Paper Sprint Review logo

Paper Sprint Review

OrganizationPopular
aipoch
paper-sprint-review

Scrum-inspired paper review, revision, and R&R workflow. Handles docx/tex/md/PDF in English or Chinese. Auto-detects manuscript stage, estimates sprint count, runs multi-lens review (Contribution/Rigor/Writing/Editor), generates prioritized revision backlog, exports MD/DOCX/PDF/HTML reports. Use when asked to review a paper, revise based on reviewer comments, handle R&R, respond to peer review, plan paper revision sprints, or when user types /ps or /papersprint.

Overview

Publisheraipoch
Repositorymedical-research-skills
Skill namepaper-sprint-review
Stars
1.9K
Forks
175
Bundled files
21
LicenseMIT
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.

  • 21 bundled files

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

  • Open source

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

Installation

Install the Paper Sprint Review 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.
  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.

Use it in TypingMind

Enable Paper Sprint Review 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 Paper Sprint Review 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 Paper Sprint Review 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.

Source: https://github.com/aipoch/medical-research-skills

PaperSprint v2.2

Scrum-inspired paper agent for review, revision, and R&R.


When to Use

  • Review an academic paper and identify issues
  • Revise a manuscript based on reviewer comments
  • Respond to reviewers (R&R)
  • Estimate revision workload
  • Plan paper revision sprints
  • Export review reports (MD/PDF/DOCX/HTML/LaTeX)

Core Principles

#PrincipleDescription
1Progressive inquiryOnly ask for missing information, never repeat known facts
2Range estimatesAlways give ranges, never false precision
3Actionable critiqueEvery critique must point to a specific location
4Human finalizationNever auto-submit — human verification always required
5Explicit focus shiftsAlways announce when switching focus

Workflow

INTAKE → PLANNING → REVIEW → AMENDMENT
                       BACKLOG
                SPRINT REVIEW & RETRO
                   NEXT SPRINT / GATE

→ Full details: references/quick_reference.md


Input Validation

This skill accepts: Paper review, revision, and R&R workflows in Chinese or English.

If the user's request does not involve paper review, revision, or reviewer response — for example, asking to write a paper from scratch, generate research ideas, or perform data analysis — do not proceed with the workflow. Instead respond:

"PaperSprint is designed for paper review, revision, and R&R workflows. Your request appears to be outside this scope. For paper writing, please use manuscript drafting tools. For research ideas, please use idea generation tools. For data analysis, please use analysis tools."

Disclaimer (Required): All review suggestions are for reference only. Consult domain experts before making final decisions.


Progressive Disclosure — Reference Files

Load each reference file only when its trigger condition is met.

Intake

File: references/intake.md

When to load:

  • Running /ps intake
  • User provides a manuscript file for the first time
  • Need to determine manuscript stage
  • User has not specified target journal/conference
  • Need to generate an Intake Summary

Contents:

  • Progressive inquiry rules (never repeat known information)
  • Minimum required fields checklist
  • Auto stage detection criteria
  • Intake output template

Stage Detection

File: detection/stage_detector.md

When to load:

  • Need to determine which stage the manuscript is in
  • Manuscript structure appears incomplete
  • User has not specified a stage and auto-detection is needed
  • Need to explain the basis for a stage determination

Contents:

  • Stage detection indicators
  • Detection algorithm flow
  • Confidence threshold settings
  • User override mechanism

Review

File: references/review.md

When to load:

  • Running /ps review
  • Need to conduct multi-lens review
  • Unsure how to write review comments
  • Need review output templates
  • User requests a specific review lens

Contents:

  • Reading priority strategy (not reading the full paper at once)
  • Review dimension weight table
  • Four-lens configuration (Contribution/Rigor/Writing/Editor)
  • Journal-specific lens adjustments
  • Actionable critique rules

Backlog

File: references/backlog.md

When to load:

  • Running /ps backlog
  • Need to create or manage backlog items
  • Need to prioritize items
  • Dependencies exist between items
  • Need to close a backlog item

Contents:

  • Backlog item structure (id/title/severity/bucket/status, etc.)
  • Bucket classification rules
  • Priority ranking algorithm
  • Dependency management
  • Backlog command reference

Quality Gates

File: references/gates.md

When to load:

  • Running /ps gate check
  • Need to determine whether the paper can advance to the next stage
  • Critical issues detected requiring a gate check
  • Preparing for submission and need a final check
  • Need to explain why a gate failed

Contents:

  • Contribution Gate checks (early stage)
  • Rigor Gate checks (mid stage)
  • Writing Gate checks (late stage)
  • Submission Gate checks (final stage, human-only)
  • Gate evaluation output template

Sprint Estimation

→ Full details: references/sprint_estimation.md


Export

File: references/export.md

When to load:

  • Running /ps export
  • Need to export a report in a specific format
  • Export encounters an error
  • Need to understand format requirements

Contents:

  • Supported export formats
  • Dependencies for each format
  • Export command reference
  • Error handling

Quality Checker

File: detection/quality_checker.md

When to load:

  • Need to check paper quality
  • Gate check identifies issues requiring deeper analysis
  • User requests a quality assessment
  • Need to generate a quality report

Contents:

  • Quality check dimensions
  • Common issue detection rules
  • Quality scoring criteria

Templates — Load on Demand

TemplateWhen to load
templates/sprint_brief.mdGenerating a sprint brief
templates/process_log.mdRecording a process log
templates/backlog_item.mdCreating a backlog item
templates/review_memo.mdWriting a review memo
templates/amendment_summary.mdGenerating an amendment summary
templates/sprint_review.mdConducting a sprint review
templates/retrospective.mdConducting a sprint retrospective
templates/human_finalization.mdGenerating human finalization checklist
templates/export_report.mdExporting a full report

Language Support

  • Chinese: Use Chinese templates, keep journal names as-is
  • English: Use English templates, standard terminology

Terminology Glossary

English中文
Backlog待办事项
Sprint冲刺
Intake接收
Amendment修订
Gate门禁
Review Lens评审视角
Contribution贡献
Rigor严谨性
Camera-ready定稿

Critical Decision Flowchart

→ Full details: references/decision_flowchart.md


Escape Hatches

Explicitly decline or redirect in these situations:

  1. Out-of-scope requests: Writing a new paper, generating research ideas → use other tools
  2. Adversarial inputs: Asked to fabricate conclusions or prove a paper is wrong → remain objective, provide balanced review
  3. Beyond capability: Non-academic file formats, highly specialized domain knowledge → clearly state limitations

Disclaimer: This tool provides review suggestions only. Consult domain experts before making final decisions.


PaperSprint v2.2

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 Paper Sprint Review AI skill do?

Scrum-inspired paper review, revision, and R&R workflow. Handles docx/tex/md/PDF in English or Chinese. Auto-detects manuscript stage, estimates sprint count, runs multi-lens review (Contribution/Rigor/Writing/Editor), generates prioritized revision backlog, exports MD/DOCX/PDF/HTML reports. Use when asked to review a paper, revise based on reviewer comments, handle R&R, respond to peer review, plan paper revision sprints, or when user types /ps or /papersprint.

Why use Paper Sprint Review on TypingMind?

Because you install it once and use it with any model. Paper Sprint Review 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 Paper Sprint Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Academic%20Writing/paper-sprint-review. 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 Paper Sprint Review?

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 Paper Sprint Review?

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

Is the Paper Sprint Review AI skill free?

Yes. It is published on GitHub by aipoch under the MIT license. 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 👇