New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Paper Figure Analyzer

by Azhi-ss in Azhi-ss/academic-figure-skills

Analyzes a repository, paper draft or reference figure into structured handoff results for academic figure drawing; it writes no prompts and generates no images.

MITAuto-check passedResearch & Science

SKILL.md written in Chinese; this summary is our English description.

Install Paper Figure Analyzer

skills CLI
$ npx skills add Azhi-ss/academic-figure-skills --skill fig1-analyze -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Azhi-ss/academic-figure-skills fig1-analyze --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Azhi-ss/academic-figure-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/fig1-analyze .claude/skills/fig1-analyze && rm -rf skills-src

Use ~/.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/

Facts

Skill name
fig1-analyze
GitHub stars
148
Token cost
~388 tokens
SKILL.md length
92 words
Files
7 (incl. scripts, references)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Analyzes a repository, paper draft or reference figure into structured handoff results for academic figure drawing; it writes no prompts and generates no images.

  • Planning the figures of a paper from its draft or manuscript
  • SKILL.md covers 路由, 交接 and 停止
  • Runs Python scripts from its folder
  • Summarizing a code repository's architecture before drawing a method diagram

What it does

The agent first inspects the input to decide the route instead of treating every URL as a repository. A paper or draft, judged by its sections or LaTeX and Markdown structure, yields a Figure Plan, and early notes or outlines get only an overall framework figure. A code repository yields a Semantic Architecture Handoff, and a reference figure or an image inside a PDF yields a ReferenceAnalysis. When a paper and a repository arrive together, the paper sets the narrative and the repository only verifies parameters, tensor dimensions, module names and direction.

Missing information is flagged, never invented, and an unreadable PDF or page is reported as a limit. scripts/extract_pdf_figures.py only filters candidate images by size, so keeping or dropping them is a judgment call. Labels, claims and topology of a reference figure are not copied into a new figure unless a faithful redraw is requested. The agent stops after delivering the analysis and hands drawing to fig1-draw. The SKILL.md is in Chinese.

When your agent uses it

  • Planning the figures of a paper from its draft or manuscript
  • Summarizing a code repository's architecture before drawing a method diagram
  • Analyzing a reference figure's style and structure

Example prompts

  • “Analyze my paper draft in draft.md and plan the overall framework figure.”
  • “Read this repository and produce a semantic architecture handoff for the method diagram.”
  • “Extract the candidate figures from related-work.pdf and analyze the reference style.”

Requirements

  • Python to run extract_pdf_figures.py for PDF figure candidates
  • A PDF reader for paper text and captions

What it can do on your machine

Read from SKILL.md and the folder at commit 88c989d. 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 Analyzer loads about 388 tokens when it runs, and up to ~5.8k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 92 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~388
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.8k

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

The full file from Azhi-ss/academic-figure-skills at commit 88c989d, republished under its MIT licence (© Azhi-ss). 92 words, ~388 tokens.

Download SKILL.mdSave it as .claude/skills/fig1-analyze/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
fig1-analyze
description
把仓库、论文/草稿、参考图分析成可交接结果（SemanticArchitecture@1、FigurePlan@1、ReferenceAnalysis@1），不写 prompt，也不生图。
metadata.version
1.0.0

fig1-analyze

把仓库、论文或草稿、参考图分析成可交接结果。本 skill 不写 prompt，也不生图。

先检查输入内容，再选择路径。不要把所有 URL 当成仓库：打开页面或正文后，再判断它是论文、代码仓库，还是图。

检查时看这三件事：

  • 正文、章节或 LaTeX/Markdown 结构 → 论文或草稿
  • 源码、README、依赖与入口脚本 → 仓库
  • 图本身、图注，或 PDF 里的嵌入图 → 参考图

路由

草稿、大纲或完整手稿

Markdown、LaTeX、PDF 正文，或论文 URL 打开后的正文，读 references/paper.md，产出 Figure Plan v1。

  • 笔记、大纲、早期草稿：只规划 Figure 1（Overall Framework），不要强行补实验图。
  • 含实验结果的完整手稿：按论文主张规划多图。
  • 当前环境读不了 PDF 或网页时，报告限制，不要编造章节结构。
仓库

本地仓库路径，或打开后确认为代码仓库的 URL，读 references/repo.md，产出 Semantic Architecture Handoff v1。任务或框架分类不确定时，再读 references/keywords.md。

