Audit Citations and References

SkillDev tools

Cross-checks citation keys in index.qmd against references.bib, reporting missing, orphaned, and duplicate entries. Use when verifying citations.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Audit Citations and References skill

What this skill tells your AI

The instructions your AI receives, as published by brycewang-stanford/auto-empirical-research-skills in skills/29-quarcs-lab-project20XXy/dot-claude/skills/bib-check/SKILL.md and read by ahel’s review.

Cross-check all citation keys in the manuscript against references.bib and report mismatches.

Steps

  1. Read index.qmd and extract every citation key:

    • Narrative citations: @key
    • Parenthetical citations: [@key], [@key1; @key2]
    • Ignore email addresses and @sec-, @fig-, @tbl- cross-references
  2. Read references.bib and extract every entry key (the identifier after @article{, @book{, etc.)

  3. Check for duplicate keys within references.bib (same key defined more than once)

  4. Report three categories:

    Errors — cited in manuscript but missing from .bib:

    • List each missing key with the line number in index.qmd where it appears
    • For each, suggest running /project:cite <key> to add the entry

    Orphaned — in .bib but never cited in manuscript:

    • List each unused key (informational, not necessarily a problem)

    Duplicates — same key appears multiple times in .bib:

    • List each duplicate with line numbers in references.bib
  5. Print a summary: total cited keys, total .bib entries, errors, orphaned, duplicates

Error handling

  • If references.bib does not exist, report the error and stop.
  • If index.qmd contains no citations, report "No citations found" and stop.

Signals

GitHub stars
4k
Forks
531
Last commit
Sep 2026
Advanced
Item type
skill
Key
bib-check
Source
github.com/brycewang-stanford/auto-empirical-research-skills