agentsclimarketplace

Fundamental analysis

Skill su-ekachai/skills/skills/finance/fundamental-analysis

My personal catalog of Agent Skills for AI agents.

Install
npx -y skills add su-ekachai/skills --skill fundamental-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Produce or refresh a fundamental analysis of a listed company as an Obsidian research note for beginner investors — business model, revenue quality, financial health, moat, risks, management, and multi-model fair value (DCF, PEG, Graham, DDM) with a scored verdict. Use when the user asks to "analyze <ticker>", "run fundamental analysis", "research this stock", "is <ticker> worth buying", or "refresh the <ticker> analysis". Covers listed equities on any exchange; excludes commodities, cryptocurrencies, and funds. Supports Analyze mode (new note) and Refresh mode (update an existing note).

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

5.2 KB, as published. Nobody here has run it

Fundamental Analysis — Analyze & Refresh

The skill acts as a senior equity analyst. Audience: beginner investors — every note must be readable without prior finance training. Output is one Obsidian research note per company, structured by references/template.md.

Scope

  • Covered: listed equities on any exchange — for example NASDAQ, NYSE, and the Stock Exchange of Thailand (SET) — including American Depositary Receipts (ADRs).
  • Excluded: commodities, cryptocurrencies (the crypto-news-screener skill screens crypto market news), exchange-traded funds (ETFs), and mutual funds. The template measures earnings-based businesses; those asset classes need different models.
  • Governed artifact: the research note. Conversational replies about stocks keep their natural register.

Non-negotiable rules

  1. Ground every claim in data. No guessing, no fabrication.
  2. State missing data explicitly ("Q1 segment split not yet reported") instead of estimating silently. Label every estimate "(est.)".
  3. Use the most recent reported figures. Highlight changes since the prior period or the last refresh.
  4. Explain jargon in parentheses on first use: "free cash flow (cash left after operating costs and capital spending)".
  5. Write like an investor, not a textbook: direct sentences, no flattery, no filler.
  6. Trace every quantitative claim to an entry in the note's Sources callout.
  7. Never deliver a note containing unfilled {{placeholders}} or leftover %% instruction blocks.

Modes

ModeActivationOutput
AnalyzeRequest to analyze a ticker with no existing noteNew note from references/template.md
Refresh"refresh" / "update", or the ticker's note already existsExisting note updated in place

Analyze procedure

  1. Resolve the company: full name, ticker, listing exchange, fiscal-year convention, reporting currency.
  2. Research with available web tools. Minimum source set: latest annual filing (10-K, 20-F, or SET Form 56-1 One Report), latest quarterly results, earnings presentation or call commentary, current price and market cap, analyst consensus, peer valuation multiples.
  3. Read references/template.md completely. Fill it top to bottom.
  4. Select valuation models per the template's decision tree. Delete rows, assumption tables, and sections that do not apply — never leave placeholder values.
  5. Score the six dimensions (1–10, one-line justification each) and write the verdict, ending with "Before buying, a beginner should verify".
  6. Run the self-check, then deliver per the Delivery section.

Refresh procedure

  1. Locate the existing note in the vault.
  2. Refresh the "Data as of" callout: price and date, market cap, trailing-twelve-month (TTM) figures, valuation multiples, analyst consensus.
  3. Recompute valuation model outputs with current inputs and update the Valuation Verdict callout.
  4. Mark material narrative changes inside the affected section with a dated bold marker: "June 2026 update: ...". Preserve the original analysis text around the marker.
  5. Append a dated source group to the Sources callout: "Refreshed YYYY-MM-DD sources:".
  6. Bump updated_at in the frontmatter. Run the self-check.

Delivery

Vault location: Investment/Asset-Analysis/ inside the owner's Obsidian vault (personal-mind-palace). Filename: <TICKER>-Fundamental-Analysis.md.

ListingDestination
SET (Thailand)02 - Thai Stocks/
US exchange, including ADRs03 - US Stocks/
Any other exchangeAsk where to file; propose a new market folder
Vault absent on this machineWrite to the working directory and state the fallback

After writing a new note, append one row to the matching market table in 00 - Asset Analysis MOC.md (the vault's Map of Content index): | [[<TICKER>-Fundamental-Analysis]] | <sector description> |. When the obsidian-vault skill is installed, delegate vault operations — placement, wikilinks, index updates — to it.

Self-check before delivery

  • Every {{placeholder}} replaced, or its row/section deleted per the template's deletion rules; every %% block removed.
  • Frontmatter complete: title, created_at, updated_at, tags, aliases.
  • "Data as of" callout states price, date, market cap, price/earnings ratio (P/E), and currency.
  • Every quantitative claim maps to a Sources entry.
  • Jargon explained in parentheses on first use.
  • Scoring table has six rows, each justified in one line.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.