paper-polish

eyh0602/skillshub · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/eyh0602/skillshub --skill paper-polish
0 commentsdiscussion
summary

Section titles should have consistent capitalization.

skill.md

Polishing and reviewing research papers in LaTeX

On writing

Contents

  • Your paper should be easily comprehensible by its reviewers. They are far less familiar with your work than you. They may not be an expert on the topic and may not be able to afford much time on your paper.
  • The introduction should convey curiosity or excitement (new problem, new solution, improved solution, impressive results, or high impact), the design novelty, substantiality, and correctness, and the evaluation relevancy and comprehensiveness.
  • Conciseness: Remove every word that contributes no meaning, such as kind of.
  • Use proper tenses:

Grammar

  • Section titles should have consistent capitalization.

    • Title Case: Capitalize the first and last words and all major words in between.
      • Good: Introduction to Fuzzing with LLMs
    • Sentence case: Capitalize only the first word and proper nouns.
      • Good: Introduction to fuzzing with LLMs
    • Choose one style and be consistent throughout the paper.
  • Avoid passive voice unless strongly justifiable. Passive voice is ambiguous because it has no subject unless followed by "by...".

    • Bad: LLM was applied to fuzzing. (Who applied it? The authors or someone else?)
    • Good: We applied LLM to fuzzing.
  • Avoid nominalization.

    • Bad: He made a proposal to use Rust.
    • Good: He proposed to use Rust.
  • Avoid "There is/are".

    • Bad: There are many developers of Rust.
    • Good: Many developers use Rust.
    • Good: Rust has many developers.
  • "Which" vs "that": Use "which" in a nonrestrictive clause and "that" in a restrictive clause. More...

    • Wrong: Rust that is safe is popular. (This is wrong because there is only one Rust.)
    • Right: Rust, which is safe, is popular.
  • Distinguish coordinating conjunction vs conjunctive adverbs.

    • Wrong: C is dangerous, Rust is safe. (Cannot join two sentences by a comma)
    • Right: C is dangerous, but Rust is safe.
    • Wrong: C is dangerous, however Rust is safe.
    • Right: C is dangerous; however, Rust is safe.
  • "Fewer" modifies countable nouns whereas "less" uncountable nouns.

    • Wrong: ten items or less
    • Right: ten items or fewer
    • Wrong: fewer feedback
    • Right: less feedback
  • Use articles (a, an, the) properly.

    • A singular countable noun must be preceded by an article.

      • Wrong: I wrote Rust program.
      • Right: I wrote a Rust program.
      • Right: I wrote Rust programs.
    • The must have a reference that is unique either by fact or in the context.

      • Right: the first Rust programmer (unique by fact)
      • Right: Our team has a Rust and a C++ programmer. The Rust programmer produces the fastest, most robust code. (unique in the context)
      • Wrong: Our team has two Rust and two C++ programmers. The Rust programmer is more productive than the C++ programmer.
  • Distinguish between compare with and compare to

    • Right: Rust is safer compared with C.
    • Right: Some people compare Rust to a panacea for memory safety problems.

On LaTeX

  • Use modern implementations of LaTeX to take advantage of Unicode and other useful features.

    • Use LuaLaTeX instead of LaTeX or pdfLaTeX
    • Use BibLaTeX for acmart and ieeetrans templates instead of BibTex
  • Use correct typefaces. Particularly, italics should be used for variables but not for descriptive terms. More...

    • Wrong: $t_{max}$
    • Right: $t_\text{max}$
  • Do not manually add separators in large numbers. \usepackage{siunitx}. Then, wrap large numbers in \num{}.

    • Bad: 12,345
    • Good: \num{12345}
  • Do not manually type reference names, such as Table, Figure, Theorem. Instead, \usepackage{hyperref}, and then \autoref{fig:xxx}, \autoref{sec:xxx}, \autoref{table:xxx}.

    • Not recommended: In Figure~\ref{fig:overview}
    • Good: In \autoref{fig:overview}

Structure

  • main.tex is the entry root of the LaTeX project, containing the usepackage commands and the document structure.
  • src/ contains all the sections.
  • tables/ contains all the tables.
  • figures/ or fig/ contains the figures. Figures are PDF files or .tex files. .tex in figures are algorithms.
  • code/ contains code listings used in the text.
how to use paper-polish

How to use paper-polish on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add paper-polish
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/eyh0602/skillshub --skill paper-polish

The skills CLI fetches paper-polish from GitHub repository eyh0602/skillshub and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/paper-polish

Reload or restart Cursor to activate paper-polish. Access the skill through slash commands (e.g., /paper-polish) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.466 reviews
  • Yusuf Flores· Dec 24, 2024

    I recommend paper-polish for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Valentina Haddad· Dec 16, 2024

    Useful defaults in paper-polish — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Pratham Ware· Dec 12, 2024

    Useful defaults in paper-polish — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Hiroshi Mehta· Dec 12, 2024

    paper-polish is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Isabella Sanchez· Dec 8, 2024

    Useful defaults in paper-polish — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Zara Wang· Dec 4, 2024

    Keeps context tight: paper-polish is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Sakura Iyer· Nov 27, 2024

    paper-polish is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Fatima Wang· Nov 23, 2024

    I recommend paper-polish for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Fatima Li· Nov 15, 2024

    Keeps context tight: paper-polish is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Olivia Ghosh· Nov 7, 2024

    paper-polish is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

showing 1-10 of 66

1 / 7