.4kAutomated safety check: PassNone
Create ArticleAbilityai/cornelius109—~3kAutomated safety check: NotesMIT
Blog FactcheckAgriciDaniel/claude-blog2.3k—~2.2kAutomated safety check: PassMIT
Deep Company Article Seriesxbtlin/ai-berkshire17k—~2kAutomated safety check: PassMIT
Financial Data Cross-Validationxbtlin/ai-berkshire17k—~1.4kAutomated safety check: PassMIT

Similar skills

  • A skill your agent uses whenever the user asks to add, absorb, migrate, port, update, merge, compare, or extract security knowledge into the AboutSecurity repository from any external resource such…

    1.8k GitHub stars~1.4k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Create Article

    Abilityai/cornelius

    Create long-form articles from knowledge base insights. An agent skill from Abilityai/cornelius.

    109 GitHub stars~3k tokensUpdated 2 days ago
    Writing & ContentAuto-check: notes
  • Blog Factcheck

    AgriciDaniel/claude-blog

    Verify statistics and claims in blog posts by fetching cited source URLs and checking if the claimed data actually appears on the page.

    2.3k GitHub stars~2.2k tokensUpdated 2 days ago
    Writing & ContentAuto-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 2 days ago
    Business, Finance & HRAuto-check passed
  • A research rule set for pulling company financials from prioritized sources by market and cross-checking every key figure against two independent sources.

    17k GitHub stars~1.4k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed
  • Reading Guide

    chingswy/Skill-Research-Figure

    Structured learning navigator for blog posts and articles. An agent skill from chingswy/Skill-Research-Figure.

    179 GitHub stars~4.5k tokensUpdated 1 mo ago
    Writing & ContentAuto-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
  • Investment Thesis Tracker

    HKUDS/Vibe-Trading

    Keeps a written investment thesis for each stock you hold and re-checks it every quarter against new earnings, scoring its health and recommending hold, add, trim or exit.

    35k GitHub stars~2.2k tokensUpdated today
    Auto-check passed

Questions about Eight-Part Company Deep Dive

What does Eight-Part Company Deep Dive do?

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. Lays out a fixed eight-part structure for a single company, moving from a cognitive-reset opener through the moat, the main profit engine, hidden balance-sheet assets, an era variable such as AI, Buffett-style financial reading, a management-integrity test, and a closing valuation piece with buy and sell signals. Each part can be read on its own but all eight share one valuation, management and pricing framework, so judgments stay consistent across the series.

When should I use Eight-Part Company Deep Dive?

Eight-Part Company Deep Dive fits situations like: writing a publication-length, multi-part analysis of a single public company; producing a textbook-depth series meant to be shared article by article; fact-checking a finance long-form for pseudo-precision and inconsistent numbers; building a company write-up around one shared valuation and management framework.

How do I install Eight-Part Company Deep Dive in Claude Code?

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

How do I install Eight-Part Company Deep Dive in Codex?

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

Can I use Eight-Part Company 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 deep-company-series -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-company-series, .gemini/skills/deep-company-series, .github/skills/deep-company-series and .opencode/skills/deep-company-series in your project.

What does Eight-Part Company Deep Dive need to run?

SKILL.md names no scripts, command-line tools or credentials: Eight-Part Company Deep Dive is instructions for the agent only.

Does Eight-Part Company 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 Eight-Part Company 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 Eight-Part Company Deep Dive use?

Eight-Part Company 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 Eight-Part Company Deep Dive use?

About 2.4k tokens (SKILL.md is roughly 9.7k 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 Eight-Part Company Deep Dive?

Skills that share tags, products or a category with Eight-Part Company Deep Dive: Aboutsecurity Content Ingestion (wgpsec/AboutSecurity, 1.8k stars), Create Article (Abilityai/cornelius, 109 stars), Blog Factcheck (AgriciDaniel/claude-blog, 2.3k stars) and Deep Company Article Series (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 Eight-Part Company Deep Dive?

HKUDS (a GitHub organization) maintains it in HKUDS/Vibe-Trading, which has 35,163 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 10, 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.