Literature PDF OCR Library Builder
LigphiDonk/Oh-my--paper
Searches and downloads legally accessible academic PDFs, OCRs them to Markdown, and organizes the results into a traceable, AI-readable literature library.
Pulls architecture, method and result figures from an arXiv paper or PDF into an Obsidian vault and writes an index of them.
SKILL.md written in Chinese; this summary is our English description.
Install Paper Figure Extractor
$ npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install juliye2025/evil-read-arxiv extract-paper-images --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/juliye2025/evil-read-arxiv.git skills-src && mkdir -p .claude/skills && cp -r skills-src/extract-paper-images .claude/skills/extract-paper-images && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "extract-paper-images" agent skill from https://github.com/juliye2025/evil-read-arxiv/tree/main/extract-paper-images into .claude/skills/extract-paper-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-paper-images", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/juliye2025/evil-read-arxiv/tree/main/extract-paper-imagesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install juliye2025/evil-read-arxiv extract-paper-images --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juliye2025/evil-read-arxiv.git skills-src && mkdir -p .agents/skills && cp -r skills-src/extract-paper-images .agents/skills/extract-paper-images && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "extract-paper-images" agent skill from https://github.com/juliye2025/evil-read-arxiv/tree/main/extract-paper-images into .agents/skills/extract-paper-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-paper-images", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install juliye2025/evil-read-arxiv extract-paper-images --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juliye2025/evil-read-arxiv.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/extract-paper-images .cursor/skills/extract-paper-images && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "extract-paper-images" agent skill from https://github.com/juliye2025/evil-read-arxiv/tree/main/extract-paper-images into .cursor/skills/extract-paper-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-paper-images", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/juliye2025/evil-read-arxiv.git --path extract-paper-images--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install juliye2025/evil-read-arxiv extract-paper-images --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juliye2025/evil-read-arxiv.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/extract-paper-images .gemini/skills/extract-paper-images && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "extract-paper-images" agent skill from https://github.com/juliye2025/evil-read-arxiv/tree/main/extract-paper-images into .gemini/skills/extract-paper-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-paper-images", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install juliye2025/evil-read-arxiv extract-paper-imagesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/juliye2025/evil-read-arxiv.git skills-src && mkdir -p .github/skills && cp -r skills-src/extract-paper-images .github/skills/extract-paper-images && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "extract-paper-images" agent skill from https://github.com/juliye2025/evil-read-arxiv/tree/main/extract-paper-images into .github/skills/extract-paper-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-paper-images", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install juliye2025/evil-read-arxiv extract-paper-images --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juliye2025/evil-read-arxiv.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/extract-paper-images .opencode/skills/extract-paper-images && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "extract-paper-images" agent skill from https://github.com/juliye2025/evil-read-arxiv/tree/main/extract-paper-images into .opencode/skills/extract-paper-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-paper-images", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
extract-paper-images- GitHub stars
- 1.7k
- Token cost
- ~298 tokens
- SKILL.md length
- 97 words
- Files
- 3 (incl. scripts)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- None found
At a glance
Pulls architecture, method and result figures from an arXiv paper or PDF into an Obsidian vault and writes an index of them.
- Works in 5 steps: 将当前 SKILL.md 的父目录视为 。 → 从 OBSIDIAN_VAULT_PATH 解析 ；缺失时要求用户提供… → 接受 → …
- Extracting the architecture diagram from an arXiv paper for a note
- SKILL.md covers 输入识别, 执行, 验证 and 失败处理
- Runs Python scripts from its folder
What it does
Given an arXiv ID or link, a public direct PDF URL or a local PDF, the skill extracts architecture, method and experiment figures and saves them under the Obsidian vault, with an index.md that lists them. The vault path comes from OBSIDIAN_VAULT_PATH, and the agent asks for it if it is missing. Output goes to an images folder beside the paper note under 20_Research/Papers, and existing images are kept unless you ask for a refresh.
scripts/extract_images.py does the work. For arXiv it prefers images from the paper's source, then figure PDFs in the source, then the paper PDF; a direct PDF URL is downloaded to a temporary folder first; a local PDF is read with no network access. Ordinary web pages must first go through a source resolver from the paper-analyze skill, and a URL that returns HTML stops the run.
Checks follow: every file in index.md must exist, architecture, method, main-result and ablation figures are preferred over logos, small icons and duplicates, and unreadable or badly cropped PNGs are not recommended. The result lists the folder, index, count and three to five best filenames, with Obsidian embeds at width 800. It never bypasses access controls, deletes existing images or leaves temporary files in the vault. The SKILL.md is in Chinese.
When your agent uses it
- Extracting the architecture diagram from an arXiv paper for a note
- Collecting method and ablation figures from a local PDF into Obsidian
- Providing embeddable images for another paper-reading skill
Example prompts
- “Extract the architecture and results figures from this arXiv link into my vault.”
- “Pull the figures out of papers/attention-survey.pdf and build the image index.”
- “Refresh the images for the diffusion paper note, since the first crop was bad.”
Requirements
- An Obsidian vault path in OBSIDIAN_VAULT_PATH
- Python to run extract_images.py
- Network access for arXiv and direct PDF URLs
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 将当前 SKILL.md 的父目录视为 。
- 从 OBSIDIAN_VAULT_PATH 解析 ；缺失时要求用户提供 Vault 路径。
- 接受
- 非 arXiv 网页不能直接传给图片脚本。先使用 paper-analyze/scripts/resolve_source.py；若其返回 selected_pdf_url 或 local_pdf，再传该值。
- 确认输出目录位于 /20_Research/Papers///images。已有图片默认保留，除非用户要求刷新。
What it can do on your machine
Read from SKILL.md and the folder at commit ef3a594. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Paper Figure Extractor loads about 298 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 97 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 97 words (~298 tokens).
