paper-polishing

paper-polishing is a skill for Claude Code from JeanDiable/academic-research-plugin. It costs 103 tokens per session (2,802 once invoked), scanned A, original, MIT.

A constructive review guide for academic papers, written in the style of an ICML meta-review. It examines technical correctness, methods, motivation, presentation, visualizations, and citations, then turns findings into revision advice.

In plain words
What is it for?
Use it to review equations, proofs, notation, methodology, explanations, figures, and references, and to produce a prioritized checklist of revisions.
Why use it?
It helps authors find gaps or unclear parts before submission and gives concrete ways to improve them. It is intended to strengthen a draft rather than simply judge it.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the academic-research plugin — 10 skills shipped together

Good fit Use it to review equations, proofs, notation, methodology, explanations, figures, and references, and to produce a prioritized checklist of revisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeandiable/academic-research-plugin/paper-polishing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add JeanDiable/academic-research-plugin --skill paper-polishing
Clone the repo
git clone --depth 1 https://github.com/JeanDiable/academic-research-plugin

Made for: Claude Code.

Or install academic-research, the plugin that ships this one along with the rest of its 10 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for paper-polishing

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/paper-polishing/github.svg)](https://agentmods.dev/skills/jeandiable/academic-research-plugin/paper-polishing)
Your own site
<a href="https://agentmods.dev/skills/jeandiable/academic-research-plugin/paper-polishing"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/paper-polishing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for paper-polishing

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeandiable/academic-research-plugin/paper-polishing"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/paper-polishing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.02802
Opus 5 $0.00051 $0.01401
Sonnet 5 $0.00021 $0.00560
Haiku 4.5 $0.00010 $0.00280

Measured 12d ago against content hash 5ee6e7463a23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

paper-polishing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/bibtex_utils.py, scripts/paper_search.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/paper-polishing/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper Polishing Skill

Overview

Unlike the paper-reviewing skill (which simulates a formal conference reviewer), this skill acts as a constructive advisor helping the author improve their draft. It provides actionable feedback with specific suggestions for improvement, not just criticism. The goal is to identify gaps in correctness, motivation, methodology, presentation, and citations, then guide the author toward a stronger submission.

Key Differences from Paper Review:

  • Tone: Supportive and solutions-oriented, not evaluative
  • Depth: Focuses on what can be improved, with concrete fix suggestions
  • Scope: Covers technical correctness, clarity, impact, and presentation quality
  • Output: Actionable revision checklist prioritized by severity

Setup

Before running this skill, ensure dependencies are installed:

pip install -r BASE_DIR/scripts/requirements.txt

This installs required libraries for PDF processing, citation retrieval, and analysis.

Workflow

The paper polishing process consists of three main phases: comprehensive reading, multi-angle analysis, and synthesis.

Phase 1: Read Full Paper

Use the Read tool with pagination to process the entire PDF:

  • Break large papers into 20-page chunks (pages 1-20, then 21-40, etc.)
  • As you read, take structured notes on:

Paper Metadata:

  • Paper title and authors
  • Target venue/journal
  • Abstract summary

Technical Elements:

  • List of ALL equations (record equation numbers, variable definitions, notation)
  • List of ALL theorems, lemmas, propositions, corollaries (with full statements and conditions)
  • List of ALL figures with descriptions and captions
  • List of ALL tables with descriptions and captions

Content Tracking:

  • Key claims and their location in the paper
  • Main contributions stated explicitly
  • Notation used throughout (build a complete notation table)
  • Assumptions made (stated and unstated)
  • Baseline methods compared

Phase 2: Multi-Angle Analysis

Read the full file on GitHub · 303 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 303 lines · 103 tokens per session scan A 5ee6e7463a23

Subscribe to this mod's changes

paper-polishing is a skill published in the GitHub repository JeanDiable/academic-research-plugin (23 stars, last pushed 5mo ago), licensed MIT. It adds 103 tokens to every session and 2,802 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens