Skills for Real Engineers. Straight from my .agents directory.
01-paper-review
Agent skill fromagentscope-ai/OpenJudge
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.
How to install 01-paper-review
npx skills add agentscope-ai/OpenJudge# or add only this skill to Claude Code: copy the folder
skills/academic-eval/01-paper-review/
# into
~/.claude/skills/01-paper-review/ (all projects)
.claude/skills/01-paper-review/ (one project)
1# Paper Review Skill23Multi-stage academic paper review using the OpenJudge `PaperReviewPipeline`:451. **Safety check** — jailbreak detection + format validation62. **Correctness** — objective errors (math, logic, data inconsistencies)73. **Review** — quality, novelty, significance (score 1–6)84. **Criticality** — severity of correctness issues95. **BibTeX verification** — cross-checks references against CrossRef/arXiv/DBLP1011## Prerequisites1213```bash14# Install OpenJudge15pip install py-openjudge1617# Extra dependency for paper_review18pip install litellm19pip install pypdfium2 # only if using vision mode (use_vision_for_pdf=True)20```2122## Gather from user before running2324| Info | Required? | Notes |25|------|-----------|-------|26| Paper file path | Yes | PDF or .tar.gz/.zip TeX package |27| API key | Yes | Env var preferred: `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc. |28| Model name | No | `gpt-5.2`, `anthropic/claude-opus-4-6`, `dashscope/qwen-vl-plus`. See **Model selection** below |29| Discipline | No | If not given, uses general CS/ML-oriented prompts |30| Venue | No | e.g. `"NeurIPS 2025"`, `"The Lancet"` |31| Instructions | No | Free-form reviewer guidance, e.g. `"Focus on experimental design"` |32| Language | No | `"en"` (default) or `"zh"` for Simplified Chinese output |33| BibTeX file | No | Required only for reference verification |34| CrossRef email | No | Improves API rate limits for BibTeX verification |3536## Quick start37…
Excerpt shown under the repository's Apache-2.0 license.
More skills in OpenJudge
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
