Agent skill

Citation Verification Guide

by LigphiDonk in LigphiDonk/Oh-my--paper

Lays out principles for catching fake, mismatched, or inconsistently formatted citations in academic writing, checked through live web search.

MITAuto-check passedResearch & Science

Install Citation Verification Guide

skills CLI
$ npx skills add LigphiDonk/Oh-my--paper --skill inno-reference-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LigphiDonk/Oh-my--paper inno-reference-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LigphiDonk/Oh-my--paper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/inno-reference-audit .claude/skills/inno-reference-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
inno-reference-audit
GitHub stars
738
Token cost
~2.2k tokens
SKILL.md length
912 words
Files
9 (incl. scripts, references)
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Lays out principles for catching fake, mismatched, or inconsistently formatted citations in academic writing, checked through live web search.

  • Works in 4 steps: Proactive Verification (Verify During… → Google Scholar Verification → Information Matching Verification → …
  • Verifying citations in a paper draft before submission
  • SKILL.md covers Canonical Summary, Trigger Rules, Resource Use Rules and Execution Contract, plus 7 more sections
  • Runs Python scripts from its folder

What it does

This skill is a reference guide rather than a fully automated tool: it sets out the idea of checking every citation proactively while writing, using web search and Google Scholar, instead of reviewing a finished paper afterward. It names the specific problems this guards against — references to papers that don't exist, mismatched authors or years, inconsistent formatting, and work that's referenced but never actually cited.

It treats AI-generated citations as a particular risk worth extra caution, which is part of why every citation needs independent checking rather than being trusted on sight. Supporting scripts and reference files cover verification rules, common mistakes, and API usage for automating part of the check, used only when their dependencies are available, with a manual fallback explained whenever a script can't run.

When your agent uses it

  • Verifying citations in a paper draft before submission
  • Checking whether an AI-assisted draft's references actually exist
  • Reviewing a bibliography for consistent citation formatting

Example prompts

  • “Verify every citation in this draft against Google Scholar.”
  • “Check if any of these references look fabricated or mismatched.”
  • “Review this bibliography for inconsistent citation formatting.”

Requirements

  • Web search access for citation verification
  • Python for the optional verification scripts

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Proactive Verification (Verify During Writing)
  2. Google Scholar Verification
  3. Information Matching Verification
  4. Claim Verification

What it can do on your machine

Read from SKILL.md and the folder at commit 6baece9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Citation Verification Guide loads about 2.2k tokens when it runs, and up to ~9.5k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 912 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LigphiDonk/Oh-my--paper at commit 6baece9, republished under its MIT licence (© LigphiDonk). 912 words, ~2,248 tokens.

Download SKILL.mdSave it as .claude/skills/inno-reference-audit/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
inno-reference-audit
description
This skill provides reference guidance for citation verification in academic writing.
id
inno-reference-audit
version
0.1.0
stages
publication
tools
read_file, search_project, write_file, run_terminal
summary
This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices"…
primaryIntent
evaluation
intents
evaluation, writing
capabilities
evaluation-benchmarking, search-retrieval
domains
general
keywords
research, academic, citation, reference, inno-reference-audit, paper review, evaluation-benchmarking, search-retrieval, inno, audit, this, provides

inno-reference-audit

Canonical Summary

This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citati...

Trigger Rules

Use this skill when the user request matches its research workflow scope. Prefer the bundled resources instead of recreating templates or reference material. Keep outputs traceable to project files, citations, scripts, or upstream evidence.

Resource Use Rules

  • Read from references/ only when the current task needs the extra detail.
  • Treat scripts/ as optional helpers. Run them only when their dependencies are available, keep outputs in the project workspace, and explain a manual fallback if execution is blocked.

Execution Contract

  • Resolve every relative path from this skill directory first.
  • Prefer inspection before mutation when invoking bundled scripts.
  • If a required runtime, CLI, credential, or API is unavailable, explain the blocker and continue with the best manual fallback instead of silently skipping the step.
  • Do not write generated artifacts back into the skill directory; save them inside the active project workspace.

Upstream Instructions

Citation Verification Reference Guide

A reference guide for citation verification in academic paper writing, providing verification principles and best practices.

