Skip to main content
skill CX Codex

consistency-checker — Claude Code skill: what it does, how to install

consistency-checker runs a pre-submission consistency check on finance and accounting manuscripts before journal submission or revision.

no license ★ 240 updated 2026-09-18

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add franklee16/academic-research-skills --skill consistency-checker -a claude-code
Open on GitHub

What consistency-checker does

The skill inspects academic papers across ten distinct categories. It verifies cross-references to tables, charts, equations, and literature citations, flagging cases where textual claims disagree with reported numbers. It also tracks consistent variable definitions, sample sizes, and econometric specifications throughout the draft.

Inputs can include the main manuscript, an online appendix, and a response letter for revision rounds. When multiple files are supplied, the skill matches revision promises in the response letter against actual adjustments in the paper.

Providing LaTeX source files yields the most thorough audit, as extracting references and math environments from raw PDF documents is far less reliable.

What it helps with

  • detect discrepancies between manuscript text and reported table figures
  • validate all in-text cross-references to equations, figures, and references
  • verify that revisions promised in a referee response letter appear in the draft
  • spot undefined variables or shifts in notation across sections

Example prompts for the agent

  • Run a consistency check on main.tex prior to journal submission
  • Audit paper.tex and response_letter.pdf to ensure all requested changes are present
  • Check cross-references and sample size counts in manuscript.tex

How to install consistency-checker

1Skills CLI (Vercel)

npx skills add franklee16/academic-research-skills --skill consistency-checker -a claude-code

2Manually: put the files in place

~/.claude/skills/consistency-checker/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/consistency-checker/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about consistency-checker

How to install consistency-checker in Claude Code?

Run npx skills add franklee16/academic-research-skills --skill consistency-checker -a claude-code in your terminal.

What document formats does this skill accept?

It accepts LaTeX source documents as the preferred format, though PDF files are also supported.

Can it audit revise-and-resubmit packages?

Yes, it inspects response letters alongside the main paper and online appendix to catch unfulfilled revision promises.

Similar skills

All skills for Science and research →

From the same set98

The whole set →
aer-literature aer-literature is a Claude Code skill that maps related economics papers and checks manuscript references. It supports topic selection, introduction drafting, and pre-submission checks. CX Codex +1 ★ 240repo stars math-proof math-proof turns a claim or a rough sketch into a finished proof for a paper: every step justified, signs stated, intermediate algebra written out. CX Codex +1 ★ 240repo stars cancer-discovery Assesses cancer biology and translational oncology manuscripts against Cancer Discovery standards, identifying desk-reject hazards and narrative framing gaps. CX Codex +1 ★ 240repo stars paper-analysis paper-analysis — a skill that walks you through a critical reading of a research paper using the 7-step Cornwell framework. Give it a DOI, a URL, or a local PDF and get a structured appraisal back. CX Codex +1 ★ 240repo stars quality-checks-diagnosis quality-checks-diagnosis helps choose the right survey check and interpret failures. Use it when you need to distinguish inattention from unclear instructions or a weak experimental treatment. CX Codex +1 ★ 240repo stars avoid-leading-questions avoid-leading-questions reviews a draft survey question, names the bias behind it, and gives a concrete rewrite for each of the three cases it covers. CX Codex +1 ★ 240repo stars dril-dataset-construction dril-dataset-construction implements the DRIL methodology to assemble economic datasets from primary sources via AI agents. Ideal for constructing panel data, legal variables, and cited codebooks. CX Codex +1 ★ 240repo stars extract-figures extract-figures pulls figures, charts, diagrams, and images from .docx, converts EMF/WMF assets to PNG, and prepares LaTeX usage notes. CX Codex +1 ★ 240repo stars

Project sponsors

Companies that keep this analytics open