Skip to main content
affpapa.org
RU EN
skill CX Codex

citation-management · lingzhi227 — Claude Code skill: BibTeX citations

A skill that keeps citations in a LaTeX paper in order: harvests missing references via Semantic Scholar, validates cite keys against .bib, and formats the bibliography.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add lingzhi227/agent-research-skills --skill citation-management -a claude-code
Open on GitHub

What citation-management does

The skill covers the whole citation lifecycle in a LaTeX paper. It scans the .tex draft, spots claims without citations, searches Semantic Scholar, and appends entries to .bib. Keys follow firstAuthorLastNameYearFirstContentWord, so you get something like vaswani2017attention.

Four actions are available: harvest, validate, add, format. Harvesting runs in rounds, up to 20, until the gaps close. Validation reports unresolved cite keys, unused entries, duplicate keys and sections, undefined references, and missing figures. Searching needs a Semantic Scholar key, passed with --api-key.

There is a --dry-run flag for previewing and a --fix flag that writes references_fixed.bib with placeholders for missing keys. Nothing gets invented: only entries returned by the API are added, and an existing citation is never duplicated. Worth running before you compile, not after.

What it helps with

  • find missing citations in a draft
  • check that every \cite key resolves in .bib
  • strip duplicate entries and keys
  • sort and tidy .bib before compilation
  • add one specific paper by title

Example prompts for the agent

  • Validate the citations in paper/main.tex against paper/references.bib and list what's missing
  • Harvest missing citations for paper/main.tex, start with --dry-run
  • Add the attention is all you need paper to .bib and clean up the key

How to install citation-management

1Skills CLI (Vercel)

npx skills add lingzhi227/agent-research-skills --skill citation-management -a claude-code

2Manually: put the files in place

~/.claude/skills/citation-management/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/citation-management/

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

Questions about citation-management

How do I install citation-management in Claude?

Run npx skills add lingzhi227/agent-research-skills --skill citation-management -a claude-code. The skill lands at ~/.claude/skills/citation-management/SKILL.md.

What does citation-management do?

It harvests missing citations from a .tex draft via Semantic Scholar, validates cite keys against .bib, deduplicates entries, and formats the bibliography.

What do I need for the paper search?

A Semantic Scholar API key, passed to the script with --api-key. Without it the search for new entries will not run.

Similar skills

Everything for Science and research →

citation-management by other authors comes first.

citation-management K-Dense-AI Searches OpenAlex, PubMed, and Google Scholar, extracts publication metadata, and builds valid BibTeX references. Helpful when preparing bibliographies for academic manuscripts. CX Codex +1 2,200installs citation-audit wanshuiyin Checks each reference in a paper against real sources: does the work exist, are authors, year and venue right, does the citation fit the claim. CX Codex +1 483installs citation-verification Galaxy-Dawn A skill that sets rules for verifying citations in academic writing, so you don't ship invented or mismatched references. CX Codex +1 1,400installs literature-review collaborative-deep-research Runs a systematic literature review on an academic topic: searches papers, triages results, reads key works and writes a themed report. CX Codex +1 732installs lit-review pedrohcgs Runs a structured literature search and synthesis: key papers, thematic clusters, gaps, and BibTeX-ready citations. Useful before writing a paper or a grant proposal. CX Codex +1 ★ 1,668repo stars semanticscholar-skill Agents365-ai Searches academic papers, authors, and citation graphs using the Semantic Scholar API. Helps agents explore scientific literature, gather references, and get recommendations. CX Codex +1 3,400installs paper-write wanshuiyin This skill drafts a LaTeX paper section by section from an outline. Useful when the plan is ready and you need the actual prose. CX Codex +1 539installs

From the same set23

literature-search Find academic papers from several research indexes and prepare bibliography data. Use it when you need related work, source lists, or recent preprints. CX Codex +1 2,600installs figure-generation Builds publication-ready scientific plots through query expansion, code execution, and visual verification. Helps researchers format charts for papers. CX Codex +1 2,300installs math-reasoning Derives equations, writes proofs, formalizes research problems, and produces publication-ready LaTeX markup for research papers. CX Codex +1 2,200installs latex-formatting Sets up conference LaTeX templates, fixes formatting, and runs a pre-submission check. Handy when the deadline is close. CX Codex +1 2,200installs backward-traceability Connects every numeric value in a research PDF directly to the source code line that produced it. Helps verify data reproducibility across LaTeX documents. CX Codex +1 2,100installs deep-research Runs a systematic academic literature review on a topic: finds papers, reads them, builds a database and writes a final report. Useful when you need the state of a field, not a few search hits. CX Codex +1 1,900installs research-planning Turns a topic or idea into a structured research plan: methodology, paper sections, dependency-ordered tasks and diagrams. CX Codex +1 1,800installs github-research Finds open-source repositories matching research topics, inspects their codebases, and produces an integration blueprint. Useful when tracking down implementations of algorithms. CX Codex +1 1,800installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor