More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Scientific Voice: Submission-Ready Prose, English & Spanish

    1

    - **Three modes.** A full rewrite with a change log, a light edit shown before → after, or a review that only lists findings, ordered by impact.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Scientific Voice: Submission-Ready Prose, English & Spanish

    Scientific Voice: Submission-Ready Prose, English & Spanish

    Example session with this skill installed

    draft.md has the Results and discussion paragraph of my paper and its Spanish abstract. Tighten these two paragraphs for submission; keep my meaning and my terms. Put the tightened version in draft-tightened.md.

    • Read your context and instructions
    • Compiled the scientific voice

    I've tightened both paragraphs and saved them to draft-tightened.md. They went from 375 to 318 words. I didn't change any numbers, and your terms are untouched: RDI/FI/WP, RDC/PA, "yield components" and "water productivity" all read as before.

    Results and discussion

    Filler phrases cut: "It is worth noting that", "As mentioned above" (fruit number hadn't actually been mentioned earlier), "In order to", "due to the fact that".

    Vague words replaced by your numbers: "very small effect" and "rose dramatically" are gone, so the yield and WP figures now speak for themselves.

    • Shorter sentences: I split the 82-word sentence about yield components and fruit counting into three.

    Hedging: "may potentially suggest … could be adopted" had four hedges; it's now "suggest … can be adopted", keeping one. I also dropped "novel".

    • Spelling: "behavior" became "behaviour" and "optimized" became "optimised".

    Resumen

    Active first person: "se presenta", "se llevó a cabo", "se realizó un análisis" and "se calculó" became "Presentamos", "realizamos", "analizamos" and "Calculamos".

    False friends fixed: "consistentes con" became "coherentes con". "eventualmente" means "possibly" in Spanish, not "eventually", so I dropped it.

    • Decimal separator: "24.7" became "24,7" to match the commas used everywhere else in the Resumen.

    Things you need to fill in or check

    • [test? P?] after "significantly smaller fruit" (62.5 g vs 57.6 g): "significantly" needs its test and P value. Otherwise, swap it for a plain word like "smaller".
    • Possible mismatch between the two paragraphs: the Resumen defines PA using marketable yield ("rendimiento comercial"), while the English paragraph uses "fruit yield". Also, the 31% cut in irrigation water appears only in the Resumen.

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

    About this skill

    What it does

    Reviewers read your draft once. This skill makes your agent edit scientific prose so that once is enough: the finding comes first, each claim carries one hedge sized to its evidence, sentences about the text itself disappear, and every vague word gives way to the number it stands for. It works in English and Spanish, including a paper with an English Results section and a Spanish "Resumen" in the same file.

    • Three modes. A full rewrite with a change log, a light edit shown before → after, or a review that only lists findings, ordered by impact.
    • 16 voice rules, applied in order. Claim before caveat, one point per paragraph, numbers with comparators and inline tests, plain reporting of what did not work, one hedge per claim, precise words instead of hype, verbs instead of nominalisations, sentence length, tense, and one term per concept.
    • Spanish done in Spanish. Spanish hedges (including the softening conditional), "se realizó un análisis de" turned back into "analizamos", "cabe destacar que" cut, false friends such as "eventualmente", "asumir que", "consistente con" and "billón" fixed, and one decimal separator throughout.
    • Meaning is fixed. Numbers, units, citations, math and your technical terms are never changed, and a claim is never strengthened. What it cannot fix without guessing gets a visible marker such as [test?] and a question for you.
    • Your own recurring errors. A plain-text personal patterns file the linter checks on every run; when you accept the same correction twice, the agent offers to add it.

    The bundled linter

    prose_lint.py (Python 3.10+, standard library, no network, writes nothing) checks Markdown, LaTeX, reStructuredText and plain text, and decides each paragraph's language on its own. It flags hedge stacks, meta-commentary, vague intensifiers, promotional words, "significant" with no test, buried verbs, wordy phrases, Spanish false friends, mixed US/UK spelling, decimal commas in English and mixed separators in Spanish, long sentences and paragraphs, doubled words and leftover markers. House preferences (spelling variant, decimal separator, em-dash ban, banned words, limits) live in a small JSON file. In the demo it found 31 tics in one English paragraph and one Spanish abstract; after the rewrite, only one long sentence kept on purpose and three gap markers remained.

