More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Journal House Style: Fit Any Venue's Author Guidelines

    1

    Every venue sets these differently, and the rules live on pages that change.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Journal House Style: Fit Any Venue's Author Guidelines

    Journal House Style: Fit Any Venue's Author Guidelines

    Example session with this skill installed

    I'm submitting draft.md to PLOS Computational Biology as a Research Article. Build a venue profile from the journal's current author guidelines, audit my draft against it, and restructure it to fit. Save the profile as venue-profile.md, the audit as venue-audit.md and the revised draft as draft-plos.md.

    • Read your context and instructions
    • Compiled the journal house style

    I've saved the venue profile, the audit and the revised draft. The revised draft passes the audit script with no limit exceeded and nothing missing. It still has 12 placeholders that only you can fill.

    Profile (venue-profile.md). I built it from seven PLOS Computational Biology pages, all read today: the submission guidelines plus the pages on figures, code, data, funding, journal information and LaTeX. The script accepts it as valid.

    Limits: the full title can be up to 200 characters and the short title up to 70. The abstract must not exceed 300 words, with no citations and no headings. A 150–200 word Author Summary is required. There is no limit on length or number of figures.

    • Not stated: reference count, keywords, US vs UK spelling, and how subheadings should be phrased.

    One conflict: the main guidelines say the Data Availability Statement goes in the submission form, but the code-sharing page says it must be in the manuscript. I put it in the manuscript; enter it in the form as well.

    What the audit found in draft.md (details in venue-audit.md):

    Missing: Author Summary, Data Availability Statement, the permits/ethics statement field studies need, title page, short title.

    • Not allowed by PLOS:
      • Code "available on request" from the authors. PLOS doesn't accept this, and refusing to share code can be grounds for rejection.
      • "data not shown" in Results.
      • Funding in the Acknowledgments; it belongs only in the submission form.
    • Fixes made:
      • Cut the abstract from 323 to 294 words and removed its headings and its citation. No number or comparison was removed.
      • Changed "Figure 1" to "Fig 1" throughout.
      • Moved each caption to just after the paragraph that first cites it.
      • Defined "ROC" at first use.
      • Renumbered the references in order of first citation.
      • Added one closing sentence to the Introduction, built only from your existing results.

    For you to do:

    Fill the placeholders: authors and affiliations, corresponding author, permits, model and classifier details, code URL, DOI and licence, data access, software reference [8].

    Make S1 Fig: I replaced "data not shown" with a pointer to it. It needs per-lake results on the left-out lakes; otherwise delete the shallow-lake sentence.

    • Review the Author Summary. I wrote it from your own findings, in first person as PLOS requires.

    Check one phrase: the abstract says BloomCast "transfers across lakes without retraining", but the model is still fitted to each lake.

    Consider cutting the last abstract sentence ("…routine in lake management around the world"). I kept it, but it's the obvious next cut and reviewers may see it as overclaiming from six temperate lakes.

    • Submission form:
      • Funding, including the grant number, which is still missing.
      • Competing interests.
      • Author contributions (CRediT roles).
      • A cover letter.
      • At least four suggested reviewers.
      • A journal section: Evolution, Ecology & Behavior looks closest.

    PLOS updates its guidelines, so recheck the profile if you submit much later.

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

    About this skill

    What it does

    Editors and thesis offices check the shape of a manuscript before anyone reads it: the word limits, the sections they require, the statements they demand, how figures are labelled and where captions go. Every venue sets these differently, and the rules live on pages that change. This skill makes your agent fit your manuscript to the venue you name, from that venue's own current guidelines, or to the requirements you give it.

    • A venue profile built from the venue's own pages. Name a journal, conference, publisher series or thesis office. The agent finds its current author guidelines, using a bundled guide to where about twenty publishers, the major ML, vision and language conferences, LaTeX template galleries and university thesis offices keep them. It fetches the pages and writes a profile for your article type: word and character limits and what the count excludes, display items and references, section order, required sections and statements, heading depth, caption rules, reference style and template.
    • Or your own requirements. A lab style sheet, a department thesis guide, a template or an editor's email becomes the same profile. This route works offline.
    • A source on every rule, nothing from memory. Each rule records the page it came from and the date it was read (or "user-supplied"). What the sources do not say is recorded as "not stated", never filled in with a typical value. When two pages disagree, both are recorded and you are told.
    • An audit you can act on. One table of what is over a limit, missing, forbidden or out of order, each finding citing the rule it breaks, then a prioritised list: missing required content first, then structure, cuts and format.
    • Restructure, cut, recheck. Sections reordered, required statements added, captions relabelled and moved, material moved rather than deleted, then cut to budget and audited again. Anything only you can supply (a DOI, an ethics approval, a grant number) becomes a visible placeholder.

