scibrief

    1

    Distill scientific papers into high-density, graphical-abstract-style briefs with quantitative evidence.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    scibrief

    Example session with this skill installed

    Summarize the paper I just uploaded about GR activation and FAS repression in breast cancer metastasis. Include the key numbers and a PDF version.

    • Read your context and instructions
    • Compiled the scibrief
    • Generated the document

    I have analyzed the provided paper and distilled it into a high-density brief. I've also generated a formatted PDF for your records.

    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
    📄 GR activation in DTCs represses FAS to evade immune killing;
    GR blockade + anti-PD-1 reduces metastasis
    Nature | 2025 | Vander Steen et al.
    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

    🔬 THE STORY
    ❓ Gap → How do DTCs survive immune surveillance during metastatic seeding?
    🧪 Approach → Jedi mice + 4T1 TNBC model, niche-labeling, scRNA-seq, CUT&RUN
    💡 Finding → GR activation transcriptionally represses FAS, blocking FAS-FASL killing
    🎯 So What → Reveals GR-FAS axis as immune evasion mechanism; enables combination therapy

    📊 KEY NUMBERS
    ▸ GR-KD DTCs: 4.2-fold ↑ FAS expression (p = 0.003, n = 6/group)
    ▸ Mifepristone + anti-PD-1: median survival 42 vs 28 days (HR = 0.41)
    ▸ shGR DTCs: 3.5-fold ↑ immune clearance (p < 0.001)

    ⚙️ MECHANISM
    GR binds FAS regulatory regions as a transcriptional repressor; FAS downregulation
    blocks FASL-mediated apoptosis, enabling DTCs to evade CD8+ T and NK cell killing.

    🧭 BOTTOM LINE
    Novel concept → GR-FAS axis as metabolic-immune checkpoint in metastasis
    New method → Niche-labeling platform for DTC-microenvironment tracking
    Clinical angle → GR antagonists (mifepristone) + ICB for TNBC metastasis prevention

    ⚠️ CAVEATS
    Mouse model validation, limited human samples, long-term GR inhibition side effects
    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

    Next steps

    1. Review the generated scibrief_vandersteen_2025.pdf for the visual layout.
    2. Use the "Mechanism" section to draft a follow-up experimental hypothesis.
    3. Share the text brief directly into your lab's Slack channel.

    scibrief_vandersteen_2025.pdf

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Scientists and computational biologists are overwhelmed by the volume of new literature. Reading a full paper takes an hour, while abstracts often omit the specific quantitative evidence needed to judge a study's merit. This skill extracts the intellectual core of a paper and compresses it into a high-density, structured brief designed for 60-second consumption.

    What it does

    • Structured extraction identifies the specific research gap, experimental strategy, and central findings without narrative padding.
    • Quantitative focus isolates the top three impactful results, including effect sizes, p-values, and sample sizes.
    • Mechanistic modeling distills the biological mechanism into a single, actionable sentence for experimental follow-up.
    • Advance classification categorizes the work by conceptual, methodological, or translational impact.
    • Visual formatting produces standardized text cards or professional PDF briefs with color-coded zones for rapid scanning.

    How it works

    1. Upload a PDF, text file, or provide a DOI/title for the agent to ingest the full study text and figures.
    2. Analyze the methods, figure legends, and supplementary data to find the strongest signals.
    3. Format the output into a structured card using six distinct visual zones for the story, data, and caveats.
    4. Export a slide-ready PDF via a Playwright-based HTML-to-PDF pipeline if a formal deliverable is required.

    Frameworks & tools

    The skill utilizes Python for data extraction and Playwright (Chromium) for generating formatted PDFs with CSS-based visual hierarchies.

    Why this beats prompting it yourself

    Generic prompts often return generic summaries that read like slightly rephrased abstracts. This skill enforces strict informational density, requiring specific quantitative evidence and mechanistic clarity while aggressively filtering out background noise and author narrative.

    Use cases

    • Journal Club preparation to generate quick-scan briefs for lab meetings or Slack shares.
    • Literature triaging to decide which papers from a weekly search deserve a deep read.
    • Slide deck creation by extracting "Story" and "Key Numbers" blocks directly into presentations.
    • Preprint evaluation to check for statistical rigor and caveats before citing new work.

    Known limitations

    This skill is optimized for single-paper distillation. It does not perform systematic literature reviews or meta-analyses across multiple documents.

    Optimized for biology and life sciences. Not intended for multi-paper synthesis or meta-analysis. PDF generation requires Playwright and Chromium.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    • Free with an Agensi account

    Requires

    GitHub
    Git

    Permissions

    Terminal / Shell
    Browser
    Network Access
    Write Files
    Environment Variables

    Allowed Hosts

    raw.githubusercontent.com
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    While general models often rephrase the abstract, scibrief uses specialized logic to extract hard data—like effect sizes and p-values—and filters out narrative fluff to provide a high-density brief designed for 60-second technical review.

    The skill accepts PDFs, plain text files, and even DOIs or titles, allowing the agent to fetch and ingest the full study text, including figure legends and supplementary data, for a comprehensive analysis.

    Your purchase includes the scibrief skill package, featuring the structured extraction logic, the mechanistic modeling engine, and the Playwright-based PDF generation pipeline for creating slide-ready summaries.

    scibrief is optimized for the life sciences and computational biology, where it excels at identifying experimental strategies and biological mechanisms, though it can be applied to other quantitative STEM fields.

    The skill is designed for single-paper distillation to ensure maximum depth and quantitative accuracy; it is not currently intended for cross-paper meta-analyses or systematic literature reviews.

    New in Research & Analysis