Skills for Real Engineers. Straight from my .agents directory.
02-bib-verify
Agent skill fromagentscope-ai/OpenJudge
Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for accuracy.
How to install 02-bib-verify
npx skills add agentscope-ai/OpenJudge# or add only this skill to Claude Code: copy the folder
skills/academic-eval/02-bib-verify/
# into
~/.claude/skills/02-bib-verify/ (all projects)
.claude/skills/02-bib-verify/ (one project)
1# BibTeX Verification Skill23Check every entry in a `.bib` file against real academic databases using the4OpenJudge `PaperReviewPipeline` in BibTeX-only mode:561. **Parse** — extract all entries from the `.bib` file72. **Lookup** — query CrossRef, arXiv, and DBLP for each reference83. **Match** — compare title, authors, year, and DOI94. **Report** — flag each entry as `verified`, `suspect`, or `not_found`1011## Prerequisites1213```bash14pip install py-openjudge litellm15```1617## Gather from user before running1819| Info | Required? | Notes |20|------|-----------|-------|21| BibTeX file path | Yes | `.bib` file to verify |22| CrossRef email | No | Improves CrossRef API rate limits |2324## Quick start2526```bash27# Verify a standalone .bib file28python -m cookbooks.paper_review --bib_only references.bib2930# With CrossRef email for better rate limits31python -m cookbooks.paper_review --bib_only references.bib --email your@email.com3233# Save report to a custom path34python -m cookbooks.paper_review --bib_only references.bib \35 --email your@email.com --output bib_report.md36```3738## Relevant options3940| Flag | Default | Description |41|------|---------|-------------|42| `--bib_only` | — | Path to `.bib` file (required for standalone verification) |43| `--email` | — | CrossRef mailto — improves rate limits, recommended |44| `--output` | auto | Output `.md` report path |45| `--language` | `en` | Report language: `en` or `zh` |4647## Interpreting results4849Each reference entry is assigned one of three statuses:50…
Excerpt shown under the repository's Apache-2.0 license.
More skills in OpenJudge
Similar skill repositories
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
The open-source app everyone uses to manage agents at work
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
