agentleFS
from68from68/claude-portfolio-management-skills/skills/full-stock-analysis/SKILL.md

full-stock-analysis

Skill0 starsChanged 3 months agoMITView on GitHub

Comprehensive US stock analysis including fundamental analysis (financial metrics, business quality, valuation), technical analysis (indicators, chart patterns, support/resistance), stock comparisons, and investment report generation. Use when user requests analysis of US stock tickers (e.g., "analyze AAPL", "compare TSLA vs NVDA", "give me a report on Microsoft"), evaluation of financial metrics, technical chart analysis, or investment recommendations for American stocks.

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. About 0 are common, 13 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    IBKR connector (optional, when connected): use search_contracts → get_company_themes to place the company in its thematic peer group, and …

    line 47
  2. Distinctive:

    Always state the fiscal years covered and the quote timestamp in the report.

    line 58
  3. Very specific:

    If a call returns empty, retry once with adjusted parameters, then mark the field N/A and note the gap.

    line 63
  4. Distinctive:

    Search for current stock data (price, volume, market cap)

    line 83
  5. Distinctive:

    Consider volume for validation

    line 184
  6. Distinctive:

    Always identify risk levels (stop-loss)

    line 186
  7. Distinctive:

    Run the standard opening calls for each ticker

    line 234
  8. Very specific:

    Use quote(endpoint="batch-quote", symbols=[…]) for a single-call price comparison

    line 235
  9. Very specific:

    If the user names only one stock, get its peer set with company(endpoint="peers", symbol=…)

    line 236
  10. Distinctive:

    Ensure comparable fiscal periods — companies with different fiscal year ends are not directly comparable.

    line 237
  11. Distinctive:

    Consider both fundamental and technical factors

    line 261
  12. Very specific:

    Output Format: Follow "Comparison Report Structure" in references/report-template.md

    line 265
  13. Very specific:

    Write the result to ./Shortlist/<TICKER>.md in the current working directory.

    line 269
  14. Distinctive:

    Use tables for financial data and comparisons (easy to scan)

    line 273
  15. Distinctive:

    When: Constructing any FMP or IBKR connector call, or unsure which endpoint yields a metric

    line 303
  16. Distinctive:

    When: Performing technical analysis or interpreting indicators

    line 308
  17. Distinctive:

    When: Performing fundamental analysis or business evaluation

    line 313
  18. Distinctive:

    When: Need definitions or calculation methods for financial ratios

    line 318
  19. Distinctive:

    When: Creating comprehensive report or comparison

    line 323

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

US Stock Analysis

Overview

Perform comprehensive analysis of US stocks covering fundamental analysis (financials, business quality, valuation), technical analysis (indicators, trends, patterns), peer comparisons, and generate detailed investment reports. Fetch market data and fundamentals from the FMP MCP connector and apply structured analytical frameworks.

Data Sources

All numbers come from the FMP MCP connector. Invoke the market-data skill for exact endpoint names, parameters, and the metric-to-field mapping. WebSearch is a supplement for narrative context only — management commentary, competitive dynamics, breaking events — and is never a substitute for a figure FMP can provide. Where a web source is used, cite it.

Standard opening calls (make these for every analysis, before any interpretation):

company(endpoint="profile-symbol", symbol=<TICKER>)                                  # sector, industry, description, beta
quote(endpoint="quote", symbol=<TICKER>)                                             # price, 52w range, volume, mkt cap, P/E
statements(endpoint="income-statement",        symbol=<TICKER>, period="annual", limit=5)
statements(endpoint="balance-sheet-statement", symbol=<TICKER>, period="annual", limit=5)
statements(endpoint="cashflow-statement",      symbol=<TICKER>, period="annual", limit=5)
statements(endpoint="metrics-ratios",          symbol=<TICKER>, period="annual", limit=5)

Add per analysis type:

NeedCall
Analyst viewanalyst(endpoint="ratings-snapshot" | "price-target-consensus" | "grades-summary", symbol=…)
Forward estimatesanalyst(endpoint="financial-estimates", symbol=…, period="annual")
Peer set for comparisoncompany(endpoint="peers", symbol=…)
Quality/distress screensstatements(endpoint="financial-scores", symbol=…) → Piotroski, Altman Z
Growth ratesstatements(endpoint="income-statement-growth", symbol=…, period="annual", limit=5)
Recent developmentsnews(endpoint="search-stock-news", symbols=[…], limit=20), news(endpoint="search-press-releases", symbols=[…])
Earnings history & surprisescalendar(endpoint="earnings-company", symbol=…, limit=8)
Dividendscalendar(endpoint="dividends-company", symbol=…)
Price historychart(endpoint="historical-price-eod-light", symbol=…, from_date=…, to_date=…)
Moving averages, RSI, ADXtechnicalIndicators(endpoint=…, symbol=…, periodLength=…, timeframe="1day")
Sector valuation contextmarketPerformance(endpoint="sector-PE-snapshot", date=…)
Filings for detailsecFilings(...), earningsTranscript(...)

