What does this skill do, and when should you use it?
This skill analyzes whether a company can produce sufficiently durable and attractive distributable income to justify a portfolio role. It enforces research discipline: confirms the data cutoff date, prioritizes primary sources, cross-verifies financial data, uses exact arithmetic tools, and builds three scenarios. It classifies the income profile as conviction+durable, opportunistic, yield trap, or unsuitable, and issues a verdict with clear gates.
Parses user input, identifying company, mode, role, quantity, cost basis, tax residence, and other parameters; runs the date command to establish the data cutoff; collects at least five years of dividend history including frequency, amounts, growth, cuts, and key dates; traces cash available for distribution via net income, free cash flow, and sector-specific measures (e.g., FFO for REITs, CET1 for banks); assesses quality, durability, and valuation; calculates gross and net income when tax inputs are complete; checks portfolio fit and concentration; constructs base, adverse, and severe scenarios; scores using a qualitative scorecard and blocking gates; saves a report to reports/{company}-income-investment-{YYYYMMDD}.md; runs release audit scripts.
- A retiree evaluating a stock for reliable dividend income in a portfolio.
- A portfolio manager deciding whether to add or reduce a high-yield position, considering concentration.
- An analyst screening for opportunistic yield in a low-rate environment, distinguishing quality from traps.
- An investor comparing after-tax yields across tax residences for global investment decisions.
- A long-term shareholder monitoring dividend coverage and valuation of an existing position.
- A finance student learning income investing through a structured case-study workflow.
How do you install this skill?
- The skill relies on external data sources and tools; network reachability may need verification when accessing from mainland China.
- This skill is not personalized investment advice; use at your own risk and exercise judgment.
- The skill instructs to use tools but does not provide fallback when tools fail; users should be prepared to handle exceptions manually.
- No malicious behavior was detected, but always ensure you trust the environment and source before running any AI-generated commands.
- Shell / CLI
- Network access
- Local filesystem
Python 3gitdate command
Clone the repository and navigate to the codex-skills/income-investment/ directory. Place the SKILL.md and any associated tools in your Agent Skills-compatible client's skill folder (e.g., for Codex, ~/.codex/skills/income-investment/). Ensure Python 3 and the necessary scripts (from the repo root) are available. No automated install script is provided; refer to the repository's Codex skill installation process, if any.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/codex-skills/income-investment" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- <company or ticker>
- Use the income-investment skill to analyze Verizon for income potential.
Invoke the skill in a chat prompt with /income-investment "<company or ticker>" [mode=new|existing] [role=core-income|opportunistic-income|unspecified] [quantity=...] [cost_basis=...] [portfolio_weight=...] [target_yield=...] [tax_residence=...] [portfolio_file=...] [horizon=...] or equivalent natural language. Ensure the date command is run before research, and follow the research discipline. The report will be generated and saved to the specified output path. In Codex, trigger by describing the task, e.g., 'Use the income-investment skill to analyze Verizon for income potential.'
What are this skill's strengths and limitations?
- Enforces rigorous research discipline with primary-source priority, date verification, and cross-source data checks.
- Requires sector-specific coverage metrics instead of generic EPS payout, leading to deeper analysis.
- Includes a qualitative scorecard and blocking gates to prevent mechanical reliance on numeric scores.
- Provides clear operational steps and output format, improving report consistency.
- Distinguishes gross vs. net income and states the conditions for net-income calculation, transparent about tax complexities.
- Mandates a three-scenario analysis and explicitly tests dividend cuts, preparing for downside risks.
- Generates audit reports to verify citations and calculations, increasing trustworthiness.
- Integrates with a broader research toolkit without duplicating its functions.
- Requires users to supply trade details and tax information to calculate net income; missing data limits the output.
- Heavily relies on external data sources and network access for verification; cannot work offline.
- Provides no personalized investment advice; final decisions remain the user's responsibility.
- Specific scripts for report auditing are referenced but not bundled; users must fetch them separately.
- No automated test suite is included, so functionality is asserted but not empirically verified.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Income Investment: Durable & Opportunistic Distribution Analysis this page | 59 · Recommended | ★ 17k | 3d ago | MIT |
| Value Investing Agent | 55 · Use with care | ★ 23 | 8mo ago | MIT |
| Buffett Investment Thinking System | 53 · Use with care | ★ 820 | 6mo ago | — |
| Industry Funnel (AI Berkshire) | 52 · Use with care | ★ 17k | 3d ago | MIT |
| Deep Company Series (看懂XX) | 49 · Use with care | ★ 17k | 3d ago | MIT |
Within the broader repository, this skill is explicitly positioned alongside portfolio-review (which handles portfolio fit and concentration) and financial-data (which handles financial data verification), owning the income-specific decision and not overriding a current portfolio-review conclusion.
How did FollowSkills review this skill?
Evidence shows the skill mandates exact arithmetic tools and cross-verification, directs stating the data cutoff date in the report header, and clearly separates facts/estimates/assumptions, which supports data-flow transparency and source attribution. It guides the user to use validation tools, suggests careful execution, and emphasizes authorization confirmation, but does not provide an explicit permission list or isolation notes, nor does it explicitly require user confirmation for key operations (e.g., running scripts). Furthermore, it handles sensitive financial data without specific protection measures. Deductions for incomplete permission, confirmation, and isolation details.
Evidence shows the skill provides a detailed step-by-step workflow including execution audit steps and tool usage, which enhances self-consistency. It instructs using tools for arithmetic and auditing, promoting predictable behavior. However, no test results or execution evidence are provided, abnormal input handling is unclear (e.g., what if tools fail), and no error handling or fallback is mentioned. Hence, score lowered to 9.
Evidence shows the skill defines a clear input format, optional parameters, and accepts natural language, making it flexibly triggerable. It lists related workflows to avoid overlap and clarifies its owned scope. It partially addresses environment fit by offering bilingual Chinese and English support and guiding to run tools from repo root, but does not explicitly verify reachability from mainland networks, and if core functions depend on unreachable overseas services, risk exists. Therefore, slight reduction to 12.
Evidence shows the skill has a clear name and description, and a structured format with numbered sections. It provides installation/usage guidance in the adapter note and references other files in the repo for context. It includes license (MIT) and version info. However, there is no explicit changelog, known limitations list, or maintenance responsibility statement. Deductions for incomplete governance and versioning.
Evidence shows the skill provides a structured process for generating analysis, including explicit verdict categories and three-scenario analysis, which seems capable of delivering the core task. It mandates using audit tools, potentially improving output usability. However, no actual example reports or verification are provided, so benefit evidence is limited. Per static review guidance, effectiveness capped at 7.
Evidence shows the skill references tools and tests in the repo (e.g., test_financial_rigor.py and test_report_audit.py), which provide limited verification of key functions. But no end-to-end tests or independent verification of the full skill workflow are available. Thus, per static review guidance, score is capped at 5, with 6 given due to presence of partial auditable tests.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →