mine2digest

    1

    A systematic literature review pipeline for dual-agent screening, evidence extraction, and auditable draft verification.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    mine2digest

    Example session with this skill installed

    Initialize a new literature project for "CLIP multimodal generalization", add 10 candidates from OpenAlex, and show me the screening queue.

    • Read your context and instructions
    • Compiled the mine2digest

    I have initialized the workspace and populated the candidate database with 10 records from OpenAlex regarding CLIP multimodal generalization.

    Workspace Initialization & Discovery

    StepActionStatusResult
    1mine2digest initSuccessWorkspace m2d/ created
    2openalex_seed.pySuccess10 candidates retrieved
    3add-candidatesSuccess10 records inserted to SQLite
    4next-candidatesPending10 papers awaiting dual-agent votes

    Current Screening Queue (Top 5)

    IDTitleSourceYearStatus
    oa:W4289...Learning Transferable Visual Models...openalex2021candidate
    oa:W3162...Robust Fine-tuning of Zero-shot Modelsopenalex2022candidate
    oa:W4301...Multimodal Few-Shot Learning with CLIPopenalex2023candidate
    oa:W2987...Evaluating CLIP on Out-of-Distribution...openalex2021candidate
    oa:W3210...Scaling Language-Image Pre-trainingopenalex2022candidate

    Next steps

    • Edit m2d/config/experiment_brief.md to refine the PICO criteria for screening.
    • Run mine2digest next-candidates --agent-id A --limit 10 to start the first screening pass.
    • Provide your UNPAYWALL_EMAIL in the .env file to enable PDF fetching for confirmed papers.

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

    About this skill

    Researching literature for academic papers or technical reports often results in fragmented notes, lost citations, and biased selection. Manually verifying every claim against PDF text is slow and prone to "hallucinated" evidence.

    This skill automates the literature pipeline from discovery to evidence extraction. It enforces a strict dual-agent screening process to eliminate bias, where two independent agents vote on candidates based on your specific research brief. It fetches full-text PDFs, extracts evidence cards with mandatory word-for-word source verification, and generates coverage matrices to identify gaps in your research. Every claim is back-linked to a specific text span in the source PDF using fuzzy locator matching, ensuring an auditable trail from draft to source.

    What it does

    • Dual-Agent Screening executes independent PICO and rule-based voting to filter candidates without cross-contamination.
    • Evidence Extraction creates cards containing verbatim text spans from PDFs with automatic locator verification.
    • Audit Logging maintains a SQLite database as the single source of truth for every paper state and evidence claim.
    • Coverage Analysis generates matrices of sections versus evidence types to highlight research gaps.
    • Draft Verification validates that every citation in a generated draft exists in the evidence database.
    • Figure Analysis extracts figure captions and context to suggest design directions based on existing literature.

    How it works

    1. Initialize the workspace using mine2digest init to set up the local database and research brief.
    2. Discover candidates by running seed scripts for OpenAlex or Semantic Scholar to populate the inbox.
    3. Screen papers by dispatching independent sub-tasks for Agent A and Agent B, then talling votes.
    4. Extract evidence by fetching PDFs and running the reader agent to generate verified evidence cards.
    5. Verify outputs by running coverage reports and checking drafts against the evidence database.

    Frameworks & tools

    Built for Python environments using SQLite for data persistence. It integrates with OpenAlex and Semantic Scholar APIs for discovery and Unpaywall for PDF retrieval. It uses rapidfuzz for text span verification and GitHub-flavored Markdown for all exports.

    Why this beats prompting it yourself

    Standard prompting often ignores source constraints or mixes up citations across multiple papers. This skill enforces a structured state machine and verbatim text matching that prevents the agent from "inventing" supporting evidence. The dual-blind screening logic ensures a higher level of systematic rigor than a single-pass prompt could achieve.

    Use cases

    • Conducting systematic literature reviews for academic publications.
    • Building a verified knowledge base for technical whitepapers.
    • Auditing existing drafts to ensure every claim has a direct source quote.
    • Identifying missing evidence types in a specific section of a manuscript.

    Known limitations

    Requires external API keys for OpenAlex or Unpaywall for full functionality. Does not support direct PDF editing or complex multi-step reasoning outside the defined pipeline phases.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires UNPAYWALL_EMAIL in .env for PDF fetching. Database modification only via CLI. Evidence spans must be verbatim. Vision capabilities required for figure design analysis.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 days ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Write Files
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    The dual-agent screening process uses two independent AI agents to evaluate papers based on your research brief; a paper only moves forward if they reach a consensus, eliminating the 'positive bias' common in single-prompt AI searches.

    Every claim generated includes a verbatim text span and a fuzzy locator that links back to the exact section in the source PDF, allowing you to instantly verify the evidence in the SQLite audit log.

    The skill is built for Python environments and integrates with OpenAlex, Semantic Scholar, and Unpaywall; while it is LLM-agnostic, it performs best with agents capable of structured data extraction and long-context window processing.

    You will receive the full Python source code for the pipeline, the SQLite database schema for audit logging, and pre-configured templates for research briefs and coverage matrices.

    The pipeline requires API keys for OpenAlex or Semantic Scholar for discovery and Unpaywall for PDF retrieval, as well as a local Python environment to host the SQLite database.

    New in Agents & Orchestration

    Free