Agent skill

Income Investment Analysis

by xbtlin in xbtlin/ai-berkshire

Assesses whether a company's distributions are durable enough to earn a place in an income portfolio, starting from a ticker or company name.

MITAuto-check passedBusiness, Finance & HR

Install Income Investment Analysis

skills CLI
$ npx skills add xbtlin/ai-berkshire --skill income-investment -a claude-code

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

GitHub CLI
$ gh skill install xbtlin/ai-berkshire income-investment --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/xbtlin/ai-berkshire.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex-skills/income-investment .claude/skills/income-investment && 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
income-investment
GitHub stars
17k
Token cost
~3k tokens
SKILL.md length
1,435 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Assesses whether a company's distributions are durable enough to earn a place in an income portfolio, starting from a ticker or company name.

  • Works in 8 steps: Parse the Request and Establish Data… → Understand the Distribution → Trace the Cash Available for Distribution → …
  • Judging whether a high-yield stock's payout looks sustainable before deeper research
  • SKILL.md covers Codex adapter note, Input, Related Workflows and Research Discipline, plus 4 more sections
  • Calls python3

What it does

Given a company name or ticker, the skill researches whether its distributable income is durable and attractive enough to hold either as a long-term income position or as an opportunistic yield trade. A high displayed yield is never accepted as evidence of a good opportunity on its own.

Optional inputs include whether the position is new or existing, its intended role as core or opportunistic income, quantity, cost basis and portfolio weight. Anything missing is marked Unknown or Not calculable instead of guessed, and net income is not estimated without tax residence, account type, treaty and withholding details. The agent confirms today's date first to set the data cutoff, defers to the financial-data and investment-research workflows, and uses repository tools such as tools/financial_rigor.py for exact arithmetic. It is meant for learning and research, not personalized investment advice.

When your agent uses it

  • Judging whether a high-yield stock's payout looks sustainable before deeper research
  • Reviewing an income holding you already own against its distribution record
  • Deciding if a company is a core income holding or only an opportunistic yield play

Example prompts

  • “Run income-investment on a utility ticker I'm considering and tell me what is still unknown.”
  • “/income-investment "Verizon" mode=existing role=opportunistic-income”
  • “Is this REIT's payout durable enough for a core income role? Mark anything you can't calculate.”

Requirements

  • Python 3 to run tools/financial_rigor.py
  • Web search access for current financial data

Workflow steps

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

  1. Parse the Request and Establish Data Quality
  2. Understand the Distribution
  3. Trace the Cash Available for Distribution
  4. Test Quality and Durability
  5. Value the Income Stream
  6. Calculate Usable Income
  7. Check Portfolio Fit
  8. Build Three Scenarios

What it can do on your machine

Read from SKILL.md and the folder at commit a221a20. 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

    Shell commands in SKILL.md call:

    • python3

    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

Income Investment Analysis loads about 3k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 1,435 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~3k

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 xbtlin/ai-berkshire at commit a221a20, republished under its MIT licence (© xbtlin). 1,435 words, ~2,975 tokens.

Download SKILL.mdSave it as .claude/skills/income-investment/SKILL.md (or your agent's skills folder).
name
income-investment
description
AI Berkshire skill: Income Investment: Durable and Opportunistic Distribution Analysis. Source: skills/income-investment.md.

Codex adapter note

This skill is generated from skills/income-investment.md so Claude Code and Codex users share one canonical workflow.

  • 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.

Income Investment: Durable and Opportunistic Distribution Analysis

Analyze $ARGUMENTS to answer:

Can this company produce sufficiently durable and attractive distributable income to justify a portfolio role, either as a long-term income conviction or as an opportunistic yield position?

Never treat a high displayed yield as evidence of a good opportunity. This workflow is for learning and research, not personalized investment advice.

Input

Use this command form:

text
/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=...]

The company or ticker is required. All other fields are optional. Accept equivalent natural-language input. Do not invent missing values: mark them Unknown or Not calculable and state the consequence. In particular, do not estimate net income without the tax residence, account type, applicable treaty, and confirmed withholding treatment.