- name
- extract-paper-images
Files
SKILL.md and 2 other files (scripts) in extract-paper-images of juliye2025/evil-read-arxiv.
- SKILL.md
- agents/openai.yaml
- scripts/extract_images.py
Open the folder on GitHubat commit ef3a594
Compare with similar skills
Paper Figure Extractor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Paper Figure Extractor this skilljuliye2025/evil-read-arxiv | 1.7k | — | ~298 | Automated safety check: Pass | None | |
| Literature PDF OCR Library BuilderLigphiDonk/Oh-my--paper | 739 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Paper AnalyzerLigphiDonk/Oh-my--paper | 739 | 1 repos | ~973 | Automated safety check: Pass | MIT | |
| Paper Research on arXivXiaomiMiMo/MiMo-Code | 14k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Arxiv MCP Serverblazickjp/arxiv-mcp-server | 3.2k | — | ~353 | Automated safety check: Pass | Apache-2.0 | |
| Arxiv Paper Writeryunshenwuchuxun/latex-paper-skills | 267 | — | ~3.2k | Automated safety check: Pass | MIT |
Similar skills
Paper Analyzer
LigphiDonk/Oh-my--paper
Analyzes one research paper in depth, writing a structured note on its methods, experiments and limitations and adding it to a paper relationship graph.
Paper Research on arXiv
XiaomiMiMo/MiMo-Code
Searches arXiv, fetches metadata, generates BibTeX, downloads PDFs and finds citations and related papers using a bundled Python script.
Arxiv MCP Server
blazickjp/arxiv-mcp-server
A skill your agent uses when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or…
Arxiv Paper Writer
yunshenwuchuxun/latex-paper-skills
Writes ML/AI review and survey papers for arXiv using the IEEEtran LaTeX template with verified BibTeX citations.
Survey Paper Generator
dair-ai/dair-academy-plugins
Builds a single-file HTML survey paper on an AI or ML topic from a research bundle the agent curates, with prose and SVG figures written by Kimi K2.6.
More from juliye2025/evil-read-arxiv
Conference Paper Recommender
juliye2025/evil-read-arxiv
Searches DBLP for papers from top conferences such as CVPR, ICLR and NeurIPS, adds Semantic Scholar data, scores them and writes a yearly Obsidian note.
Obsidian Paper Notes Search
juliye2025/evil-read-arxiv
Searches already-saved paper notes in a local Obsidian vault by title, author, keyword, tag, field or arXiv ID, and ranks the matches by relevance.
Daily arXiv Paper Brief
juliye2025/evil-read-arxiv
Searches arXiv for recent papers matching your research interests, scores them and writes a daily recommendation note into an Obsidian vault.
Paper and Web Source Analyzer
juliye2025/evil-read-arxiv
Analyzes arXiv papers, PDFs, project pages and blogs and writes an evidence-backed Obsidian note with images and a knowledge-graph entry.
Related
Categories
Questions about Paper Figure Extractor
What does Paper Figure Extractor do?
Pulls architecture, method and result figures from an arXiv paper or PDF into an Obsidian vault and writes an index of them. md that lists them. The vault path comes from OBSIDIAN_VAULT_PATH, and the agent asks for it if it is missing.
When should I use Paper Figure Extractor?
Paper Figure Extractor fits situations like: extracting the architecture diagram from an arXiv paper for a note; collecting method and ablation figures from a local PDF into Obsidian; providing embeddable images for another paper-reading skill.
How do I install Paper Figure Extractor in Claude Code?
Run `npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a claude-code`. Or copy the skill folder (extract-paper-images in juliye2025/evil-read-arxiv) into .claude/skills/extract-paper-images in your project. Claude Code loads it when a task matches its description.
How do I install Paper Figure Extractor in Codex?
Run `npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a codex`. Or copy the skill folder (extract-paper-images in juliye2025/evil-read-arxiv) into .agents/skills/extract-paper-images in your project. Codex loads it when a task matches its description.
Can I use Paper Figure Extractor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add juliye2025/evil-read-arxiv --skill extract-paper-images -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/extract-paper-images, .gemini/skills/extract-paper-images, .github/skills/extract-paper-images and .opencode/skills/extract-paper-images in your project.
What does Paper Figure Extractor need to run?
Going by SKILL.md and its folder, Paper Figure Extractor needs Python for the scripts in its folder. Our summary lists: An Obsidian vault path in OBSIDIAN_VAULT_PATH; Python to run extract_images.py; Network access for arXiv and direct PDF URLs.
Does Paper Figure Extractor access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Paper Figure Extractor safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Paper Figure Extractor use?
No licence was found for Paper Figure Extractor or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Paper Figure Extractor use?
About 298 tokens (SKILL.md is roughly 1.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Paper Figure Extractor?
Skills that share tags, products or a category with Paper Figure Extractor: Literature PDF OCR Library Builder (LigphiDonk/Oh-my--paper, 739 stars), Paper Analyzer (LigphiDonk/Oh-my--paper, 739 stars), Paper Research on arXiv (XiaomiMiMo/MiMo-Code, 14k stars) and Arxiv MCP Server (blazickjp/arxiv-mcp-server, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Paper Figure Extractor?
juliye2025 (a GitHub user) maintains it in juliye2025/evil-read-arxiv, which has 1,703 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 15, 2026.
Source: juliye2025/evil-read-arxiv on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.