agentleFS
ray5273ray5273/kr-research-kit/skills/us-stock-analysis/SKILL.md

us-stock-analysis

Skill2 starsChanged 8 days agoMITView on GitHub

Build dated, source-backed analysis for U.S. public companies and U.S.-listed ETFs. Use when analyzing a U.S. ticker, comparing U.S. stocks, preparing a pre-earnings or post-earnings memo, assessing valuation, summarizing an investment thesis, reviewing catalysts and risks, or adding style-specific U.S. growth stock, U.S. value stock, ETF, peer valuation, or chart analysis using current filings, investor materials, and recent news.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

23 rules. About 0 are common, 15 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈15

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to produce equity research style analysis for U.S.

    line 8
  2. Distinctive:

    Treat prices, market caps, financial statements, guidance, analyst estimates, ownership, regulations, and news as time-sensitive.

    line 12
  3. Distinctive:

    Prefer primary sources first: SEC filings, investor relations pages, earnings releases, earnings decks, transcripts, exchange …

    line 13
  4. Very specific:

    If the workspace is writable, treat the default deliverable as a markdown report file, not just a chat reply.

    line 15
  5. Very specific:

    If exact SEC filing support matters, use us-sec-analysis first.

    line 16
  6. Distinctive:

    Read current price context, recent SEC filings, the latest earnings package, and any recent company-specific news needed for the question.

    line 25
  7. Distinctive:

    Check balance sheet strength, cash generation, dilution, cyclicality, customer concentration, regulatory risk, and plausible bear cases.

    line 31
  8. Distinctive:

    Use simple, defensible valuation methods that fit the business.

    line 33
  9. Distinctive:

    Create or update the report file first when the workspace is writable, then lead with the conclusion, evidence, valuation, catalysts, …

    line 35
  10. Distinctive:

    Read references/workflow.md for the detailed checklist.

    line 37
  11. Distinctive:

    Read references/us-style-checklists.md when analyzing U.S.

    line 38
  12. Distinctive:

    Read references/output-format.md for answer templates.

    line 39
  13. Distinctive:

    Read references/script-inputs.md when using the bundled scripts with structured JSON inputs.

    line 40
  14. Very specific:

    Use scripts/peer-valuation.js when the user provides peer metrics and you need a consistent markdown comparison table.

    line 44
  15. Very specific:

    Use scripts/etf-overlap.js when the user provides two ETF holdings files and you need weighted overlap, common names, and top overlaps.

    line 45
  16. Very specific:

    Use scripts/chart-basics.js when the user provides OHLCV price history and you need a basic technical read on trend, momentum, and volume …

    line 46
  17. Very specific:

    Run all bundled scripts with node.

    line 47
  18. Distinctive:

    Use exact dates for earnings, filings, guidance, and news.

    line 52
  19. Distinctive:

    Prefer ranges and scenarios over false precision.

    line 54
  20. Distinctive:

    If the user asks for portfolio sizing, tax, or personal suitability, keep the response informational unless the user provides those …

    line 56
  21. Distinctive:

    If you produced a full single-stock memo, keep the file deliverable synchronized with the final chat answer rather than letting the report …

    line 57
  22. Very specific:

    Do not re-collect SEC filings blindly when a matching sec-reference.md or sec-cache.json already covers the accession numbers being used.

    line 58
  23. Very specific:

    Use us-sec-analysis as the SEC filing-precision stage when exact filing evidence is more important than a broad investment memo.

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

U.S. Stock Analysis

Use this skill to produce equity research style analysis for U.S. stocks and U.S.-listed ETFs without relying on stale memory.

Quick Start

  • Treat prices, market caps, financial statements, guidance, analyst estimates, ownership, regulations, and news as time-sensitive. Verify them with current sources before using them.
  • Prefer primary sources first: SEC filings, investor relations pages, earnings releases, earnings decks, transcripts, exchange announcements, ETF fact sheets, and official macro data.
  • Pin the scope before analyzing: ticker, exchange, analysis horizon, comparison set, and the desired output type.
  • If the workspace is writable, treat the default deliverable as a markdown report file, not just a chat reply. For a U.S. stock or ETF, create or update analysis-example/us/<company>/memo.md.
  • If exact SEC filing support matters, use us-sec-analysis first. Read any existing analysis-example/us/<company>/sec-analysis.md, sec-reference.md, or sec-cache.json before re-fetching filings.
  • Open every memo with a 한줄요약 line directly under the title: one sentence of at most 50 characters that states the conclusion. See references/output-format.md.
  • State an explicit "as of" date in the final answer.

Workflow

  1. Define the task. Capture the security, market, user goal, time horizon, and whether the user wants a quick view, a deep memo, a comparison, or an event-driven read.
  2. Gather verified facts. Read current price context, recent SEC filings, the latest earnings package, and any recent company-specific news needed for the question. 2A. Add SEC precision when needed. For filing-sensitive claims about reported results, MD&A, Risk Factors, liquidity, cash flow, segment disclosure, controls, or exact XBRL facts, route through us-sec-analysis and ingest its sec-reference.md / sec-cache.json artifacts before drafting.
  3. Build the thesis. Explain what drives the business, why the market may be underpricing or overpricing it, and which metrics matter most for this business model.
  4. Stress test the idea. Check balance sheet strength, cash generation, dilution, cyclicality, customer concentration, regulatory risk, and plausible bear cases.
  5. Value the security. Use simple, defensible valuation methods that fit the business. Do not force a DCF when the inputs are too weak.
  6. Write the answer. Create or update the report file first when the workspace is writable, then lead with the conclusion, evidence, valuation, catalysts, risks, and what would change the view.

Read references/workflow.md for the detailed checklist. Read references/us-style-checklists.md when analyzing U.S. growth stocks, U.S. value stocks, or ETFs. Read references/output-format.md for answer templates. Read references/script-inputs.md when using the bundled scripts with structured JSON inputs.

Bundled Scripts

  • Use scripts/peer-valuation.js when the user provides peer metrics and you need a consistent markdown comparison table.
  • Use scripts/etf-overlap.js when the user provides two ETF holdings files and you need weighted overlap, common names, and top overlaps.
  • Use scripts/chart-basics.js when the user provides OHLCV price history and you need a basic technical read on trend, momentum, and volume regime.
  • Run all bundled scripts with node.

Operating Rules

  • Cite where each important factual claim came from.
  • Use exact dates for earnings, filings, guidance, and news.
  • Separate verified facts from your inference.
  • Prefer ranges and scenarios over false precision.
  • Say when data is missing or uncertain.
  • If the user asks for portfolio sizing, tax, or personal suitability, keep the response informational unless the user provides those constraints explicitly.
  • If you produced a full single-stock memo, keep the file deliverable synchronized with the final chat answer rather than letting the report drift.
  • Do not re-collect SEC filings blindly when a matching sec-reference.md or sec-cache.json already covers the accession numbers being used.

Source Priority

  1. SEC filings and official investor relations materials
  2. Exchange notices and fund sponsor documents
  3. Official macro or industry data
  4. Reputable news and transcript providers for context

Use us-sec-analysis as the SEC filing-precision stage when exact filing evidence is more important than a broad investment memo.

Minimum Output Standard

  • Summary judgment
  • What the business does and what matters most
  • Evidence from current results and balance sheet
  • Valuation view with at least one comparable metric
  • Catalysts
  • Risks and disconfirming evidence
  • Clear "what would change my mind" section

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.