Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    comparable company valuation

    1

    Manual spreadsheet valuation is prone to formula errors and inconsistent outlier handling.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    comparable company valuation

    comparable company valuation

    Example session with this skill installed

    Calculate the relative valuation for TechFlow Inc. as of Oct 2023. Peers: CloudScale (EV 500M, EBITDA 50M) and NetLogic (EV 800M, EBITDA 75M). TechFlow EBITDA is 60M with 10M net debt. Source E1.

    • Read your context and instructions
    • Compiled the comparable company valuation

    The valuation for TechFlow Inc. has been computed using the supplied peer data. All calculations were performed by the internal execution engine.

    Comparable Company Valuation — TechFlow Inc., 2023-10-31

    1. Scope, sources and assumptions

    • Valuation Date: 2023-10-31
    • Currency: USD (Millions)
    • Sources: E1 (User provided financials, Oct 2023)
    • Subject Period: LTM

    2. Peer universe and exclusions

    PeerStatusExclusion reasonCurrencyPeriodMarket date
    CloudScaleIncludedn/aUSDLTM2023-10-31
    NetLogicIncludedn/aUSDLTM2023-10-31

    3. Multiples table

    PeerEnterprise ValueEV/EBITDAP/E
    CloudScale500.0010.00xn/a
    NetLogic800.0010.67xn/a

    4. Peer statistics

    MultiplenMinQ1MedianMeanQ3Max
    EV/EBITDA210.00x10.17x10.33x10.33x10.50x10.67x

    5. Implied valuation

    MultiplePointMultiple appliedImplied EVImplied equity
    EV/EBITDAMid10.33x620.00610.00

    6. Comparability and selection limits

    • Flags: Peer set size is small (n=2); statistical significance is limited.
    • Selection: Peer selection was made by the user and may be biased toward specific valuation outcomes.

    7. Warnings and data gaps

    • W01: P/E multiples undefined due to missing Net Income data.
    • Gap: Net Income for subject and peers not provided.

    8. Interpretation and items for human review

    • The implied equity value of 610.00 is a computed result based on the median EV/EBITDA of 10.33x.
    • Narrow spread between peers suggests high local trading consistency.
    • Management decision required for any pricing or transaction based on this analysis.

    Next steps

    1. Verify if Net Income data is available to compute P/E ratios.
    2. Review the small peer sample size for sector representativeness.
    3. Confirm the 10M net debt figure against the latest balance sheet.

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

    About this skill

    Manual spreadsheet valuation is prone to formula errors and inconsistent outlier handling. This skill automates relative valuation by processing user-supplied peer data through a deterministic Python engine to ensure arithmetic precision.

    What it does

    • Multiples computation calculates EV/Revenue, EV/EBITDA, EV/EBIT, and P/E ratios for every peer.
    • Statistical analysis generates median, mean, quartile, and min/max distributions for the peer group.
    • Outlier management applies explicit exclusion rules and IQR filters to remove non-representative data points.
    • Range derivation produces implied enterprise and equity value ranges for a subject company.
    • Data auditing flags comparability limits and identifies information gaps in supplied financials.

    How it works

    1. Data Ingestion reads user-provided financials for a subject and its peers, including sources and observation dates.
    2. Validation checks for required fields like market capitalization, net debt, and specific metrics before processing.
    3. Execution runs the input through scripts/run.py to perform all arithmetic using exact decimals.
    4. Reporting generates a structured valuation report with tables, exclusion reasons, and warnings.

    Frameworks & tools

    This skill uses a self-contained Python calculation engine, JSON schema validation for input integrity, and standard financial formulas for enterprise value bridges.

    Why this beats prompting it yourself

    LLMs frequently hallucinate math or apply inconsistent rounding when calculating enterprise value bridges and multiples. This skill offloads all arithmetic to a fixed script, ensuring the output is always deterministic and grounded in the data you provide.

    Use cases

    • Generating trading comps tables for investment memos or internal reports.
    • Applying standardized outlier rules to a volatile peer set.
    • Bridging enterprise value to equity value with sourced adjustments.
    • Auditing the comparability of a selected peer universe based on growth and geography.

    Known limitations

    Does not fetch market data or find peers. Requires user-supplied financials, sources, and dates. Does not support DCF or precedent transaction methods.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.

    Requires user-provided financial data and sources. No automated data fetching. Restricted to relative valuation (multiples) only. No DCF support.

    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 buying a skill.

    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 5 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    This skill solves the issue of mathematical hallucinations and inconsistent outlier handling common in LLMs by offloading all calculations to a deterministic Python engine, ensuring 100% arithmetic accuracy in your comps tables.

    The skill requires a structured input of financials for your subject company and its peers, including market cap, net debt, and metrics like Revenue, EBITDA, and Net Income; it does not browse the web to find this data for you.

    You will receive the core Python calculation engine, the JSON schema for data validation, the `run.py` execution script, and comprehensive documentation on how to integrate it into your agent's workflow.

    The skill is designed to be framework-agnostic and can be integrated into any AI agent capable of executing Python scripts or interacting with a local API, such as AutoGPT, LangChain, or custom-built LLM agents.

    Yes, the skill includes customizable outlier management where you can apply specific IQR (Interquartile Range) filters or explicit exclusion rules to ensure non-representative data points don't skew your medians.

    This skill is focused strictly on relative valuation (Trading Comps); it does not currently support Discounted Cash Flow (DCF) models or Precedent Transaction analysis.

    New in Finance & Accounting