- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add agentscope-ai/OpenJudge --skill 01-paper-review -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add agentscope-ai/OpenJudge --skill 01-paper-review -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add agentscope-ai/OpenJudge --skill 01-paper-review -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add agentscope-ai/OpenJudge --skill 01-paper-review -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/academic-eval/01-paper-review來自發布者
Multi-stage academic paper review using the OpenJudge PaperReviewPipeline:
# Install OpenJudge
pip install py-openjudge
# Extra dependency for paper_review
pip install litellm
pip install pypdfium2 # only if using vision mode (use_vision_for_pdf=True)
File type is auto-detected: .pdf → PDF review, .tar.gz/.zip → TeX review, .bib → BibTeX verification.
# Basic PDF review
python -m cookbooks.paper_review paper.pdf
# With discipline and venue
python -m cookbooks.paper_review paper.pdf \
--discipline cs --venue "NeurIPS 2025"
# Chinese output
python -m cookbooks.paper_review paper.pdf --language zh
# Custom reviewer instructions
python -m cookbooks.paper_review paper.pdf \
--instructions "Focus on experimental design and reproducibility"
# PDF + BibTeX verification
python -m cookbooks.paper_review paper.pdf \
--bib references.bib --email [email protected]
# Vision mode (for models that prefer images over text extraction)
python -m cookbooks.paper_review paper.pdf \
--vision --vision_max_pages 30 --format_vision_max_pages 10
# TeX source package
python -m cookbooks.paper_review paper_source.tar.gz \
--discipline biology --email [email protected]
# TeX source package with Chinese output and custom instructions
python -m cookbooks.paper_review paper_source.tar.gz \
--language zh --instructions "This is a short paper, be concise"
# Verify a standalone BibTeX file
python -m cookbooks.paper_review --bib_only references.bib --email [email protected]
Review score (1–6):
Correctness score (1–3):
BibTeX verification:
verified: found in CrossRef/arXiv/DBLPsuspect: title/author mismatch or not found — manual check recommendedThis pipeline uses litellm for model calls. Provider prefixes are handled automatically by the pipeline — see the table below.
IMPORTANT: The model MUST support multimodal (vision) input. PDF review uses vision mode
(--vision) to render pages as images, which requires a vision-capable model. Text-only models
will fail or produce empty reviews.
The --model value uses a provider/model-name convention so the pipeline knows
which API endpoint to call. The table below shows the exact string to pass:
Note on prefixes: The
dashscope/andanthropic/prefixes are interpreted by the pipeline itself — do not add them to the actual API key or base URL. For OpenAI models the bare model name (e.g.gpt-5.2) is sufficient.
If the user does not specify a model, choose one based on available API keys:
DASHSCOPE_API_KEY set → use dashscope/qwen-vl-plus (vision-capable)OPENAI_API_KEY set → search web for the latest vision-capable OpenAI model and use it (currently gpt-5.2)ANTHROPIC_API_KEY set → search web for the latest vision-capable Anthropic model and use it with anthropic/ prefix (currently anthropic/claude-opus-4-6)Vision mode is enabled by default for PDF review. Pages are rendered as images, which
preserves formatting, figures, and tables. To disable, pass --no_vision (not recommended).
The model must support multimodal (vision) input.
PipelineConfig options: reference.mdCRITICAL: When the pipeline fails with an API error, you MUST diagnose and fix the root cause. Do NOT fall back to reading the PDF as plain text yourself and calling the API manually — this bypasses the entire review pipeline and produces incorrect, incomplete results.
Diagnose by reading the full error message, then follow the checklist below:
echo $DASHSCOPE_API_KEY — must be non-empty.--model and re-run.--base_url ending with /v1/chat/completions instead of /v1.
litellm appends the path automatically — strip everything after /v1.--vision.--base_url or switch to a vision-capable model and re-run.--base_url points to the wrong host or port.curl <base_url>/models -H "Authorization: Bearer <key>"--base_url to the reachable endpoint and re-run.--timeout (default 7500 s) or reduce --vision_max_pages.Never summarise or interpret the paper yourself as a substitute for a failed pipeline run.
>
---name: 01-paper-reviewdescription: >---# skills/academic-eval/01-paper-review/SKILL.md常見問題
從發布者下載 skills/academic-eval/01-paper-review/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/agentscope-ai/OpenJudge。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。
30 |
| Max pages in vision mode (0 = all) |
--format_vision_max_pages | 10 | Max pages for format check (0 = use --vision_max_pages) |
--timeout | 7500 | API timeout in seconds |