Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    Medical & Clinical Writing Skill for AI Agents

    2

    Give your agent CMPP-certified medical-writing expertise — 30+ frameworks for clinical manuscripts, congress content, and regulatory QC. Build compliant pharma/biotech workflows that pass MLR and peer review.

    Free

    3 installsSecurity scanned
    Medical & Clinical Writing Skill for AI Agents

    Medical & Clinical Writing Skill for AI Agents

    Example session with this skill installed

    Draft a data-anchored conclusion for a phase 3 RCT of Drug X in first-line mCRC with n=450, HR 0.62 for PFS, and 12% Grade 3/4 AEs. Use the Structured Abstract framework.

    • Read your context and instructions
    • Compiled the medical & clinical

    Conclusion: In this phase 3 RCT (n=450), Drug X significantly improved PFS vs placebo (HR 0.62; 95% CI, 0.48-0.81; p<0.001). The safety profile was consistent with previous reports, with Grade 3/4 AEs occurring in 12% of patients. These data support Drug X as a new SoC in first-line mCRC.

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

    About this skill

    Equip your AI agent with medical & clinical writing expertise

    Give any AI agent production-grade medical and scientific writing capability. Built by a CMPP-certified PhD with 10+ years in pharma, this skill turns a general-purpose agent into a domain specialist that drafts to AMA style and CONSORT/STROBE standards — output that survives peer review and MLR, not generic "fluff." Ideal for developers building agents for life-sciences, medical-affairs, or regulatory clients.

    What it does

    This skill transforms an AI agent into a professional medical writing partner. It supports the entire publication lifecycle, including:

    • Journal Submissions: Draft IMRaD sections, structured abstracts, and cover letters.
    • Congress Deliverables: Create ASCO/ASH-compliant abstracts, poster narratives, and oral scripts.
    • Strategic Planning: Conduct gap analyses, journal selection, and publication planning.
    • QC & Compliance: Execute AMA-style edits, MLR promotional checks, and statistical reporting audits according to CONSORT/STROBE.

    Why use this skill?

    General AI often lacks the nuance needed for medical communications, frequently producing "fluff" or promotional language that fails MLR review. This toolkit enforces data-anchored, non-promotional tone and ensures precise reporting of effect sizes (95% CI) and p-values. It includes the ADAPT framework (Audience, Document, Accuracy, Purpose, Tone) to ensure every output is fit for its specific regulatory or academic context while maintaining strict data safety protocols.

    See it in action: MLR compliance check

    Prompt:
    "Use the promotional language check tool to review this manuscript sentence for MLR compliance: Drug X is a breakthrough therapy that dramatically outperforms all competitors and offers unmatched, superior efficacy for every patient."

    Output:

    This sentence contains several elements that would likely be flagged during an MLR (Medical-Legal-Regulatory) review due to promotional bias and the lack of qualifying data.

    Here is a breakdown of the compliance concerns and suggested revisions:

    Compliance Review

    • "Breakthrough therapy": This is a specific regulatory designation by the FDA. Using it as a marketing term rather than a factual statement regarding regulatory status is misleading.
    • "Dramatically outperforms all competitors": This is a direct comparative claim. Unless you have robust, statistically significant head-to-head data against all competitors, this is non-compliant and potentially disparaging.
    • "Unmatched, superior efficacy": "Unmatched" is a superlative that is rarely, if ever, substantiated by clinical data. "Superior" requires specific, pre-specified statistical evidence from a comparative trial.
    • "For every patient": This is an absolute claim. Clinical data typically demonstrates efficacy in specific patient populations; claiming "every patient" ignores potential non-responders and safety profiles, making it highly non-compliant.

    Suggested Compliant Alternatives

    Option 1 (Focus on specific data): "In clinical trials, Drug X demonstrated statistically significant improvements in [Primary Endpoint] compared to [Specific Control/Comparator] in patients with [Indication]."

    Option 2 (Focus on clinical profile, if data is limited): "Drug X offers a new treatment option for patients with [Indication], providing meaningful clinical benefits as observed in [Study Name/Reference]."

    Recommendation: Remove all superlatives ("unmatched," "dramatically") and absolute claims ("every patient"). Replace comparative language with precise references to the specific study data and the patient population for which the drug is indicated.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    3 installs

    Downloaded by developers to date

    Free forever

    No account required to browse

    Trust & safety

    Security scanned

    Verified clean 3 months ago

    • Free to download with an account

    Listed3 months ago
    Updated29 days ago

    Frequently Asked Questions