Improve Journal Acceptance logo

Improve Journal Acceptance

Community
GuangyaoYin
improve-journal-acceptance

Review and improve an academic manuscript submission package to increase the chance of journal acceptance or external review. Use when the user asks for pre-submission checks, journal-fit advice, title/abstract/cover-letter polishing, figure-message review, editor/reviewer suggestions, resubmission after rejection, or transfer strategy, especially for Science Advances-style editorial screening.

Overview

PublisherGuangyaoYin
Repositoryskills
Skill nameimprove-journal-acceptance
Stars
64
Forks
2
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by GuangyaoYin on GitHub. Read the source before you install it.

Installation

Install the Improve Journal Acceptance AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/GuangyaoYin/skills/tree/main/skills/improve-journal-acceptance
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/GuangyaoYin/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/improve-journal-acceptance .claude/skills/improve-journal-acceptance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Improve Journal Acceptance in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Improve Journal Acceptance on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Improve Journal Acceptance is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Improve Journal Acceptance

Purpose

Use this skill to help an author make a manuscript easier for editors and reviewers to evaluate favorably. The skill is based on Warren S. Warren's 2022 Science Advances editorial, "Beating the odds for journal acceptance," and is meant for practical pre-submission or resubmission review.

Do not treat this as a promise of acceptance. The goal is to remove avoidable reasons for editorial rejection and make the real scientific contribution visible.

Core Editorial Logic

Assume busy editors form early impressions from:

  • The title.
  • The abstract.
  • The cover letter.
  • The figures and captions.
  • The comparison with the most relevant prior work.
  • The fit between manuscript, journal scope, suggested editors, and suggested reviewers.

Editors at broad journals are curators. They look for work that matters beyond a narrow subfield and is more than incremental. Help the user show that clearly and honestly.

Workflow

  1. Identify the target journal and manuscript type.
  2. Inspect the available package: title, abstract, cover letter, main figures, captions, manuscript text, suggested editors, suggested reviewers, prior reviews, or rejection letters.
  3. Diagnose editorial risk before line editing.
  4. Rewrite or advise only after the core message, novelty, journal fit, and evidence chain are clear.
  5. Return concrete edits, not generic encouragement.

When files are provided, work from the actual files. Do not invent manuscript claims, results, citations, author lists, reviewer names, editor names, or journal policies.

Ten-Point Check

1. Title And Abstract

Check whether the title and abstract are concise, accurate, and not overstated. Remove inflated adjectives and make the essential finding visible.

Ask:

  • What is the one result the reader must remember?
  • Is the claim proportional to the evidence?
  • Can a broad scientific reader understand the abstract without decoding jargon?

2. Duplicate Or Near-Duplicate Resubmission

If this is a resubmission to the same journal, check whether an editor explicitly invited revision or whether there is substantial new data, analysis, or framing.

Require the cover letter to explain the reason for resubmission clearly. Otherwise, flag a high risk of desk rejection.

3. Prior Work Comparison

Check whether the manuscript fairly and prominently compares with the most relevant prior work, including work that could limit the novelty claim.

Do not allow the user to hide key papers in a late paragraph or minimize them vaguely. A strong manuscript should state exactly what prior work did and what this manuscript adds.

4. Cover Letter

Use the cover letter to support the editor's first impression. It should:

  • State the core contribution in plain language.
  • Explain why the work matters to the journal's audience.
  • Place the work in the actual research landscape.
  • Avoid a long list of high-profile but loosely related papers.
  • Avoid generic praise for the journal.

5. Grammar And Clarity

Check the title, abstract opening, figure captions, and cover letter first. Small errors in these places signal weak attention to detail.

For non-native English writing, prioritize clarity and precision over ornate phrasing.

6. Main Message In Figures

Assume editors and reviewers may start with figures and captions. Check whether each main figure communicates a clear piece of the argument.

Flag:

  • Figures placed far from their captions when the format allows embedding.
  • Captions that describe only what is plotted, without the key interpretation.
  • Simulation or calculation results described as if they were experimental observations.
  • Main figures that require reading the full Methods before any message is visible.

7. Associate Editor Suggestions

If the journal allows suggested editors, recommend people who can actually evaluate the work and who match the journal's editor groups.

A poor editor suggestion can make the paper harder to route and may signal poor journal fit. Do not invent editor names; verify against the journal's current editorial board when needed.

8. Reviewer Suggestions

Suggest reviewers who are competent and plausibly unbiased. Avoid close collaborators, recent coworkers, recent coauthors, direct competitors with obvious conflict, or people with severe personal/professional conflicts.

In the cover letter, briefly explain why suggested reviewers are qualified when that helps the editor.

9. After Rejection Elsewhere

If submitting after rejection from another journal:

  • Change the target journal name everywhere.
  • Address prior reviewer comments seriously.
  • Consider disclosing prior reviews when it strengthens the case and the journal allows it.
  • Explain what changed and why the manuscript is now a better fit.

Never imply that ignoring prior reviews is acceptable.

10. Transfer Strategy

If asking for transfer to a sibling journal, check real scope fit. Do not assume journal families form a simple hierarchy.

Recommend transfer only when the receiving journal's audience and article type fit the content.

Output Formats

For a quick review, return:

text
Overall risk: low / medium / high
Main desk-rejection risks:
Top fixes before submission:
Journal-fit judgment:
Specific text edits:

For a full pre-submission audit, return:

text
1. Editorial first impression
2. Title and abstract diagnosis
3. Novelty and prior-work comparison
4. Figure and caption message check
5. Cover letter plan or revision
6. Editor/reviewer suggestion strategy
7. Resubmission or transfer risks
8. Final submission checklist

For manuscript rewriting, preserve the user's scientific claims and mark uncertain claims as questions instead of inventing support.

Good Final Checklist

Before telling the user a package is ready, confirm:

  • The title and abstract state the main finding without exaggeration.
  • The cover letter explains contribution, audience, and fit.
  • The most relevant prior work is compared fairly.
  • Figures and captions reveal the main message.
  • Suggested editors and reviewers are appropriate and not conflicted.
  • Any prior rejection has been addressed honestly.
  • The target journal name is correct in all visible submission materials.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Improve Journal Acceptance AI skill do?

Review and improve an academic manuscript submission package to increase the chance of journal acceptance or external review. Use when the user asks for pre-submission checks, journal-fit advice, title/abstract/cover-letter polishing, figure-message review, editor/reviewer suggestions, resubmission after rejection, or transfer strategy, especially for Science Advances-style editorial screening.

Why use Improve Journal Acceptance on TypingMind?

Because you install it once and use it with any model. Improve Journal Acceptance is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Improve Journal Acceptance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/GuangyaoYin/skills/tree/main/skills/improve-journal-acceptance. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Improve Journal Acceptance?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Improve Journal Acceptance?

As many as you like. As long as a model supports skills, you can use Improve Journal Acceptance with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Improve Journal Acceptance AI skill free?

It is published on GitHub by GuangyaoYin. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