Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Research Architect — Evidence-Driven Research

    1

    Design source-grounded research workflows with clear questions, evidence standards, verification, citations, uncertainty, and reproducible methods.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AI Research Architect — Evidence-Driven Research

    AI Research Architect — Evidence-Driven Research

    Example session with this skill installed

    We need a decision-grade research workflow to compare three project-management platforms for a 120-person remote design agency choosing a tool for the next 12 months. We have not chosen a geography-specific compliance requirement. Define the exact questions, inclusion rules, source plan, scoring model, contradiction handling, and refresh plan. Use official product documentation and independently authored evidence when available. Do not perform or claim live research; present a reusable workflow and clearly mark assumptions.

    • Read your context and instructions
    • Compiled the ai research architect

    Research Architecture: Project-Management Platform Selection

    Decision need

    Select a platform for a 120-person remote design agency for the next 12 months. This is a

    research workflow design, not a live comparison: no vendors, sources, prices, or performance claims have been researched in this example.

    Primary question

    Which candidate platform best fits the agency’s documented workflow, security, collaboration, integration, accessibility, and total-cost requirements over the decision horizon?

    Subquestions

    1. Which workflows must the platform support (intake, planning, design review, client approvals, resourcing, delivery, and reporting)?
    2. Which capabilities are mandatory, preferred, or out of scope?
    3. What current security, privacy, identity, retention, export, and administrative controls are documented?
    4. Which integrations are required, and are they native, partner-provided, or dependent on custom work?
    5. What is the 12-month total cost under realistic seats, tiers, add-ons, implementation, and support assumptions?
    6. What migration, adoption, accessibility, reliability, and exit risks need testing?

    Scope lock

    Included: platforms named by the buyer; current product capabilities; documented commercial terms; relevant independent evaluations; workflow-fit tests.

    Excluded until specified: legal certification, negotiated discounts, undocumented roadmap items, and claims about the agency’s internal systems. Geography, budget, and current stack are unknown and must be requested before final scoring.

    Source and inclusion plan

    Primary: official product documentation, security/privacy pages, status history, accessibility statements, and dated pricing/plan pages. Record the exact page, date checked, and claim supported.

    Independent: credible hands-on evaluations, public incident reporting, and research with disclosed methods. Record author, date, method, sample, and conflicts where available.

    Internal: authorized workflow requirements, integration inventory, seat estimate, test scenarios, and user feedback.

    • Exclude anonymous claims and undated marketing summaries from decisive scoring. Treat vendor statements as vendor-reported, not independently verified.

    Comparison method

    First label each requirement

    mandatory,

    preferred, or

    informational with an owner and evidence standard. Score each candidate 0–3 per requirement: 0 = no evidence or does not meet; 1 = partial or high uncertainty; 2 = meets with documented conditions; 3 = meets with strong, current evidence. Keep confidence separate from score. A missing answer is

    unknown, never a zero-quality claim. Do not average away a failed mandatory requirement.

    DimensionEvidence to collectWeight
    Workflow fitScripted scenarios with representative usersSet by buyer
    Security and administrationCurrent official docs plus security reviewSet by buyer
    Collaboration and client approvalsDemonstrated role and approval flowsSet by buyer
    Integrations and exportDocs and sandbox test where authorizedSet by buyer
    Accessibility and usabilityPublished statement plus user evaluationSet by buyer
    12-month cost and exitDated pricing, seat assumptions, export termsSet by buyer

    Contradictions and uncertainty

    Maintain a claim ledger with claim, source, date, source type, evidence excerpt or location, candidate, confidence, and status. Preserve disagreements—for example, vendor documentation versus a dated independent test—and investigate version, plan, or test-condition differences. Mark stale evidence when product terms may have changed.

    Next steps

    Confirm candidate names, geography, budget range, current stack, mandatory controls, and research deadline. Then collect dated evidence, run approved workflow trials, document assumptions, and produce a comparison with unresolved gaps and a recommendation proportional to evidence strength.

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

    About this skill

    Build research systems people can trust

    AI Research Architect designs rigorous research agents and workflows that turn a decision need into traceable, decision-ready evidence. It helps teams define the question, set scope and evidence standards, discover and screen sources, map claims to evidence, preserve contradictions, and communicate uncertainty.

    What it helps design

    • Research questions, subquestions, scope, timeframe, population, geography, and comparison logic
    • Source strategies, query plans, inclusion and exclusion rules, and freshness requirements
    • Source verification, quality assessment, deduplication, and data extraction
    • Claim-to-citation maps, provenance records, contradiction and assumption ledgers
    • Quantitative and qualitative analysis plans, alternative explanations, and confidence labels
    • Reproducible workflows with methods, filters, transformations, and refresh plans
    • Decision briefs that distinguish evidence, inference, scenario, and unknowns

    Evidence and truthfulness

    The agent never invents sources, URLs, authors, quotations, statistics, search results, citations, calculations, or findings. It uses browsing, files, connectors, datasets, and other tools only when they are actually available and authorized. When tools are unavailable, it produces a transparent research blueprint or manual-ready plan rather than implying research was conducted.

    How to use it

    Describe the decision to support, key questions, audience, scope, required freshness, source restrictions, depth, deadline, and output format. Provide authorized documents or datasets where relevant. The agent will clarify material gaps, tailor the methodology to the question type, and deliver either a research architecture or a source-grounded analysis based on actually inspected evidence.

    Boundaries

    Results depend on available evidence, tool access, and the stated scope. Research support does not replace specialist judgment in scientific, legal, financial, medical, or other high-consequence decisions. Current claims require current sources, and conclusions must not exceed what the evidence supports.

    Research quality depends on scope, source availability, freshness, and actual tool access. The skill cannot verify inaccessible sources, guarantee completeness, or replace specialist judgment. Current facts require dated evidence; citations must be checked against sources actually inspected. High-consequence scientific, legal, medical, financial, or policy decisions need qualified review.

    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 1 month ago

    Permissions

    Terminal / Shell
    Read Files
    Browser
    Network Access

    Use browsing/network access, files, or terminal/data tools only when available, in scope, and explicitly authorized. Cite sources actually checked. Do not access restricted systems, bypass controls, or claim unperformed searches, calculations, or source verification. Handle only files the user is authorized to share.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    It can produce a research plan or, when authorized tools and evidence are actually available, a source-grounded analysis with scope, methods, claim-to-source mapping, uncertainty, contradictions, gaps, and decision implications.

    Only when suitable browsing/search tools are available and authorized. It must cite sources it actually inspected and state when a source could not be verified. Without those capabilities, it produces a transparent research blueprint instead of implying searches or checks occurred.

    It records source, date, scope, and confidence; preserves contradictions; identifies missing evidence and alternative explanations; and labels inference separately from documented findings. Unknown information remains unknown until verified.

    New in Research & Analysis