Use or refer to existing workflows instead of reproducing them:

NeedWorkflow
Verified financial data and cross-source reconciliationfinancial-data
Full general fundamental researchinvestment-research
Final pre-purchase decisioninvestment-checklist
Portfolio fit, concentration, and sizingportfolio-review
Post-decision monitoringthesis-tracker
Update after reported resultsearnings-review
Rapid analysis of a discrete eventnews-pulse

income-investment owns the income-specific decision. It must not silently override a current portfolio-review conclusion.

Research Discipline

  1. Run date before research. Put the data cutoff date in the report header.
  2. Prefer annual and interim reports, earnings releases, investor documents, regulatory filings, official releases, and official exchange data, in that order. Use secondary sources only to fill gaps and label them as secondary.
  3. Apply skills/financial-data.md: verify decision-critical financial data with at least two independent sources when available and flag discrepancies above 1%.
  4. Date or period-label every time-sensitive figure. Separate every material statement as Verified fact, Estimate, Assumption, or Analytical judgment.
  5. Use python3 tools/financial_rigor.py for exact payout, yield, valuation, market-cap, portfolio-income, and scenario arithmetic. Never rely on mental arithmetic for a decision-sensitive result.
  6. After saving the report, run the tools/report_audit.py extract and verdict workflow. A report that fails audit is a draft, not publishable research.

Execution Workflow

1. Parse the Request and Establish Data Quality
  • Resolve the security, listing, currency, distribution currency, mode, desired role, and optional portfolio inputs.
  • State which gross-income, net-income, yield-on-cost, portfolio contribution, and after-trade calculations are possible.
  • Rate evidence quality A (complete primary material), B (partial primary material), or C (mostly secondary/incomplete). Materially insufficient fundamentals trigger the INSUFFICIENT DATA gate.
2. Understand the Distribution

Cover at least five years when available:

  • frequency; ordinary, special, or variable status; payment currency;
  • annual dividend per share and total distributions;
  • counts of increases, holds, cuts, and suspensions;
  • dividend CAGR, with the exact period and treatment of special dividends;
  • indicative announcement, ex-dividend, record, and payment dates.

Explain that waiting for the ex-dividend date is not a free gain: the share price theoretically adjusts by the distribution. The calendar may inform execution timing, but must never justify buying a weak company or delaying a necessary sale.

3. Trace the Cash Available for Distribution

Analyze net-income payout, free-cash-flow payout, cash flow after necessary investment, cash-flow stability and quality, interest coverage, net debt, debt maturities, refinancing needs, maintenance and growth capex, relevant off-balance-sheet commitments, and buybacks competing with dividends.

Do not mechanically apply an EPS payout ratio across sectors:

SectorRequired sector measures
REIT / SIICFFO, AFFO, occupancy, LTV
BankCET1, distributable earnings, regulatory constraints
InsurerSolvency and capital generation
BDCNII, NAV, non-accruals
ResourcesMid-cycle cash flow and variable-distribution policy
Telecom / utilityCapex, debt, and FCF coverage
4. Test Quality and Durability

Assess the business model, moat, pricing power, cyclicality, rate/currency/commodity sensitivity, income predictability, capital allocation, management quality, and the ability to maintain the distribution in a downside case. Distinguish accounting profit from repeatable distributable cash.

5. Value the Income Stream

Analyze current yield, historical average yield, appropriate sector multiples, FCF yield, a reasonable intrinsic-value range, margin of safety, and combined price-decline/dividend-cut scenarios. Yield on cost is retrospective information only and never a reason to keep a position.

6. Calculate Usable Income

Only when inputs support it, calculate annual gross dividend, gross dividend per payment frequency, known source withholding, estimated net income, contribution to portfolio income, and annual income after the proposed trade. If tax or account information is incomplete, show gross income and explain exactly why net income is not calculable. Label treaty rates and tax treatments with jurisdiction, account assumptions, and effective date.