IBKR connector (optional, when connected): use search_contracts → get_company_themes to place the company in its thematic peer group, and get_price_snapshot for a live bid/ask when timing an entry. If the user holds the stock, get_account_positions() gives their cost basis and unrealised P&L — fold that into the recommendation rather than analysing in a vacuum.

Data hygiene:

  • Ratios from FMP are fractions (0.147 = 14.7%). Convert before display.
  • metrics-ratios is as of the fiscal period end; quote is live. Never put both in one column without labelling which is which.
  • Always state the fiscal years covered and the quote timestamp in the report.
  • technicalIndicators needs a paid FMP plan. If it errors, derive moving averages and volatility from chart closes and say the indicator was computed locally.
  • MACD and Bollinger Bands are not FMP endpoints — derive them from chart data or omit them and say so. Do not report an indicator you did not actually compute.
  • If a call returns empty, retry once with adjusted parameters, then mark the field N/A and note the gap. Never interpolate.

Analysis Types

This skill supports four types of analysis. Determine which type(s) the user needs:

  1. Basic Stock Info - Quick overview with key metrics
  2. Fundamental Analysis - Deep dive into business, financials, valuation
  3. Technical Analysis - Chart patterns, indicators, trend analysis
  4. Comprehensive Report - Complete analysis combining all approaches

Analysis Workflows

1. Basic Stock Information

When to Use: User asks for quick overview or basic info

Steps:

  1. Search for current stock data (price, volume, market cap)
  2. Gather key metrics (P/E, EPS, revenue growth, margins)
  3. Get 52-week range and year-to-date performance
  4. Find recent news or major developments
  5. Present in concise summary format

Output Format:

  • Company description (1-2 sentences)
  • Current price and trading metrics
  • Key valuation metrics (table)
  • Recent performance
  • Notable recent news (if any)

2. Fundamental Analysis

When to Use: User wants financial analysis, valuation assessment, or business evaluation

Steps:

  1. Gather comprehensive financial data:
    • Revenue, earnings, cash flow (3-5 year trends)
    • Balance sheet metrics (debt, cash, working capital)
    • Profitability metrics (margins, ROE, ROIC)
  2. Read references/fundamental-analysis.md for analytical framework
  3. Read references/financial-metrics.md for metric definitions and calculations
  4. Analyze business quality:
    • Competitive advantages
    • Management track record
    • Industry position
  5. Perform valuation analysis:
    • Calculate key ratios (P/E, PEG, P/B, EV/EBITDA)
    • Compare to historical averages
    • Compare to peer group
    • Estimate fair value range
  6. Identify risks:
    • Company-specific risks
    • Market/macro risks
    • Red flags from financial data
  7. Generate output following references/report-template.md structure

Critical Analyses:

  • Profitability trends (improving/declining margins)
  • Cash flow quality (FCF vs earnings)
  • Balance sheet strength (debt levels, liquidity)
  • Growth sustainability
  • Valuation vs peers and historical average

3. Technical Analysis

When to Use: User asks for technical analysis, chart patterns, or trading signals

Steps:

  1. Gather technical data:
    • chart(endpoint="historical-price-eod-light", symbol=…, from_date=…) — at least 250 sessions so a 200-day average is computable
    • quote(endpoint="quote", symbol=…) — current price, volume vs average volume, 52-week range
    • technicalIndicators(endpoint="simple-moving-average", periodLength=20|50|200, timeframe="1day")
    • technicalIndicators(endpoint="relative-strength-index", periodLength=14, timeframe="1day")
    • technicalIndicators(endpoint="average-directional-index", periodLength=14, timeframe="1day") — trend strength
    • MACD and Bollinger Bands: derive from the chart closes, or omit and say so
  2. Read references/technical-analysis.md for indicator definitions and patterns
  3. Identify trend:
    • Uptrend, downtrend, or sideways
    • Strength of trend
  4. Locate support and resistance levels:
    • Recent highs and lows
    • Moving average levels
    • Round numbers
  5. Analyze indicators:
    • RSI: Overbought (>70) or oversold (<30)
    • ADX: Trend strength (>25 trending, <20 rangebound)
    • MACD: Crossovers and divergences (if derived)
    • Volume: Confirmation or divergence
    • Bollinger Bands: Squeeze or expansion (if derived)
  6. Identify chart patterns:
    • Reversal patterns (head and shoulders, double top/bottom)
    • Continuation patterns (flags, triangles)
  7. Generate technical outlook:
    • Current trend assessment
    • Key levels to watch
    • Risk/reward analysis
    • Short and medium-term outlook

Interpretation Guidelines:

  • Confirm signals with multiple indicators
  • Consider volume for validation
  • Note divergences between price and indicators
  • Always identify risk levels (stop-loss)

