skills/29-quarcs-lab-project20XXy/dot-claude/skills/bib-check/SKILL.md
Cross-checks citation keys in index.qmd against references.bib, reporting missing, orphaned, and duplicate entries. Use when verifying citations.
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research bib-checkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Cross-check all citation keys in the manuscript against references.bib and report mismatches.
Read index.qmd and extract every citation key:
@key[@key], [@key1; @key2]@sec-, @fig-, @tbl- cross-referencesRead references.bib and extract every entry key (the identifier after @article{, @book{, etc.)
Check for duplicate keys within references.bib (same key defined more than once)
Report three categories:
Errors — cited in manuscript but missing from .bib:
index.qmd where it appears/project:cite <key> to add the entryOrphaned — in .bib but never cited in manuscript:
Duplicates — same key appears multiple times in .bib:
references.bibPrint a summary: total cited keys, total .bib entries, errors, orphaned, duplicates
references.bib does not exist, report the error and stop.index.qmd contains no citations, report "No citations found" and stop.tools
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
tools
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
tools
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
tools
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".