Citecheck

Community

color4-alt

citecheck

Use when the user asks to "verify citations", "check references", "validate paper citations", or "evaluate reference relevance". It extracts references from LaTeX/PDF papers, checks formatting rules, verifies existence via Crossref / Semantic Scholar / OpenAlex / PubMed / arXiv / dblp / Google Scholar / WebSearch, and scores thematic/semantic relevance.

Overview

Publisher	color4-alt
Repository	`CiteCheck`
Skill name	`citecheck`
Stars	69
Forks	2
Bundled files	6
License	MIT
Links	Skill source Repository

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.
6 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by color4-alt on GitHub. Read the source before you install it.

Installation

Install the Citecheck AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/color4-alt/CiteCheck/tree/main/skills/citecheck
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.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/color4-alt/CiteCheck.git /tmp/CiteCheck
mkdir -p .claude/skills
cp -r /tmp/CiteCheck/skills/citecheck .claude/skills/citecheck

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Citecheck 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 Citecheck 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 Citecheck 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.

CiteCheck — Paper Citation Verification

Overview

CiteCheck verifies academic paper citations by combining structured parsing with agent-native LLM evaluation. It supports LaTeX source files (preferred) and PDF fallback.

Workflow

Parse paper: Call citecheck CLI to read LaTeX (preferred) or PDF, extract references and body text
Format check: Call citecheck CLI to validate bibliography entries
Queryability verification: Call citecheck CLI to verify existence via Crossref / Semantic Scholar
Evaluate thematic relevance: Evaluate directly using the agent's reasoning capabilities — compare cited paper title/abstract/venue against the citing paper
Evaluate semantic accuracy: Evaluate directly using the agent's reasoning capabilities — compare in-text citation context against cited source content
Generate report: Aggregate all results into a Markdown report

Why matching steps are not done by the CLI The citecheck CLI can run standalone with optional --api-key for external LLM-powered matching. When used as a Skill, the host agent itself possesses LLM reasoning capabilities. Direct evaluation is faster, more consistent, and requires no additional API keys from the user.

1. Parse Paper (CLI)

LaTeX source (preferred)

bash
citecheck path/to/latex_project/ --skip-verification --skip-semantic -o parsed_report.md

Or parse a single file:

bash
citecheck main.tex --skip-verification --skip-semantic -o parsed_report.md

PDF (fallback)

bash
citecheck paper.pdf --skip-verification --skip-semantic -o parsed_report.md

--skip-verification and --skip-semantic are required in Skill mode because steps 3–5 are performed directly by the agent.

2. Format Check (CLI)

Call citecheck to check and report format issues:

Check item	Description
Required fields	Author, title, year, venue completeness
Format consistency	Punctuation, capitalization, abbreviation uniformity
DOI/URL	If present, whether format is correct and accessible
Year sanity	No `202x` placeholders, not in the future

Detailed rules: see ./references/format-check-rules.md.

3. Queryability Verification (CLI + Agent Supplement)

Call citecheck to query Crossref and Semantic Scholar public APIs for citation existence.

API details: see ./references/api-reference.md.

If the CLI fails due to network/SSL issues, use WebSearch to directly query suspicious citations (especially those marked "unverifiable"), supplementing the verification results.

4. Evaluate Thematic Relevance (Agent Direct)

Do not call the CLI or any external API. Evaluate directly using the agent's reasoning capabilities.

For each reference, extract:

Citing paper: title, abstract, keywords
Cited paper: title, abstract (from API results or WebSearch), venue

Evaluation prompt template: see ./references/thematic-scoring-prompt.md.

5. Evaluate Semantic Accuracy (Agent Direct)

Do not call the CLI or any external API. Evaluate directly using the agent's reasoning capabilities.

For each in-text citation position:

Extract 1–2 sentences before and after the citation marker as citing_text
Obtain the cited paper's abstract via Semantic Scholar or WebSearch as cited_text
Evaluate semantic consistency using the prompt template: see ./references/semantic-matching-prompt.md.

6. Output Report

Generate a Markdown report containing:

Summary

Total references
Format issues count
Query failures / suspicious count
Average thematic relevance score
Average semantic accuracy score

Detailed Results Table

No.	Title	Format	Queryable	Thematic	Semantic	Notes
1	...	✅/⚠️/❌	✅/❌	0.85	0.90	DOI mismatch

Issue Summary

List all findings and recommendations by severity

Dependencies

bash
pip install CiteCheck

For PDF support:

bash
pip install CiteCheck[pdf]

Notes

No --api-key is required in Skill mode. Thematic and semantic matching are performed directly by the agent, with no external LLM API calls.
Prioritize LaTeX source files; parsing accuracy is far higher than PDF.
Add delays and retries to API calls to avoid rate limiting.
When Semantic Scholar abstracts are missing, fall back to Crossref + title keywords.
Semantic matching requires the cited paper's abstract; mark "source unreachable" when unavailable.
If placeholder citations like =? or [?, ?] are found, mark them as "unverifiable references".

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 Citecheck AI skill do?

Why use Citecheck on TypingMind?

Because you install it once and use it with any model. Citecheck 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 Citecheck in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/color4-alt/CiteCheck/tree/main/skills/citecheck. 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 Citecheck?

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 Citecheck?

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

Is the Citecheck AI skill free?

Yes. It is published on GitHub by color4-alt 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

Tavily

openclaw

OrganizationPopular

Tavily web search, content extraction, and research tools.

Deep Research

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

Exa Search

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search…

Wayfinder

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

CiteCheck — Paper Citation Verification

Overview

Workflow

1. Parse Paper (CLI)

LaTeX source (preferred)

PDF (fallback)

2. Format Check (CLI)

3. Queryability Verification (CLI + Agent Supplement)

4. Evaluate Thematic Relevance (Agent Direct)

5. Evaluate Semantic Accuracy (Agent Direct)

6. Output Report

Summary

Detailed Results Table

Issue Summary

Dependencies

Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now