Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Autonomous Deep Research & Source Verification Agent

    1

    Rigorous research agent for verifying claims, auditing source credibility, and cross-checking evidence across domains.

    $39.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Autonomous Deep Research & Source Verification Agent

    Autonomous Deep Research & Source Verification Agent

    Example session with this skill installed

    Research the current market share of RISC-V in server CPUs as of 2024. Verify the claims using primary industry reports and identify any conflicting data between sources.

    • Read your context and instructions
    • Compiled the autonomous deep research

    I have completed a deep research investigation into RISC-V server CPU market share for 2024. I focused on primary disclosures from the RISC-V International foundation, industry analyst reports from SHD Group and Omdia, and official vendor announcements.

    RISC-V Server CPU Research Report (Cut-off: May 2024)

    Executive Summary

    The market share for RISC-V in the server segment remains in the "early adoption" phase, estimated at less than 2% of the total server CPU market by volume. While growth in the broader RISC-V ecosystem is rapid (expected 40% CAGR), the server market is currently dominated by evaluation deployments and specialized accelerators rather than general-purpose high-performance computing (HPC) replacements for x86 or ARM.

    Claim Verification Matrix

    Claim IDExact ClaimBest EvidenceCorroborationStatusConfidence
    C-001RISC-V to capture 16% of server market by 2030SHD Group Report (Jan 2024)Omdia IoT/Data Center ForecastAttributedMedium
    C-002Meta uses RISC-V for AI video transcodingMeta Engineering Blog (May 2023)Semianalysis Tech ReviewVerifiedHigh
    C-00310 billion RISC-V cores shipped by 2024RISC-V InternationalMultiple vendor press releasesCorroboratedHigh

    Contradictions and Alternative Explanations

    A material disagreement exists regarding "market share" definitions. SHD Group calculates share based on "processor cores," while traditional analysts (IDC/Gartner) use "socket shipments." Because a single AI accelerator may contain hundreds of small RISC-V management cores, the "core count" share is significantly higher than the "server socket" share.

    Source Register

    • S-001: RISC-V International, "2023 Annual Review," published Feb 2024. Primary Source.
    • S-002: SHD Group, "RISC-V Market Analysis: Server & Data Center," published Jan 2024. Secondary Research.
    • S-003: Meta Engineering, "Scalable Video Transcoding with RISC-V," official blog post. Primary Evidence.

    Next steps

    1. Review the SHD Group report to distinguish between "management cores" and "application processors."
    2. Investigate upcoming 2025 roadmaps from Ventana Micro Systems and Tenstorrent for high-performance server silicon.

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

    About this skill

    Web search results often return a high volume of low-quality links or AI-generated summaries that lack true verification. This skill provides a rigorous, evidence-first framework for developers and researchers who need to validate claims, cross-check sources, and produce decision-ready reports with full traceability.

    What it does

    • Evidence verification breaks down complex statements into individual claims and checks them against authoritative primary sources.
    • Source auditing evaluates the authority, provenance, methodology, and potential bias of any reference or institution.
    • Contradiction mapping identifies and analyzes disagreements between credible sources to find the most accurate interpretation.
    • Quantitative auditing verifies datasets, recalculates ratios, and checks for survival bias or inconsistent units in statistical reporting.
    • Research synthesis produces structured artifacts like evidence matrices and source registers with traceable citations.

    How it works

    1. Frame the Objective by defining precise research questions, sub-questions, and evidence requirements.
    2. Execute Discovery by searching for primary documents, official records, and original research datasets.
    3. Analyze and Verify using the Claim Verification Matrix to cross-check findings against independent corroboration.
    4. Final Synthesis delivers a report organized by finding, complete with confidence levels and a full source register.

    Frameworks & tools

    This skill is designed for use in AI agents with web search capabilities and document processing tools. It uses structured logic compatible with any LLM that supports markdown output and multi-step reasoning.

    Why this beats prompting it yourself

    Generic prompts often lead to "citation dumping" where an agent provides links that do not actually support the text. This skill enforces a claim-level verification logic that prevents the agent from claiming a fact is verified just because it appeared in a search snippet.

    Use cases

    • Conduct technical due diligence on a new technology or market competitor.
    • Fact-check marketing claims or technical specifications against original data.
    • Build a timeline of events using independent, corroborated news and official records.
    • Perform a literature review to identify gaps in existing research or documentation.

    Known limitations

    Does not provide professional legal, medical, or financial determinations. Cannot bypass paywalls or access private, restricted, or non-public datasets.

    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.

    Requires web search and document access. Cannot access paywalled content or private records. Not a substitute for professional legal or financial advice.

    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 2 days ago

    Permissions

    No special permissions declared or detected

    Listed2 days ago

    What's inside

    Frequently Asked Questions

    Unlike standard prompts that simply summarize search results, this skill implements a claim-level verification matrix that requires each statement to be cross-checked against independent primary sources before it is accepted as a fact.

    The skill is designed as a logic-based framework compatible with any LLM that supports multi-step reasoning and markdown output, specifically optimized for agents with web browsing and document analysis tools.

    You will receive the complete logic framework, including the Claim Verification Matrix, instructions for source auditing, and structured templates for generating evidence-based reports.

    While the agent can navigate the live web to find the most current public data, it cannot bypass paywalls or access private internal databases that are not publicly indexed.

    Yes, the framework is highly modular, allowing you to define specific evidence requirements or adjust the 'confidence level' thresholds to match the rigor needed for your specific industry.

    New in Research & Analysis