portafoglio da rivista

    1

    Transforms financial magazine articles into analyzed educational portfolios with ML-based performance projections.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    portafoglio da rivista

    Example session with this skill installed

    Analizza questo PDF di 'Borsa & Finanza', estrai i titoli citati e costruisci un portafoglio moderato da 50.000 EUR in valuta Euro. Includi le proiezioni Kronos.

    • Read your context and instructions
    • Compiled the portafoglio da rivista
    • Generated the document

    Analisi completata per la rivista 'Borsa & Finanza' del 12 Ottobre 2024. Sono stati individuati 12 titoli, con una strategia focalizzata su diversificazione geografica e settoriale.

    Report Portafoglio Didattico

    1. Sintesi e Parametri

    • Fonte: Borsa & Finanza (12/10/2024)
    • Capitale Iniziale: 50.000,00 EUR
    • Profilo: Moderato (Orizzonte 5 anni)
    • Titoli estratti: 12 (8 Azioni, 3 ETF, 1 ETC)

    2. Allocazione Portafoglio

    TickerNomePeso %QuotePrezzo (EUR)Settore
    MC.PALVMH10.0%7685.40Consumer Cyclical
    ASML.ASASML Holding8.5%5842.10Technology
    IWDA.ASiShares MSCI World22.0%12587.95Diversified
    GLDSPDR Gold Shares5.0%11245.30Commodities
    CASHLiquidità3.2%-1.600,00-

    3. Proiezioni Ensemble (Kronos + Chronos)

    TickerTrend 5gTrend 21gConsensoMinimo Previsto (Livello Entry)
    MC.PA+1.2%+4.5%3/3678.50 (tra 3 giorni)
    ASML.AS-0.5%+2.1%2/3825.00 (tra 5 giorni)

    Metriche Aggregate:

    • Volatilità attesa (1a): 14.2%
    • Dividend Yield stimato: 2.15%
    • Max Drawdown storico: 18.4%

    Next steps:

    1. Esaminare il file out/portfolio.xlsx per il dettaglio dei costi commissionali.
    2. Consultare le schede titolo nel report out/report.md per i rischi specifici citati dalla rivista.
    3. Monitorare i livelli di ingresso segnalati nella tabella delle proiezioni per il timing operativo.

    Contenuto a scopo educativo. Non costituisce consulenza finanziaria.

    portfolio.xlsx

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Building a portfolio based on financial media often leads to fragmented data, missing market context, and manual calculation errors. This skill automates the extraction of tickers from financial magazines and transforms them into a structured, statistically analyzed educational portfolio.

    What it does

    • Media Extraction identifies tickers, sentiments, and target prices from PDF, images, or text files with page-level citations.
    • Market Data Retrieval fetches real-time prices, volatility, drawdown, and dividend yields using free financial APIs.
    • Ensemble Forecasting runs Kronos and Amazon Chronos models to project 5-day and 21-day performance trends.
    • Portfolio Construction calculates allocations with full-share constraints, managing sector limits and currency conversion.
    • Multi-Format Exporting generates comprehensive reports in Markdown, HTML, PDF, and Excel formats.

    How it works

    1. Analyze Provide a financial magazine file; the skill performs OCR and extracts all cited assets and macro themes.
    2. Fetch It uses fetch_market_data.py to pull historical and current data for all identified symbols.
    3. Project Models like Kronos-small and Chronos-bolt-small run batch inferences to identify potential entry points and short-term trends.
    4. Build The skill applies diversification rules to generate a balanced allocation based on the magazine's sentiment.
    5. Report A final dossier is produced containing metric tables, pie charts, and individual asset deep-dives.

    Frameworks & tools

    The tool utilizes Python 3.11, PowerShell, and the Kronos/Chronos forecasting libraries. Data handling is managed via yfinance, pandas, matplotlib, and openpyxl.

    Why this beats prompting it yourself

    Generic prompts cannot perform multi-model time-series forecasting or enforce strict allocation math with whole-share rounding. This skill integrates local machine learning models and Python scripts to ensure data integrity that a standard LLM chat context cannot maintain.

    Use cases

    • Convert a weekend financial column into a trackable educational watchlist.
    • Compare predictions from multiple AI models against professional analyst sentiments.
    • Audit the diversification and risk metrics of a suggested thematic portfolio.
    • Generate professional-grade financial reports and Excel spreadsheets from static articles.

    Known limitations

    Forecasting models require local GPU/CPU resources and pre-cached weights. Market data is limited to what is available on free public sources like Yahoo Finance and Stooq.

    Requires local Python 3.11 and PowerShell environment. Forecasting models (Kronos/Chronos) must be downloaded separately. Market data relies on free API availability.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 9 days ago

    Requires

    Stooq
    Python

    Permissions

    Terminal / Shell
    Network Access
    Read Files

    Allowed Hosts

    stooq.com
    Listed9 days ago

    What's inside

    Frequently Asked Questions

    The skill accepts PDFs, static images (like scans or screenshots), and raw text files. It uses advanced OCR to identify ticker symbols, analyst sentiments, and macro themes directly from the page.

    Unlike basic LLM prompts, this skill uses dedicated ML models (Kronos and Chronos) for time-series forecasting and specialized Python scripts to handle complex financial math like whole-share rounding and currency conversion. This ensures higher data integrity and professional-grade reporting that standard chat models can't replicate.

    You will receive the complete source code (Python 3.11 and PowerShell), the forecasting model integration scripts, and a detailed user guide for setup. It includes everything needed to automate data fetching, trend projection, and report generation.

    The skill utilizes public data sources like Yahoo Finance and Stooq via API. While it provides real-time price fetching for its analysis, please note that it is dependent on the uptime and data availability of these free third-party providers.

    Yes, for the most efficient performance of the Kronos and Chronos forecasting models, a local GPU is recommended. However, the system is designed to run on CPU resources if necessary, though processing times for the batch inferences may be longer.

    New in Trading & Investing