Show full SKILL.md (559 more words)Show less
7. Check Portfolio Fit

If a portfolio is provided:

  • determine current and proposed weight;
  • examine sector and geographic concentration, duplicated risks, and income dependence on one industry;
  • distinguish capital diversification from dividend diversification;
  • read the latest relevant portfolio-review report when available.

If conclusions diverge, show both conclusions, explain why, and separate company quality from allocation fit. A sound income security may still merit HOLD – DO NOT ADD, REDUCE, or WATCHLIST because of portfolio concentration.

When data permit, show expected gross income by month. Never recommend an inferior company to fill an empty month; quarterly payers can be combined to create monthly cash flow without requiring monthly payers.

8. Build Three Scenarios

Provide base, adverse, and severe cases. Each must state operating assumptions, distributable cash flow, payout coverage, balance-sheet/refinancing effect, dividend outcome, and valuation implication. The adverse and severe cases must explicitly test a dividend cut rather than assuming the dividend is fixed.

Classification, Gates, and Verdict

First classify the income profile:

  • Conviction + durable income: quality business, sustainable and potentially growing dividend, plausible long holding period.
  • Opportunistic income: temporary yield or discount with explicit entry, monitoring, holding-period, and exit rules.
  • Yield trap: recurring lack of coverage, incompatible leverage/investment needs, structural decline, or yield driven mainly by a falling price.
  • Unsuitable for income: no meaningful distribution, marginal yield, insufficient evidence, or shareholder returns primarily delivered another way.

Use this qualitative scorecard; do not calculate a numeric average:

DimensionRating (Strong, Adequate, Weak, Critical, Unknown)Evidence
Business quality
Cash-flow visibility
Dividend coverage
Balance-sheet strength
Distribution history
Dividend growth potential
Valuation
Cyclicality
Cut risk
Portfolio fit

Check these blocking gates before the verdict:

  • recurring uncovered distribution;
  • critical debt or refinancing risk;
  • structural business deterioration;
  • insufficient fundamental data;
  • material governance or integrity concern.

A failed safety, debt, deterioration, or integrity gate overrides the scorecard and normally requires REJECT / YIELD TRAP (or REDUCE for an existing position when immediate disposal cannot be concluded from available portfolio facts). The insufficient-data gate requires INSUFFICIENT DATA. Do not use a score to offset a failed gate.

Return exactly one verdict:

  • CORE INCOME
  • OPPORTUNISTIC INCOME
  • WATCHLIST
  • HOLD – DO NOT ADD
  • REDUCE
  • REJECT / YIELD TRAP
  • INSUFFICIENT DATA

For the verdict provide: possible portfolio role, primary reason, primary risk, entry conditions, a position-size range to study (never universally suitable), reinforcement conditions, reduction/exit criteria, monitoring indicators, and confidence. Do not give a firm personalized recommendation when portfolio, tax, or risk-tolerance information is insufficient.

Required Report Format

Use these headings exactly once and avoid repeating the same analysis:

  1. Executive summary
  2. Verdict and category
  3. Possible portfolio role
  4. Business and source of distributed cash
  5. Dividend history and calendar
  6. Distribution coverage and safety
  7. Balance sheet and refinancing
  8. Income growth
  9. Valuation and margin of safety
  10. Tax and currency
  11. Portfolio fit
  12. Scenarios: base, adverse, severe
  13. Dividend-cut risks
  14. Purchase or reinforcement conditions
  15. Reduction or sale conditions
  16. Monitoring table
  17. One-sentence conclusion
  18. Sources and data quality

Save the result to reports/{company}-income-investment-{YYYYMMDD}.md, using a filesystem-safe company identifier. Include the scorecard and blocking-gate result in section 2, the monthly income calendar in section 11 when calculable, and source title, issuer/publisher, publication date, accessed date, reporting period, URL, and primary/secondary label in section 18.

Release Audit

bash
python3 tools/report_audit.py extract --report reports/{company}-income-investment-{YYYYMMDD}.md
# Verify every extracted item against reliable sources, then:
python3 tools/report_audit.py verdict --results '<verified JSON>' --report {company}-income-investment-{YYYYMMDD}.md

Fix failed items and repeat the audit. Clearly retain unresolved gaps and lower confidence rather than filling them with assumptions.

