Validate Bib

Documents

validate-bib

Validate Bib is an Agent Skill for documents published in the brycewang-stanford/Auto-Empirical-Research-Skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Validate bibliography entries against citations in manuscript and Quarto book files. Find missing entries, unused references, potential typos, and quality issues. This skill should be used when asked to "check the bibliography", "validate citations", or "validate-bib".

View on GitHub ↗

QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

Open your project in Codex.
Copy and paste the prompt below.
Review files and risks before approving any action.

Prompt to paste

Inspect the Agent Skill at https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/HEAD/skills/41-sticerd-eee-sewage-econometrics-check/skills/validate-bib/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/validate-bib, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Validate Bibliography

Cross-reference all citations in manuscript and book files against bibliography entries.

Workflow

Step 1: Read the bibliography

Read docs/overleaf/refs.bib and extract all citation keys.

Step 2: Scan all files for citation keys

.tex files in docs/overleaf/: look for \textcite{, \parencite{, \cite{, \citet{, \citep{, \citeauthor{, \citeyear{}
.qmd files in book/: look for @key, [@key], [@key1; @key2]
Extract all unique citation keys used

Step 3: Cross-reference

Missing entries (CRITICAL): Citations used in files but NOT in refs.bib
Unused entries (informational): Entries in refs.bib not cited anywhere
Potential typos: Similar-but-not-matching keys (Levenshtein distance)

Step 4: Check entry quality

For each bib entry:

Required fields present (author, title, year, journal/booktitle)
Author field properly formatted (Last, First and Last, First)
Year is reasonable (1900-2026)
No malformed characters or encoding issues
Entry type appropriate (@article, @incollection, @techreport, etc.)

Step 5: Report findings

## Bibliography Validation Report
**Date:** YYYY-MM-DD
**Bibliography:** docs/overleaf/refs.bib
**Total entries:** N
**Files scanned:** N .tex + N .qmd

### Missing Entries (CRITICAL)
| Citation Key | Used In | Line |
|-------------|---------|------|
| ... | ... | ... |

### Unused Entries
| Citation Key | Entry Type |
|-------------|------------|
| ... | ... |

### Potential Typos
| Used Key | Similar Bib Key | File |
|----------|----------------|------|
| ... | ... | ... |

### Quality Issues
| Citation Key | Issue |
|-------------|-------|
| ... | Missing journal field |

Files to scan

docs/overleaf/*.tex
book/*.qmd

Bibliography location

docs/overleaf/refs.bib