More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Equity Research: Tear Sheets and Deep Dives

    1

    Analyze a company the disciplined way: triage the request, source every number, work six dimensions, value in layers, and state what would prove the thesis wrong.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Equity Research: Tear Sheets and Deep Dives

    Equity Research: Tear Sheets and Deep Dives

    Example session with this skill installed

    Analyze Northgate Components for me. I have a meeting tomorrow and need something I can read in one sitting — not a giant report.

    • Read your context and instructions
    • Compiled the equity research

    TEAR SHEET (excerpt) — produced by applying the skill. Triage: the request named a deadline and one sitting, so the skill delivered a tear sheet, Level 1 valuation — not the 25-page pipeline.

    Northgate Components — industrial fasteners and assemblies specified into customers' certified designs. As-of date stated; all figures sourced from the latest filing and cross-checked.

    Business and moat: switching cost. Requalifying a rival supplier takes customers 9–14 months, so revenue is stickier than the "commodity parts" label suggests. Erosion path named: two large customers began dual-sourcing last year. So what: the moat is real but narrowing.

    Financial quality: revenue +6%, decomposed as volume +2%, price +5%, mix −1%. Growth is mostly pricing power, which reverses when contracts reset. Cash conversion 84% of operating profit; no earnings-quality flags. So what: headline growth overstates underlying demand growth.

    Valuation: 11.2× forward earnings vs. a peer median of 13.8× (peers chosen by business similarity; the multiple explained, not assumed). Own 10-year band: 9–17×. Scenarios weighted 25/50/25 — bull: qualification cycle holds, pricing sticks; base: modest share loss, pricing partially resets; bear: one dual-sourcing customer switches fully, fair value ~25% below current price.

    Thesis: the discount prices in faster share loss than the 9–14 month qualification cycle allows. Proven wrong if either dual-sourcing customer announces a full switch within two quarters.

    Data gap, stated on the sheet: segment-level margins are not disclosed, so moat strength is assessed at group level only.

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

    About this skill

    Most stock write-ups fail in predictable ways: they start formatting before the analysis exists, pick peers that flatter the multiple, print a target price with no sensitivity, and present one side of the argument. This skill enforces the order that prevents all four. It opens with intent triage — a bare factual question gets a conversational answer, an ambiguous "look into this stock" gets asked rather than defaulted to the heaviest output, and a full report gets an explicit valuation-depth choice (comparables and scenarios, or a full three-statement model with DCF). Then data discipline: real sources only, critical figures cross-verified, an as-of date on the cover, the last 7 days of news included, and any unsourceable number named as a gap with the conclusions it weakens. The analysis runs in six dimensions — business and moat, industry and position, financial quality, management and governance, catalysts and risks, valuation — and every dimension ends in a "so what" tied to the thesis. Valuation is built in layers: justified peer multiples, DCF with a growth-by-discount-rate sensitivity matrix, probability-weighted bull/base/bear scenarios that trace back to dimension findings, and the company's own historical band. Bull and bear cases are both mandatory and steel-manned. Full reports are built in stages — research document, then model, then final document — with scope confirmed between stages so the expensive hours land on agreed ground. Deliverables include the tear sheet skeleton, a six-dimension readiness rubric (ship at 10+/12, no zero on data discipline or balance), a pre-delivery checklist, and edge-case handling for pre-revenue companies, conglomerates, and recent IPOs.

    • It is research craft, not personalized financial advice: it presents sourced analysis, scenarios, and uncertainty, and the investment decision stays with the reader.
    • Output quality depends on data access — without current filings and prices it will name the gaps rather than fill them, which limits how far the valuation layers can go.
    • Full reports with a three-statement model are slow by design; if you need speed, the tear sheet mode is the honest trade.

    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 24 days ago

    Permissions

    No special permissions declared or detected

    Listed24 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    No — triage is the first step and it exists for exactly this case. A factual question gets a conversational answer. The report pipeline only starts when you ask for analysis, and when your request is ambiguous the skill asks which depth you want instead of defaulting to the heaviest output.

    Every figure must trace to a real source — filings first, cross-verified for critical numbers — and carries an as-of date. If a data point cannot be sourced, the skill says so and marks which conclusions the gap weakens. Inventing a plausible-looking number is the one failure the data discipline rules forbid outright.

    Because it is layered and falsifiable. Peer multiples are justified by business similarity, the DCF ships with a sensitivity matrix instead of a point estimate dressed up as precision, bull/base/bear scenarios are probability-weighted and trace back to specific findings, and the thesis paragraph states in writing what evidence would prove it wrong.

    New in Trading & Investing