© xbtlin, 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 codex-skills/income-investment of xbtlin/ai-berkshire.

Open the folder on GitHubat commit a221a20

Compare with similar skills

Income Investment Analysis 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.

Income Investment Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Income Investment Analysis this skillxbtlin/ai-berkshire17k—~3kAutomated safety check: PassMIT
AI-Trader Market IntelHKUDS/AI-Trader23k—~1.1kAutomated safety check: PassNone
Eastmoney Market DataHKUDS/Vibe-Trading35k—~1kAutomated safety check: PassMIT
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
SEC EDGAR Filings FetcherHKUDS/Vibe-Trading35k—~1.4kAutomated 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
  • 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
    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
  • 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
    Business, Finance & HRAuto-check passed
  • Longbridge Earnings

    helsome/folio

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

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

More from xbtlin/ai-berkshire

All 22 skills in this repo
  • 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 2 days ago
    Auto-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
    Auto-check passed
  • Earnings Report Deep Reading

    xbtlin/ai-berkshire

    Reads a company's filings and earnings call material in depth, rates how complete the sources are and extracts the key figures into a structured review.

    17k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed
  • Runs four parallel analyst personas over one earnings report, then an editor and reader-review pass turn the findings into a publishable article.

    17k GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • A four-step research framework for finding and tracking high-growth core companies in one industry: map the sector, ask core questions, verify, then hold to the turning point.

    17k GitHub stars~974 tokensUpdated 2 days ago
    Auto-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
    Auto-check passed

Questions about Income Investment Analysis

What does Income Investment Analysis do?

Assesses whether a company's distributions are durable enough to earn a place in an income portfolio, starting from a ticker or company name. Given a company name or ticker, the skill researches whether its distributable income is durable and attractive enough to hold either as a long-term income position or as an opportunistic yield trade. A high displayed yield is never accepted as evidence of a good opportunity on its own.

When should I use Income Investment Analysis?

Income Investment Analysis fits situations like: judging whether a high-yield stock's payout looks sustainable before deeper research; reviewing an income holding you already own against its distribution record; deciding if a company is a core income holding or only an opportunistic yield play.

How do I install Income Investment Analysis in Claude Code?

Run `npx skills add xbtlin/ai-berkshire --skill income-investment -a claude-code`. Or copy the skill folder (codex-skills/income-investment in xbtlin/ai-berkshire) into .claude/skills/income-investment in your project. Claude Code loads it when a task matches its description.

How do I install Income Investment Analysis in Codex?

Run `npx skills add xbtlin/ai-berkshire --skill income-investment -a codex`. Or copy the skill folder (codex-skills/income-investment in xbtlin/ai-berkshire) into .agents/skills/income-investment in your project. Codex loads it when a task matches its description.

Can I use Income Investment Analysis 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 xbtlin/ai-berkshire --skill income-investment -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/income-investment, .gemini/skills/income-investment, .github/skills/income-investment and .opencode/skills/income-investment in your project.

What does Income Investment Analysis need to run?

Going by SKILL.md and its folder, Income Investment Analysis needs the command-line tools its instructions call (python3). Our summary lists: Python 3 to run tools/financial_rigor.py; Web search access for current financial data.

Does Income Investment Analysis 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 Income Investment Analysis 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 Income Investment Analysis use?

Income Investment Analysis 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 Income Investment Analysis use?

About 3k tokens (SKILL.md is roughly 12k 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 Income Investment Analysis?

Skills that share tags, products or a category with Income Investment Analysis: AI-Trader Market Intel (HKUDS/AI-Trader, 23k stars), Eastmoney Market Data (HKUDS/Vibe-Trading, 35k stars), Stock Deep Analysis Workflow (wbh604/UZI-Skill, 7.1k stars) and Zhengxi Fund Manager Views Library (lyra81604/zhengxi-views, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Income Investment Analysis?

xbtlin (a GitHub user) maintains it in xbtlin/ai-berkshire, which has 16,676 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 8, 2026.

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