Core Principle: Proactively verify every citation during the writing process using WebSearch and Google Scholar.

Core Problems

Citation issues in academic papers seriously impact research integrity:

  1. Fake citations - Citing non-existent papers (common issue with AI-generated citations)
  2. Incorrect information - Mismatched authors, titles, years, etc.
  3. Inconsistent formatting - Mixed citation formats
  4. Missing citations - Referenced but uncited work

These issues can lead to:

  • Paper rejection or retraction
  • Damage to academic reputation
  • Reviewers questioning research rigor

Special risk with AI-assisted writing: AI-generated citations have approximately 40% error rate; every citation must be verified via WebSearch.

Verification Principles

This skill provides verification principles based on WebSearch and Google Scholar:

1. Proactive Verification (Verify During Writing)

Core idea: Verify immediately when adding a citation, rather than checking after writing is complete.

  • Search for the paper via WebSearch each time a citation is needed
  • Confirm the paper exists on Google Scholar
  • Add to bibliography only after verification passes
2. Google Scholar Verification

Why Google Scholar:

  • Most comprehensive academic literature coverage
  • Provides citation count (credibility indicator)
  • Directly provides BibTeX format
  • Free and no API required

Verification steps:

  1. WebSearch query: "site:scholar.google.com [paper title] [first author]"
  2. Confirm the paper appears in results
  3. Check citation count (abnormally low counts may indicate issues)
  4. Click "Cite" to get BibTeX
3. Information Matching Verification

Information that must match:

  • Title (minor differences allowed, e.g., capitalization)
  • Authors (at least the first author must match)
  • Year (±1 year difference allowed, considering preprints)
  • Publication venue (conference/journal name)
4. Claim Verification

Key principle: When citing a specific claim, you must confirm the claim actually appears in the paper.

  • Use WebSearch to access the paper PDF
  • Search for relevant keywords
  • Confirm the accuracy of the claim
  • Record the section/page where the claim appears

Verification Workflow

Integration into Writing Process
Need a citation during writing
    ↓
WebSearch to find the paper
    ↓
Google Scholar to verify existence
    ↓
Confirm paper details
    ↓
Get BibTeX
    ↓
(If citing a specific claim) Verify the claim
    ↓
Add to bibliography

Key point: Verification is part of the writing process, not a separate post-processing step.

Usage Guide

Using with ml-paper-writing

The verification principles of this skill are integrated into the Citation Workflow of the ml-paper-writing skill.

Auto-trigger: Citation verification is automatically executed when writing papers with the ml-paper-writing skill.

Manual reference: Refer to this skill when you need detailed verification principles.

Show full SKILL.md (357 more words)Show less
Verification Step Example

Scenario: Need to cite the Transformer paper

Step 1: WebSearch lookup
Query: "Attention is All You Need Vaswani 2017"
Result: Found multiple sources for the paper

Step 2: Google Scholar verification
Query: "site:scholar.google.com Attention is All You Need Vaswani"
Result: ✅ Paper exists, 50,000+ citations, NeurIPS 2017

Step 3: Confirm details
- Title: "Attention is All You Need"
- Authors: Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; ...
- Year: 2017
- Venue: NeurIPS (NIPS)

Step 4: Get BibTeX
- Click "Cite" on Google Scholar
- Select BibTeX format
- Copy BibTeX entry

Step 5: Add to bibliography
- Paste into .bib file
- Use \cite{vaswani2017attention} in the paper
Handling Verification Failures

If the paper cannot be found on Google Scholar:

  1. Check spelling - Is the title or author name correct?
  2. Try different queries - Use different keyword combinations
  3. Find alternative sources - Try arXiv, DOI
  4. Mark as pending - Use [CITATION NEEDED] marker
  5. Notify the user - Clearly state the citation cannot be verified

If information doesn't match:

  1. Confirm the source - Did you find the correct paper?
  2. Check versions - Preprint vs. published version
  3. Update information - Use the most accurate version
  4. Record discrepancies - Note the reason for differences

