sciwrite prose

    1

    Scientific prose editor based on Stanford's Writing in the Sciences to cut clutter and improve technical clarity.

    Free

    2 uses2.0 (1 review)

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    sciwrite prose

    Example session with this skill installed

    Review this paragraph for clarity and word count: "It should be noted that there is a significant amount of evidence which suggests that the data are not in agreement with previous studies."

    • Read your context and instructions
    • Compiled the sciwrite prose

    I have reviewed the sentence using the clutter and verb passes. I removed the dead-weight opener and converted the weak "to be" construction into a more precise active verb.

    Prose Edit: Evidence Review

    Original TextRevised TextReasoning
    It should be noted that there is a significant amount of evidence which suggests that the data are not in agreement with previous studies. (24 words)Evidence suggests these data contradict previous studies. (7 words)Removed "It should be noted that there is" (clutter) and "not in agreement with" (nominalization).

    Next steps

    1. Review the surrounding sentences to ensure "these data" clearly refers to the specific dataset mentioned previously.
    2. Run numeric_consistency.py to verify that the specific data points causing this contradiction are cited correctly in the results section.
    3. If this is for a Methods section, consider if the passive voice is preferred by your target journal for this specific claim.

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

    About this skill

    Scientific writing often suffers from dense, circular prose that obscures research value. This skill applies the principles of Stanford's Writing in the Sciences to tighten technical manuscripts, grant proposals, and abstracts at the sentence and paragraph level. It prioritizes clarity and the reader's effort over formal fluff.

    What it does

    • Prose auditing by identifying clutter, dead-weight openers, and redundant prepositions.
    • Verb optimization by converting unnecessary passive voice to active and identifying buried predicates.
    • Paragraph restructuring using the upshot method to eliminate repetition and logical gaps.
    • Consistency checking for terminology, acronym usage, and numeric data across sections.
    • Punctuation refinement using colons, semicolons, and dashes to vary rhythm and improve flow.

    How it works

    1. Submit text such as a single sentence, a full paragraph, or a file path for a manuscript section.
    2. Execute scripts like prose_audit.py or keyword_consistency.py to flag candidates for revision.
    3. Review the upshot for paragraphs, where the agent reduces text to plain-line points before rewriting.
    4. Apply the five-pass audit (Clutter, Verbs, Punctuation, Terminology, Consistency) in sequence.

    Frameworks & tools

    This skill includes Python scripts for automated text extraction and auditing. It supports .tex, .docx, .md, and .txt formats.

    Why this beats prompting it yourself

    Generic prompts often result in "flowery" AI writing that violates scientific standards. This skill uses a specific five-pass protocol and the upshot method to ensure edits stay grounded in the Stanford methodology without changing scientific claims.

    Use cases

    • Shorten abstracts to meet strict word limits without losing critical data.
    • Clarify Methods sections by fixing parallelism and terminology drift.
    • Tighten Discussion sections by removing buried predicates and weak "to be" verbs.
    • Polish grant proposals to ensure the main point and significance appear early.

    Known limitations

    Does not judge scientific correctness or restructure whole manuscripts into IMRaD sections. The Python scripts require local installation to run automatically on files.

    Does not judge scientific accuracy. Requires local script installation for file processing. Designed for sentence/paragraph level edits rather than whole-document structural engineering.

    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

    2.0
    1 review
    5
    0
    4
    0
    3
    0
    2
    1
    1
    0

    This skill has been used 2 times.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Node.js

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike general-purpose AI that often adds "fluff," this skill follows a strict five-pass protocol based on Stanford's methodology to actively remove clutter, unbury verbs, and shorten text while preserving your scientific claims.

    The skill includes a suite of Python scripts (`prose_audit.py`, `keyword_consistency.py`) and specific logic for the 'upshot method' of paragraph restructuring, supporting .tex, .docx, .md, and .txt formats.

    The Python auditing scripts require a local installation to process files automatically; however, you can also use the skill manually by submitting text snippets directly to your AI agent.

    No, the skill focuses on sentence and paragraph-level clarity; it does not verify the accuracy of your data or reorganize the high-level IMRaD (Introduction, Methods, Results, and Discussion) structure of your manuscript.

    Yes, one of the primary use cases is using the 'clutter audit' pass to significantly reduce word counts in abstracts and discussion sections without sacrificing technical detail.

    New in Research & Analysis