4. Comprehensive Investment Report

When to Use: User asks for detailed report, investment recommendation, or complete analysis

Steps:

  1. Perform data gathering (as in Basic Info)
  2. Execute fundamental analysis (follow workflow above)
  3. Execute technical analysis (follow workflow above)
  4. Read references/report-template.md for complete report structure
  5. Synthesize findings:
    • Integrate fundamental and technical insights
    • Develop bull and bear cases
    • Assess risk/reward
  6. Generate recommendation:
    • Buy/Hold/Sell rating
    • Target price with timeframe
    • Conviction level
    • Entry strategy
  7. Create formatted report following template structure

Report Must Include:

  • Executive summary with recommendation
  • Company overview
  • Investment thesis (bull and bear cases)
  • Fundamental analysis section
  • Technical analysis section
  • Valuation analysis
  • Risk assessment
  • Catalysts and timeline
  • Conclusion

Stock Comparison Analysis

When to Use: User asks to compare two or more stocks (e.g., "compare AAPL vs MSFT")

Steps:

  1. Gather data for all stocks:
    • Run the standard opening calls for each ticker
    • Use quote(endpoint="batch-quote", symbols=[…]) for a single-call price comparison
    • If the user names only one stock, get its peer set with company(endpoint="peers", symbol=…)
    • Ensure comparable fiscal periods — companies with different fiscal year ends are not directly comparable; say so if they differ
  2. Read references/fundamental-analysis.md and references/financial-metrics.md
  3. Create side-by-side comparison:
    • Business models comparison
    • Financial metrics table (all key ratios)
    • Valuation metrics table
    • Growth rates comparison
    • Profitability comparison
    • Balance sheet strength
  4. Identify relative strengths:
    • Where each company excels
    • Quantified advantages
  5. Technical comparison:
    • Relative strength
    • Momentum comparison
    • Which is in better technical position
  6. Generate recommendation:
    • Which stock is more attractive and why
    • Consider both fundamental and technical factors
    • Portfolio allocation suggestion
    • Risk-adjusted return assessment

Output Format: Follow "Comparison Report Structure" in references/report-template.md

Output

Write the result to ./Shortlist/<TICKER>.md in the current working directory. Use the template below. Fill every field — use N/A or UNKNOWN when data is genuinely missing.

General Principles:

  • Use tables for financial data and comparisons (easy to scan)
  • Bold key metrics and findings
  • Include data sources and dates
  • Quantify whenever possible
  • Present both bull and bear perspectives
  • Be clear about assumptions and uncertainties

Formatting:

  • Headers for clear section separation
  • Tables for metrics, comparisons, historical data
  • Bullet points for lists, factors, risks
  • Bold text for key findings, important metrics
  • Percentages for growth rates, returns, margins
  • Currency formatted consistently ($B for billions, $M for millions)

Tone:

  • Objective and balanced
  • Acknowledge uncertainty
  • Support claims with data
  • Avoid hyperbole
  • Present risks clearly

Reference Files

Load these references as needed during analysis:

market-data skill (separate skill, not a file here)

  • When: Constructing any FMP or IBKR connector call, or unsure which endpoint yields a metric
  • Contains: Endpoint catalogue, parameter shapes, metric-to-field mapping, connector fallbacks

references/technical-analysis.md

  • When: Performing technical analysis or interpreting indicators
  • Contains: Indicator definitions, chart patterns, support/resistance concepts, analysis workflow

references/fundamental-analysis.md

  • When: Performing fundamental analysis or business evaluation
  • Contains: Business quality assessment, financial health analysis, valuation frameworks, risk assessment, red flags

references/financial-metrics.md

  • When: Need definitions or calculation methods for financial ratios
  • Contains: All key metrics with formulas (profitability, valuation, growth, liquidity, leverage, efficiency, cash flow)

references/report-template.md

  • When: Creating comprehensive report or comparison
  • Contains: Complete report structure, formatting guidelines, section templates, comparison format

Example Queries

Basic Info:

  • "What's the current price of AAPL?"
  • "Give me key metrics for Tesla"
  • "Quick overview of Microsoft stock"

Fundamental:

  • "Analyze NVDA's financials"
  • "Is Amazon overvalued?"
  • "Evaluate Apple's business quality"
  • "What's Google's debt situation?"

Technical:

  • "Technical analysis of TSLA"
  • "Is Netflix oversold?"
  • "Show me support levels for AAPL"
  • "What's the trend for AMD?"

Comprehensive:

  • "Complete analysis of Microsoft"
  • "Give me a full report on AAPL"
  • "Should I invest in Tesla? Give me detailed analysis"

Comparison:

  • "Compare AAPL vs MSFT"
  • "Tesla vs Nvidia - which is better?"
  • "Analyze Meta vs Google"

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.