Best Practices

Preventing Fake Citations
  1. Never generate citations from memory - AI-generated citations have 40% error rate
  2. Use WebSearch to find - Verify every citation through WebSearch
  3. Confirm on Google Scholar - Verify paper existence on Google Scholar
  4. Verify promptly - Verify when adding citations, don't wait until finished
Handling Verification Failures
  1. Don't guess - If you can't find the paper, don't fabricate information
  2. Mark clearly - Use [CITATION NEEDED] to mark explicitly
  3. Notify the user - Clearly state which citations cannot be verified
  4. Provide reasons - Explain why verification failed (not found, info mismatch, etc.)
Improving Verification Accuracy
  1. Complete queries - Include title, author, year
  2. Check citation count - Citation count on Google Scholar is a credibility indicator
  3. Confirm venue - Verify conference/journal name is correct
  4. Verify claims - When citing specific claims, confirm they exist in the paper
Common Pitfalls

❌ Wrong approach:

  • Generating BibTeX from memory
  • Skipping Google Scholar verification
  • Assuming a paper exists
  • Not marking unverifiable citations

✅ Correct approach:

  • Search every citation with WebSearch
  • Confirm on Google Scholar
  • Copy BibTeX from Google Scholar
  • Clearly mark unverifiable citations

Summary

Core Principle: Proactively verify every citation during the writing process using WebSearch and Google Scholar.

Key Steps:

  1. WebSearch to find the paper
  2. Google Scholar to verify existence
  3. Confirm details
  4. Get BibTeX
  5. Verify claims (if needed)
  6. Add to bibliography

Failure handling: When verification fails, mark as [CITATION NEEDED] and clearly notify the user.

Integration: The principles of this skill are integrated into the ml-paper-writing skill for automatic verification.

© LigphiDonk, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in skills/inno-reference-audit of LigphiDonk/Oh-my--paper.

  • SKILL.md
  • references/README.md
  • references/api-usage.md
  • references/common-errors.md
  • references/verification-rules.md
  • scripts/README.md
  • scripts/api-clients.py
  • scripts/format-checker.py
  • scripts/verify-citations.py

Open the folder on GitHubat commit 6baece9

Compare with similar skills

Citation Verification Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Citation Verification Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Citation Verification Guide this skillLigphiDonk/Oh-my--paper738—~2.2kAutomated safety check: PassMIT
Citation Verification GuideGalaxy-Dawn/claude-scholar5.7k2 repos~1.9kAutomated safety check: PassMIT
Article Fact Checkerdigoal/blog8.6k—~939Automated safety check: PassGPL-2.0
Citation VerificationLight0305/Light-skills640—~3.4kAutomated safety check: PassMIT
Grounded CitationsNousResearch/hermes-agent252k—~3.1kAutomated safety check: PassMIT
Reference VerifierYuan1z0825/nature-skills47k2 repos~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Citation Verification Guide

    Galaxy-Dawn/claude-scholar

    Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.

    5.7k GitHub starsUsed in 2 repos~1.9k tokens
    Research & ScienceAuto-check passed
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated today
    Research & ScienceAuto-check passed
  • Citation Verification

    Light0305/Light-skills

    Verifies that every reference in a manuscript is real, correctly identified and actually supports its claim, and produces a citation registry for typesetting.

    640 GitHub stars~3.4k tokensUpdated 3 mo ago
    Research & ScienceAuto-check passed
  • Grounded Citations

    NousResearch/hermes-agent

    Attaches a numbered, URL-backed citation to every outside fact in an answer or document, rejecting quotes that aren't real.

    252k GitHub stars~3.1k tokensUpdated today
    Research & ScienceAuto-check passed
  • Reference Verifier

    Yuan1z0825/nature-skills

    Cross-checks each academic reference against several sources field by field, flags conflicts such as year, DOI, author order and page errors, and outputs a structured report.

    47k GitHub starsUsed in 2 repos~1.4k tokens
    Research & ScienceAuto-check passed
  • Research

    zhongkaifu/TensorSharp

    A skill your agent uses for web searches and current information lookups, finding sources, fact-checking, researching questions, comparing sources, or summarising web pages.

