More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Primary Market Research Report

    1

    A PE/VC-style sector research method: written scope lock, sourced evidence base, market sizing anchored two independent ways, thesis-first drafting, and an editor-grade QC gate.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Primary Market Research Report

    Primary Market Research Report

    Example session with this skill installed

    We're a small fund looking at refurbished enterprise IT equipment — laptops, mainly — in the US. Is this sector worth a closer look? We need a short brief to decide whether to commission a full report, and we don't have access to paid deal databases.

    • Read your context and instructions
    • Compiled the primary market research

    Scope lock, recorded before any research: Sector — US refurbished enterprise laptops, B2B resale channel. Out of scope: consumer refurb, phones and tablets, non-US markets. Window: 2021–2026 history, 2029 horizon. Reader: your investment committee. Decision: commission a full study or pass. Mode: argument-led brief, 6–8 pages. Your existing position: none stated — recorded, so the brief tests the sector cold rather than confirming a hunch.

    Evidence plan, built for no paid databases: Tier 1–2 anchors come from listed-company disclosures (public refurbishers and IT-asset-disposition firms report segment data) and federal surplus and procurement records; Tier 3 is the industry association's annual volume reporting. The funding map runs on filings and press releases — deal databases are a convenience in this sector, not a dependency, and the method note will say exactly that.

    Sizing, two anchors, with inputs exposed rather than dressed up: top-down, the strongest published US estimate for refurbished enterprise computing, its category definitions checked so consumer devices do not inflate it; bottom-up, annual enterprise laptop retirements × refurb capture rate × average resale price. If the anchors land within roughly a quarter of each other, the brief uses the range; if they diverge, the spread itself becomes a finding with a named cause.

    Working thesis, stated to be tested and not served: "Supply is structurally rising — shorter corporate refresh cycles, return-to-office surplus — while demand is price-elastic and the resale channel is concentrated; margin sits with whoever owns grading and certification, not with whoever holds inventory." The body sections exist to attack that sentence: unit economics, channel concentration, and OEM refurb programs each get their strongest counter-evidence. The closing states what would overturn it and what a full report would need to resolve.

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

    About this skill

    Sector reports usually fail in one of two directions: the encyclopedia — forty pages, no point of view — or the brochure, a conclusion with charts hired to support it. This skill produces the kind of study a private-market investor actually reads: a thesis up front, every number sourced, and enough evidence that the conclusion feels earned.

    It starts with a scope lock, in writing, before any research: sector boundary and named exclusions, geography, time window, whose decision the report informs, memo or compendium mode, and — critically — any position the requester already holds, recorded so the report tests it instead of quietly serving it. The evidence base is built to a standard: a funding-history map that reads capital flows as a pattern, market sizing anchored twice (a top-down published figure and a bottom-up build, with the spread between them disclosed and a side picked for a stated reason), and a five-tier source hierarchy that decides what may support a key claim and what is only corroboration.

    Drafting is thesis-first: section headings that are claims rather than topics, one chart per point with an assertion title and a dated source line, and a closing that states what the evidence implies for deploying capital — including what would change the thesis. A ten-point QC gate closes the work: every number traced to its source, exec summary claims verified against the body, no unnamed-source support anywhere. The method degrades honestly when data is thin or paywalled — the claim shrinks, the standard does not.

    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.

    This is a method, not a data subscription: it does not include access to any paid database, and figures are only as current as the sources the agent can reach — every source line carries a date so staleness is visible rather than hidden. In sparse-data sectors the method deliberately narrows claims instead of manufacturing precision, which means some briefs conclude "not yet knowable" with the gaps named. It produces analysis, not investment advice, and it will not write a report backwards from a conclusion you supply — the scope lock records your position so the research can test it honestly.

    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 24 days ago

    Permissions

    No special permissions declared or detected

    Listed24 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    Yes — that case is designed for. The evidence plan re-anchors on regulatory filings, listed-company disclosures, association data, and trade press, and the report's method note discloses the access limit. The two-anchor sizing rule and the source hierarchy still apply; the anchors come from lower tiers, labeled as such.

    Discipline at three points a chat answer skips: a written scope lock (including your existing position) before research starts, market sizing anchored two independent ways with the disagreement disclosed, and a QC gate that traces every number on the page back to a tiered source — or removes it. The output is a report built to be argued with, not a summary built to be skimmed.

    It will test it, which is the useful version of that request. Your position is recorded at scope lock, the body must include the strongest evidence against it, and the closing names what would change the thesis. If the evidence supports you, the report says so with receipts; if it doesn't, you find out before your capital does.

    New in Research & Analysis