Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    literature evidence mapping

    1

    This skill automates record screening and thematic coding to build structured evidence maps.

    $1.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    literature evidence mapping

    literature evidence mapping

    Example session with this skill installed

    Map these 5 abstracts on digital health to my themes: 'Telemedicine' (keywords: remote, video, consult) and 'Wearables' (keywords: sensor, watch, tracker). Min threshold is 2.

    • Read your context and instructions
    • Compiled the literature evidence mapping

    I have processed the 5 literature records against your defined themes and parameters. The screening script has categorized the records and identified evidence levels based on source types.

    Literature Evidence Map — 2023-11-20

    1. Screening Summary

    • Total Records: 5
    • Included: 4
    • Excluded: 1 (Reason: Missing abstract)
    • Inclusion Rate: 80%

    2. Evidence Map Matrix

    ThemeStrongModerateLimited
    Telemedicine110
    Wearables011

    3. Research Gaps

    • Theme: Wearables
    • Type: Evidence Quantity Gap
    • Status: 2 records (Threshold: 2)
    • Recommendation: Monitor emerging sensor data studies; current evidence is below the high-confidence threshold.

    4. Coded Records

    IDStatusMatched ThemesStrength
    REC001IncludedTelemedicineStrong
    REC002IncludedTelemedicineModerate
    REC003IncludedWearablesModerate
    REC004IncludedWearablesLimited
    REC005ExcludedN/AN/A

    5. Theme Coverage

    • Telemedicine: 50% (2/4 included records)
    • Wearables: 50% (2/4 included records)

    6. Assumptions and Warnings

    • Assumption: Records from peer-reviewed journals are treated as Strong sources.
    • Warning: REC004 matched 'tracker' but the context is borderline; manual review recommended.

    7. Recommendations for Human Review

    • The high concentration of Strong evidence in Telemedicine suggests a mature sub-topic. (Computed result)

    Analytical estimate — validation required: The lack of Strong evidence in Wearables may reflect the pilot-study nature of the current record set.

    This evidence map supports, and does not replace, systematic review methodology and expert judgment.

    Next steps

    1. Review REC004 to confirm if the 'tracker' keyword match aligns with your Wearables definition.
    2. Increase the min_evidence_threshold if you require higher stringency for the gap analysis.
    3. Import the Coded Records table into your systematic review software for full-text screening.

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

    About this skill

    Manual literature screening for scoping reviews is slow and prone to inconsistency. This skill automates record screening and thematic coding to build structured evidence maps.

    What it does

    • Automated Screening filter records against inclusion criteria like date ranges, source types, and mandatory keywords.
    • Thematic Coding assigns papers to specific research themes using systematic keyword and synonym matching in abstracts.
    • Evidence Mapping generates a matrix crossing defined themes with evidence strength categories.
    • Gap Identification flags themes with insufficient coverage based on user-defined evidence thresholds.

    How it works

    1. Input Records provide a collection of literature abstracts and a list of themes with associated keywords.
    2. Schema Generation the skill extracts these into a structured JSON request including screening parameters and evidence thresholds.
    3. Deterministic Mapping a dedicated script processes the records to ensure consistent inclusion and coding logic.
    4. Structured Reporting the agent produces a standardized evidence map report covering screening stats, matrices, and research gaps.

    Frameworks & tools

    This skill uses a Python-based execution environment for deterministic processing. It relies on JSON schema validation for input integrity and keyword-matching algorithms for thematic classification.

    Why this beats prompting it yourself

    Standard prompts often hallucinate counts or apply inclusion criteria inconsistently across large batches of abstracts. This skill uses a self-contained logic script to ensure every record is processed against the exact same rules, providing stable, audit-ready numbers.

    Use cases

    • Scoping Reviews rapidly map the breadth of literature in a new research area.
    • Evidence Synthesis categorize a large corpus of papers into a theme-by-strength matrix.
    • Grant Proposals identify and document specific research gaps to justify new studies.
    • Policy Briefs summarize the strength of evidence across different policy themes.

    Known limitations

    This skill performs abstract-level keyword matching only. It cannot perform full-text analysis, assess the quality of study methodology, or conduct statistical meta-analyses.

    Analyzes abstracts only, not full-text. Requires abstracts for thematic coding. Keyword-based matching cannot assess study validity or argument quality.

    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 day ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    The skill requires a structured collection of literature abstracts (such as those exported from PubMed or Zotero) and your specific list of research themes and inclusion keywords. It processes these through a JSON schema to ensure your screening criteria are applied consistently.

    Unlike standard LLM prompting which can be inconsistent with large datasets, this skill uses a deterministic logic script to process records. This ensures that every abstract is evaluated against the exact same rules, providing the stable, audit-ready counts required for formal research.

    The skill generates a standardized evidence map report, which includes a cross-tabulated matrix of themes versus evidence strength, detailed screening statistics, and a targeted list of identified research gaps.

    This skill is designed for high-level thematic mapping and gap identification based on abstracts; it does not perform deep full-text analysis or qualitative risk-of-bias assessments. It is best used for the initial scoping and categorization phases of a review.

    Upon purchase, you receive the AI agent skill configuration, the underlying Python-based execution environment for local or cloud processing, and the JSON schema templates needed to structure your literature data.