    559 GitHub stars~2.3k tokensUpdated today
    Research & ScienceAuto-check: warnings

More from LigphiDonk/Oh-my--paper

All 27 skills in this repo
  • Preprint Search on bioRxiv

    LigphiDonk/Oh-my--paper

    Searches bioRxiv life sciences preprints by keyword, author, date range or category with a Python script, returning JSON metadata and optional PDF downloads.

    738 GitHub starsUsed in 12 repos~3.7k tokens
    Auto-check passed
  • Literature PDF OCR Library Builder

    LigphiDonk/Oh-my--paper

    Searches and downloads legally accessible academic PDFs, OCRs them to Markdown, and organizes the results into a traceable, AI-readable literature library.

    738 GitHub stars~1.1k tokensUpdated 5 mo ago
    Auto-check passed
  • Inno Code Survey

    LigphiDonk/Oh-my--paper

    Finds and clones missing code repositories for a chosen research idea, then writes a survey that maps academic concepts to their implementations.

    738 GitHub stars~3.6k tokensUpdated 5 mo ago
    Auto-check passed
  • Turns experimental data such as CSV, JSON or TensorBoard logs into statistical significance tests, visualizations and a drafted Results section.

    738 GitHub stars~3k tokensUpdated 5 mo ago
    Auto-check passed
  • Single-Cell Initial Analysis

    LigphiDonk/Oh-my--paper

    Runs a seven-step quality-control and exploration pipeline on scRNA-seq, CyTOF or flow cytometry data and writes a plain-language report of what it found.

    738 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Making Academic Presentations

    LigphiDonk/Oh-my--paper

    Create academic presentation slide decks and optionally demo videos from research papers.

    738 GitHub stars~2k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Citation Verification Guide

What does Citation Verification Guide do?

Lays out principles for catching fake, mismatched, or inconsistently formatted citations in academic writing, checked through live web search. This skill is a reference guide rather than a fully automated tool: it sets out the idea of checking every citation proactively while writing, using web search and Google Scholar, instead of reviewing a finished paper afterward. It names the specific problems this guards against — references to papers that don't exist, mismatched authors or years, inconsistent formatting, and work that's referenced but never actually cited.

When should I use Citation Verification Guide?

Citation Verification Guide fits situations like: verifying citations in a paper draft before submission; checking whether an AI-assisted draft's references actually exist; reviewing a bibliography for consistent citation formatting.

How do I install Citation Verification Guide in Claude Code?

Run `npx skills add LigphiDonk/Oh-my--paper --skill inno-reference-audit -a claude-code`. Or copy the skill folder (skills/inno-reference-audit in LigphiDonk/Oh-my--paper) into .claude/skills/inno-reference-audit in your project. Claude Code loads it when a task matches its description.

How do I install Citation Verification Guide in Codex?

Run `npx skills add LigphiDonk/Oh-my--paper --skill inno-reference-audit -a codex`. Or copy the skill folder (skills/inno-reference-audit in LigphiDonk/Oh-my--paper) into .agents/skills/inno-reference-audit in your project. Codex loads it when a task matches its description.

Can I use Citation Verification Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LigphiDonk/Oh-my--paper --skill inno-reference-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/inno-reference-audit, .gemini/skills/inno-reference-audit, .github/skills/inno-reference-audit and .opencode/skills/inno-reference-audit in your project.

What does Citation Verification Guide need to run?

Going by SKILL.md and its folder, Citation Verification Guide needs Python for the scripts in its folder. Our summary lists: Web search access for citation verification; Python for the optional verification scripts.

Does Citation Verification Guide access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Citation Verification Guide safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Citation Verification Guide use?

Citation Verification Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Citation Verification Guide use?

About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.2k tokens, read only when the agent opens those files.

What are the alternatives to Citation Verification Guide?

Skills that share tags, products or a category with Citation Verification Guide: Citation Verification Guide (Galaxy-Dawn/claude-scholar, 5.7k stars), Article Fact Checker (digoal/blog, 8.6k stars), Citation Verification (Light0305/Light-skills, 640 stars) and Grounded Citations (NousResearch/hermes-agent, 252k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Citation Verification Guide?

LigphiDonk (a GitHub user) maintains it in LigphiDonk/Oh-my--paper, which has 738 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on April 15, 2026.

Source: LigphiDonk/Oh-my--paper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.