More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Equity Deep Analysis

    1

    Stock Deep Analysis does the actual work of an equity research desk — and it is honest by design.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    equity-deep-analysis

    equity-deep-analysis

    Example session with this skill installed

    Deep-analyze NVIDIA (NVDA) for me. I'm deciding whether to add to my position at today's price with a 3-year horizon. My thesis on trial: "AI compute demand keeps NVDA a compounding machine at any sane price." Run the full deep memo: business quality scores, your forensics checklist, valuation triangulation, and steel-man the bear case before you give a verdict.

    • Read your context and instructions
    • Compiled the equity-deep-analysis

    Deep Analysis: NVIDIA (NVDA)

    Analysis Contract — Decision: hold / add on pullbacks · Horizon: 3 years · Thesis on trial: "AI compute demand keeps NVDA compounding at any sane price"

    VERDICT FIRST
    Hold / add on pullbacks — do not chase. The business is a genuine franchise with a widening moat and forensic-grade cash conversion; the risk is not the business, it is the price. Confidence: Medium-High (financials are [F] from filings; forward growth and live pricing are [E]/[U]).

    BUSINESS QUALITY
    Moat 5/5 — CUDA software lock-in (switching costs) plus datacenter scale (cost advantage); trend widening, no credible second source at systems scale. Unit economics 5/5 — 75.0% GAAP gross margin [F, FY2025]; SBC ~3.6% of revenue, buybacks more than offset. ROIC 5/5 — well above 50% [E], reinvestment is compounding. Management 4/5 — delivered the AI ramp; watch hyperscaler financing exposure. VERDICT: Franchise.

    FINANCIAL FORENSICS
    A1 cash conversion CLEAR — CFO $64.1B / NI $72.9B = 0.88 FY2025 [F], gap explained by receivables from hypergrowth, not accrual games. A3 receivables WATCH — AR growth outpaced revenue [F]; consistent with shipment concentration, monitor quarterly. A5 SBC dilution CLEAR. Balance sheet CLEAR — net cash, no maturity wall. Growth quality WATCH — top hyperscalers dominate Data Center revenue [F]; a capex pause at two or three of them is the biggest swing factor. ALARM: 0 · WATCH: 3.

    VALUATION
    Reverse DCF: the current price already implies years of near-flawless execution — visible near-term backlog, aggressive outer years. Scenarios (25/50/25 weights): bear ~$95 (2027 capex pause, margins compress to ~60%), base ~$165 (growth decelerates, margins ~70%), bull ~$240 (inference supercycle into 2029). Value range $95–$240, weighted ≈ $165; price sits in the upper third — margin of safety ≈ negative 9%. Reliability: Medium.

    THE BEAR CASE (steel-manned)
    NVIDIA is a cyclical supplier whose largest customers are simultaneously its financed borrowers and its most credible future competitors via custom silicon. When accelerator inventory digests, revenue falls off a cliff while margins mean-revert from peak — a double hit to EPS, the exact pattern prior compute cycles printed. The bear path is not a crash scenario; it is the reversion path.

    KEY ASSUMPTIONS · 1) Hyperscaler AI capex keeps growing through 2028. 2) CUDA-to-ASIC migration stays slower than its cost-savings promise. 3) Gross margins hold ≥ 65% through the cycle.

    KILL CRITERIA · Any top-4 hyperscaler guides AI capex down for a full year → re-review. Gross margin < 65% for two consecutive quarters → exit-criteria review. Two major inference platforms ship production workloads off-CUDA by end-2027 → moat assumption wrong.

    UNKNOWN · live price at your read time; backlog quality; off-balance-sheet demand risk.

    Decision framework, not financial advice. [E]/[U] items — verify before acting.

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

    About this skill

    Most stock skills either role-play a famous investor or pull a price and shrug. Stock Deep Analysis does the actual work of an equity research desk — and it is honest by design.

    The six-step workflow

    1 · Frame the Question — pins your ticker, the real decision (buy/add/hold/trim/sell), horizon, and your thesis on trial into a 3-line Analysis Contract. 2 · Gather Evidence — filings > transcripts > data providers > news. Every datum tagged [F]act / [E]stimate / [U]nknown. Nothing silently guessed; unverifiable items are listed as Unknowns, not hidden. 3 · Judge Business Quality — moat type and trend, unit economics, 5-period ROIC, management scorecard → verdict: Franchise / Strong / Average / Fragile. 4 · Financial Forensics — a 20+ red-flag checklist: cash conversion, accruals, receivables divergence, inventory build, SBC dilution, maturity walls, sector-specific traps. Each flag rated Clear / Watch / Alarm with the number that justified it. 5 · Triangulate Value — reverse DCF (what does the price already imply?), multiples vs. own history and peers, bear/base/bull scenario valuation with explicit weights. Always a range, never a point. If inputs are too uncertain, it says "value range unreliable" and tells you what evidence would fix it. 6 · Red-Team & Deliver — steel-mans the bear case (not a strawman), runs a pre-mortem, sets falsifiable kill criteria, and polices the memo itself against confirmation bias, anchoring, recency, sunk cost, and story capture.

    The honesty floor

    · No fabricated price targets, no guaranteed returns, ever. · Confidence (High/Medium/Low) is tied to how many inputs were estimates or unknowns. · A memo that concludes "Low confidence — wait for the FY26 filings" is a useful deliverable. Honest uncertainty is the product.

    Five dispatch paths

    Quick screen (no files read) · Deep memo (full six steps) · Red team ("poke holes in my thesis") · Valuation check ("is it overvalued?") · Earnings quality ("are these earnings real?").

    Works for US-listed, HK-listed, and A-share tickers, in English or Chinese. Every historical figure carries its fiscal period. The memo ends with a decision framework — you own the decision.

    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.

    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 8 days ago

    Permissions

    Read Files
    Write Files
    Network Access
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    Institutional-grade deep equity analysis with a red-teamed verdict. Business quality scoring, financial forensics, valuation triangulation, and falsifiable kill criteria — every claim tagged fact, estimate, or unknown. Ranges, never points.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use equity-deep-analysis on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Finance & Accounting