    What's included

    • SKILL.md: modes, house preferences, a 12-pass rewrite order, hard constraints and the report format
    • references/voice-rules.md: the 16 rules with before/after examples
    • references/spanish.md: hedges, impersonal and passive forms, wordy phrases, false friends, numbers and units, bilingual abstracts
    • references/lint-rules.md: every rule, configuration, personal patterns and what the linter cannot judge
    • scripts/prose_lint.py: the linter, one self-contained file with every rule and word list built in

    Part of the Aurora Lab research pipeline

    Works entirely on its own on any text you point it at. Pairs well with Aurora Lab's Claim Check (does each sentence stay inside its evidence?), Journal House Style (does the paper fit the venue?) and Test Readers (how a cold reader takes it), but needs none of them.

    It edits voice: sentences and paragraphs. It does not check whether a claim is supported by its numbers or intervals, and it does not restructure a paper to a venue's sections or word limits. It never adds results, tests or citations, so a missing test or comparator is marked ([test?], [comparator?]) for you to fill. The linter finds mechanical patterns from fixed word lists: it cannot tell whether a paragraph leads with its claim, whether a hedge matches the evidence or whether a term was renamed, and its findings are prompts to look, not orders (a quoted word, a technical use of "novel", a long sentence that reads well are fine to keep). Languages are English and Spanish only; the language of very short paragraphs is guessed from the paragraph that follows, and --lang es forces Spanish. In Spanish it does not check the gerund after a comma or quotation-mark style; numbers such as 1,250 that could be thousands are not judged. Spanish usage varies by country, so some false-friend and anglicism flags are style advice rather than errors.

    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 28 days ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    research/paper/**
    research/claims.md
    .prose-lint.json
    .prose-lint-personal.txt

    Reads the text you ask it to edit (any file or pasted text; with a research/ folder, research/paper/*) and, read-only, research/claims.md so wording stays no stronger than each claim's recorded status. Writes the revised text where you say, and edits files in place only when you ask. May write .prose-lint.json with house preferences you state and .prose-lint-personal.txt with recurring errors you agree to add. The linter reads files and writes nothing. No network access.

    Listed29 days ago
    Updated28 days ago

    What's inside

    Frequently Asked Questions

    Yes. Each paragraph is checked in its own language, so one file can hold an English Results section and a Spanish "Resumen". In Spanish it handles hedges (including the softening conditional), meta-commentary such as "cabe destacar que", buried verbs such as "se realizó un análisis de", wordy phrases, false friends such as "eventualmente" and "consistente con", and one decimal separator throughout. Other languages are not supported.

    No. Numbers, units, citations, cross-references, math and your technical terms are fixed. It never adds a result and never strengthens a claim; when a sentence needs something it does not have, such as the test behind "significantly", it leaves a marker like [test?] and asks.

    A grammar checker fixes words. This edits the shape of scientific sentences: finding before caveat, one hedge sized to the evidence, no sentences about the text, a number instead of "dramatically", the verb hidden in "performed an analysis of". It also reports each change with its reason.

    No. The agent can apply the same checks by reading. With Python 3.10+ (standard library only) it runs the linter first and again after editing, so remaining findings are either fixed or listed with a reason.

    Yes, through a plain-text personal patterns file: one line per pattern, with a message and a suggestion. The linter checks it on every run, and the agent offers to add a line when you accept the same correction twice. The file is yours and lives in your project or wherever you keep it; the linter reference has example rules.

    For the mechanical parts: US, British or Oxford spelling; decimal comma or point in Spanish; an em-dash ban; a list of banned words; sentence and paragraph limits. These go in a small .prose-lint.json. Venue structure and word limits are outside its scope.

    Yes. The linter reads LaTeX source and skips the preamble, math, citations, references and environments such as tables and code; the agent edits the prose and leaves commands and math untouched.

    New in Writing & Content