Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    company sector evidence research

    1

    Structured company research agent that enforces source-grounded evidence, metric reconciliation, and data provenance.

    $16

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    company sector evidence research

    company sector evidence research

    Example session with this skill installed

    Analyze the Q3 performance of CloudScale Inc. using the provided 10-Q and earnings release. Focus on revenue growth and GAAP vs non-GAAP margin reconciliation.

    • Read your context and instructions
    • Compiled the company sector evidence

    I have processed the Q3 financial data for CloudScale Inc. (Ticker: CLD). The analysis reconciled the reported $450M revenue against the provided 10-Q filing (Hash: 8f2b3c...) and verified the non-GAAP adjustments.

    Research Findings: CloudScale Inc. Q3

    MetricValueBasisSource ReferenceStatus
    Total Revenue$450.2MGAAP10-Q, p. 4Verified
    Revenue Growth22% YoYGAAPEarnings Release, p. 1Verified
    Operating Margin12.5%GAAP10-Q, p. 6Verified
    Adj. Op Margin18.2%Non-GAAPEarnings Release, p. 3Verified
    SBC Expense$25.7MGAAP10-Q, p. 14Verified

    Interpretation

    CloudScale's 22% YoY growth is driven by a 30% increase in subscription revenue, partially offset by a decline in professional services. The 570bps spread between GAAP and Non-GAAP margins is entirely attributable to Stock-Based Compensation (SBC) and a one-time restructuring charge of $4.2M. The figures are consistent across the 10-Q and the investor deck, with no conflicting restatements identified in the provided period.

    Catalyst & Risk Table

    • Catalyst: Expansion into EMEA market (Management forecast, Q4 launch).
    • Risk: Concentration risk; top 3 customers account for 28% of ARR (Source: 10-Q Risk Factors).

    Unresolved: The impact of the new tax residency in Ireland was mentioned in the call but not quantified in the 10-Q.

    Next steps

    1. Review the specific SBC vesting schedule on page 18 of the 10-Q to model future margin compression.
    2. Cross-reference the EMEA expansion targets with independent Gartner regional market reports.
    3. Quantify the tax residency impact once the FY annual report is released.

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

    About this skill

    The problem

    Manual company research often suffers from messy metric comparisons, halluncinated figures, and missing provenance. It is difficult to track whether a data point is a GAAP fact, an analyst estimate, or a management forecast across different reporting periods.

    What it does

    • Extracts financial figures with explicit metadata for currency, scale, and GAAP/non-GAAP status.
    • Enforces a source-grounded workflow requiring URLs, publication dates, and file hashes for every claim.
    • Runs a structured evidence-table checker to detect metric conflicts and context mismatches.
    • Generates cited briefs with transparent calculations and a dedicated catalyst/risk table.
    • Flags unresolved questions and incompatible accounting bases between peer companies.

    Frameworks & tools

    Python 3 for data analysis scripts, JSON for structured reporting, and Markdown for human-readable briefs.

    Why this beats prompting it yourself

    Standard LLM prompts often mix interpretations with facts and ignore restatement statuses. This skill implements a strict evidence-check protocol that treats data extraction as a formal audit process, ensuring every figure is tied to a specific file hash and reviewer status.

    Use cases

    • Due diligence for investment research or M&A.
    • Competitor benchmarking using standardized accounting bases.
    • Preparing source-grounded briefing books for executive teams.
    • Auditing internal financial datasets for conflicting metrics.

    Known limitations

    Does not include live news/filing connectors. Relies on user-provided authorized tools for source retrieval and manual input mapping for external data exports.

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

    No built-in API for live filings or news. Requires manual input mapping for external data. Does not perform independent authentication of provided source hashes or reviewer names.

    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 1 month ago

    Software
    Python

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    It checks supplied claim metadata, source references, review status, publication timing, and same-context metric conflicts. It does not authenticate source hashes, read filings automatically, or guarantee that figures are correct.

    The helper runs with Python 3.10+ and normalized JSON. Any agent may prepare the documented source and claim records, but no model-specific integration or live research connector is included.

    The package includes the instructions, local Python evidence checker, normalized JSON contract, synthetic valid and adverse fixtures, example report, runtime notes, smoke-test script, source notes, and logo. It does not include filing retrieval, extraction, or report-writing services.

    Per the technical limitations, this skill does not include pre-configured API keys for paid financial databases or live web scrapers. Users should connect it to their own authorized source retrieval tools or provide the specific documents/data exports for the skill to process.

    Install or run the Python helper, prepare normalized JSON for the entity, sources, and claims, and provide the source metadata and reviewer fields required by the contract. Source retrieval and claim review happen outside the helper.

    It flags conflicting values only when claims share the same metric name, period, unit, and accounting basis. Comparing GAAP and non-GAAP figures, currencies, or incompatible periods requires external normalization and review.

    New in Research & Analysis