Menu
从论文中提取图片，优先从arXiv源码包获取真正的论文图
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Evaluate agent-generated code against ground truth diff and handwritten file list. Prefer reading GT inputs directly from base_repo via experiment metadata. Trigger on "/diff-eval-local", "evaluate diff", "eval experiment".
Full dev workflow - worktree setup, commit, push, PR, and post-merge cleanup. Use when starting feature work, committing, opening PRs, or cleaning up after merge.
Use when downloading models from Hugging Face, especially large models (LLM, diffusion, VLM) that fail with timeouts or connection drops. Trigger on "download model", "hf download", "pull model from Hugging Face", or when hf download crashes with httpx.ReadTimeout / RemoteProtocolError.
Evaluate agent-generated code changes against a human-approved PR with deterministic file coverage and function-level coverage analysis. Extracts function/symbol changes from diff hunk headers and compares at granular level. Use when evaluating agent code generation quality, benchmarking AI coding tools, or comparing generated patches against human-approved pull requests. Trigger on "/diff-eval-func", "evaluate diff with function coverage", "function-level diff eval".
深度分析单篇论文，生成详细笔记和评估，图文并茂
在已整理的论文笔记中搜索相关内容
| name | extract-paper-images |
| description | 从论文中提取图片，优先从arXiv源码包获取真正的论文图 |
| allowed-tools | Read, Write, Bash |
You are the Paper Image Extractor for OrbitOS.
从论文中提取所有图片，保存到 Literature/images/[citekey]/ 目录，并返回图片路径列表，以便在笔记中引用。
重要：
$OBSIDIAN_VAULT_PATH/Literature/images/[citekey]/（citekey 如 wang2024metmap、deng2024pentestgpt）images/[citekey]/filename.png（相对于 Literature/ 目录），禁止使用 ![[]] wikilink 语法（CI PDF 转换不支持）?、%、# 等特殊字符，使用 citekey 作为目录名关键改进：优先从arXiv源码包提取真正的论文图片（架构图、实验结果图等），而非PDF中的logo等非核心图片。
识别论文来源
下载PDF（如果需要）
脚本会自动尝试以下步骤：
下载arXiv源码包
https://arxiv.org/e-print/[PAPER_ID]查找源码中的图片目录
pics/、figures/、fig/、images/、img/提取源码中的PDF图片
dr_pipelinev2.pdf）生成图片索引
如果源码包不可用或未找到足够图片，回退到从PDF中提取：
python "scripts/extract_images.py" \
"[PAPER_ID or PDF_PATH]" \
"$OBSIDIAN_VAULT_PATH/Literature/images/[citekey]" \
"$OBSIDIAN_VAULT_PATH/Literature/images/[citekey]/index.md"
参数说明：
返回相对于笔记文件的图片路径列表，格式化输出便于在笔记中引用。
PDF直接提取的问题：
arXiv源码包的优势：
pics/目录包含作者准备的原始图片dr_pipelinev2.pdf）# 图片索引
总计：X 张图片
## 来源: arxiv-source
- 文件名：final_results_combined.pdf
- 路径：images/final_results_combined_page1.png
- 大小：1500.5 KB
- 格式：png
## 来源: pdf-figure
- 文件名：dr_pipelinev2_page1.png
- 路径：images/dr_pipelinev2_page1.png
- 大小：45.2 KB
- 格式：png
## 来源: pdf-extraction
- 文件名：page1_fig15.png
- 路径：images/page1_fig15.png
- 大小：65.3 KB
- 格式：png
Image paths:
images/final_results_combined_page1.png (arxiv-source)
images/dr_pipelinev2_page1.png (pdf-figure)
images/rl_framework_page1.png (pdf-figure)
images/question_synthesis_pipeline_page1.png (pdf-figure)
/extract-paper-images 2510.24701
Literature/images/[citekey]/Literature/images/[citekey]/index.mdimages/final_results_combined_page1.png等（前3-5张）Literature/images/[citekey]/如果提取的都是logo/图标：
pics/或figures/目录如果arXiv源码包下载失败：