    The audit script

    venue_audit.py (Python 3.10+, standard library, no network) validates the profile and audits a Markdown or LaTeX draft, one file or a folder of section files. It checks every rule it can count: title, abstract and per-section word limits, the main-text limit with the components the venue counts, captions and caption titles, figures, tables and references, heading depth, section order, required statements, forbidden phrases, citations or headings in the abstract, subheading rules, caption label and placement. Every other rule in the profile is listed for the agent to check by reading. In the demo it flagged a 323-word abstract against a 300-word limit, a missing Author Summary and Data Availability Statement, "data not shown", a citation and headings in the abstract, "Figure 1" callouts where the journal uses "Fig 1", and captions in the wrong place.

    What's included

    • SKILL.md: the five-step workflow (profile, audit, restructure, cut, check) and its rules
    • references/where-to-look.md: where house styles live (publishers, conferences, template galleries, thesis offices), each pattern checked, and how to fetch pages that block automated tools
    • references/profile-format.md: the profile format, every key, and the checklist of what to extract
    • references/generic-structure.md: generic research-article heuristics, labelled as such
    • scripts/venue_audit.py and examples/: a profile built from fictional thesis-chapter requirements, a draft and its audit

    Part of the Aurora Lab research pipeline

    Works entirely on its own. With a research/ folder it writes research/venue-profile.md and research/paper/venue-audit.md; without one, it works next to your draft. Pairs well with Aurora Lab's Scientific Voice (how the sentences read) and Claim Check (does each sentence stay inside its evidence?), but needs neither.

    The profile is only as complete as the venue's pages: the agent reads them carefully and records a source for every rule, but a rule buried in a page it did not open can be missed, so check the profile before you submit. Several publisher sites (at the time of checking: Elsevier, Wiley, Cell Press, Springer, Science, PNAS, ACM, ACS, MDPI and others) show bot checks to automated fetches; the agent then asks you to paste the page or save it as PDF. Guidelines change: each rule records the date its page was read. The audit script checks only what can be counted from source text (word and character limits, counts, section order, required statements, listed phrases, caption label and placement, abstract citations and headings, heading depth); page limits, fonts, figure resolution and reference formatting are checked by reading or on your compiled PDF. Its generic research-article checks are keyword heuristics. It reads Markdown and LaTeX; convert a Word file to Markdown (for example with pandoc) or paste its text. It works at the venue level: it does not edit sentence-level style, check claims against data, fill in submission-system forms or prepare figure files. It never adds results or numbers: missing content becomes a placeholder for you to fill.

    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 29 days ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files

    File Scopes

    research/venue-profile.md
    research/paper/**
    research/figures/*.md
    research/refs.bib
    research/claims.md

    Network Access: only to read the target venue's public author-guideline pages (journal, conference, template or thesis-office pages) with the agent's web-fetch tool or curl; nothing is uploaded, and no account or login is used. Not needed when you supply the requirements yourself. Reads the manuscript you point it at (Markdown or LaTeX, a file or a folder; with a research/ folder, research/paper/*), any requirements files you give it, caption drafts in research/figures/*.md, research/refs.bib to count references and research/claims.md so cuts never drop a claim's evidence. Writes the venue profile (research/venue-profile.md, or venue-profile.md next to the draft), the audit report (research/paper/venue-audit.md, or next to the draft) and a revised draft where you ask for one; it edits your files in place only when you ask. The audit script reads files, writes only the report you name, and never uses the network.

    Listed29 days ago

    What's inside

    Frequently Asked Questions

    Any venue that writes down its requirements: journals, conferences, publisher series and thesis or graduate offices, plus your own lab or department rules. It ships a guide to where about twenty publishers, the major ML, vision and language conferences, LaTeX template galleries (Overleaf, CTAN) and university thesis offices keep their author requirements; for anything else the agent searches for the venue's own guidelines page. It ships no venue's rules: it reads the current ones each time.

    They are read from the venue's pages when you run it, and every rule in the profile records the URL and the date it was read. A saved profile is reused with its build date shown, and the agent offers to refresh an old one. Guidelines change, so check the profile's dates before you submit much later.

    It uses its web-fetch tool or curl with a normal browser identity. If the site still serves a bot check or a consent page, it tells you which URL it tried and asks you to paste the page text or save it as PDF. It never fills a value from memory or from another journal of the same publisher.

    Yes. Give it a lab style sheet, a thesis guide, a template or an email, and the profile is built from that, offline, with "user-supplied" as the source. The demo's second run built one from an editor's Short Report invitation and cut the draft to its limits. The skill ships a worked example built from fictional thesis-chapter requirements.

    No. Missing content (a code DOI, an ethics approval, a grant number) becomes a visible placeholder listed for you. Wording that would change a claim is flagged, not rewritten: in the demo it flagged "transfers across lakes without retraining" for a model fitted to each lake. Text it writes from your own draft, such as a required lay or author summary, is marked for your review.

    Yes. The audit script reads LaTeX source as well as Markdown, and the agent edits in the format you wrote in. Page limits cannot be measured from source text, so they are listed as rules for you to check on the compiled PDF.

    Scientific Voice edits sentences. Journal House Style works at the level of the venue: limits, section order, required statements, headings, captions and end matter. They pair well, and neither needs the other.

    New in Writing & Content