论文加仓库

论文与用户意图决定叙事和拓扑。仓库只核验参数、张量维度、模块名与执行方向，不另起一套架构。

参考图

外部风格参考图、PDF 中的图，或图片，读 references/reference-figure.md，产出 ReferenceAnalysis v1。

  • PDF 正文与图注用 PDF reader。
  • 只有需要抽出图片候选时，才运行 scripts/extract_pdf_figures.py。
  • 该脚本只按尺寸筛候选，不是结构分类器；保留、丢弃或不确定仍由证据判断。

证据不足时读 references/missing-info-policy.md。标出缺失项，不要补造模块、边或数值。

交接

字段与 JSON 形状以对应 reference 里的定义为准，此处不重写 schema：

  • Semantic Architecture Handoff v1（academic-figure/SemanticArchitecture@1）→ references/repo.md
  • Figure Plan v1（academic-figure/FigurePlan@1）→ references/paper.md
  • ReferenceAnalysis v1（academic-figure/ReferenceAnalysis@1）→ references/reference-figure.md

多种输入同时出现时，各走各的 reference，再按「论文定叙事、仓库只核验」合并。不要改字段名。参考图中的标签、主张与拓扑不要写入新方法图，除非用户明确要求忠实重绘。

停止

分析结果交付后即停止。用户要 prompt 或要图时，交给 fig1-draw。不要在本 skill 里编译 prompt，也不要生图。

© Azhi-ss, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (scripts, references) in fig1-analyze of Azhi-ss/academic-figure-skills.

  • SKILL.md
  • references/keywords.md
  • references/missing-info-policy.md
  • references/paper.md
  • references/reference-figure.md
  • references/repo.md
  • scripts/extract_pdf_figures.py

Open the folder on GitHubat commit 88c989d

Compare with similar skills

Paper Figure Analyzer 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.

Paper Figure Analyzer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Paper Figure Analyzer this skillAzhi-ss/academic-figure-skills148—~388Automated safety check: PassMIT
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Econ Writehanlulong/econ-writing-skill6512 repos~14kAutomated safety check: PassMIT
NSFC Grant Rationale Writerhuangwb8/ChineseResearchLaTeX2.9k—~945Automated safety check: PassMIT
Paper OrchestraAr9av/PaperOrchestra6791 repos~3.5kAutomated safety check: PassCustom licence
Backward Traceabilitylingzhi227/agent-research-skills390—~802Automated safety check: PassNone

Similar skills

  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Econ Write

    hanlulong/econ-writing-skill

    Expert economics paper writing assistant synthesizing advice from 50+ top guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Glaeser, Kremer, and other leading economists.

    651 GitHub starsUsed in 2 repos~14k tokens
    Research & ScienceAuto-check passed

  • NSFC Grant Rationale Writer

    huangwb8/ChineseResearchLaTeX

    Writes, restructures, reviews and polishes the rationale section of NSFC research grant applications in LaTeX, with backups and a diff before every write.

    2.9k GitHub stars~945 tokensUpdated 6 days ago
    Research & ScienceAuto-check passed

  • Paper Orchestra

    Ar9av/PaperOrchestra

    Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines…

    679 GitHub starsUsed in 1 repo~3.5k tokens
    Research & ScienceAuto-check passed

  • Backward Traceability

    lingzhi227/agent-research-skills

    Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.

    390 GitHub stars~802 tokensUpdated 7 mo ago
    Research & ScienceAuto-check passed

  • NSFC Proposal Length Aligner

    huangwb8/ChineseResearchLaTeX

    Checks a Chinese NSFC grant proposal against section length budgets, reports where it runs short or long, and guides meaning-preserving expansion or trimming.

    2.9k GitHub starsUsed in 1 repo~1.3k tokens
    Research & ScienceAuto-check passed

More from Azhi-ss/academic-figure-skills

  • Academic Figure Designer

    Azhi-ss/academic-figure-skills

    Plans, writes prompts for, renders and audits academic figures from repos, papers or notes, with an option to turn rendered text into editable PowerPoint.

    148 GitHub stars~5k tokensUpdated 4 days ago
    Auto-check passed

Works with

Categories

Questions about Paper Figure Analyzer

What does Paper Figure Analyzer do?

Analyzes a repository, paper draft or reference figure into structured handoff results for academic figure drawing; it writes no prompts and generates no images. The agent first inspects the input to decide the route instead of treating every URL as a repository. A paper or draft, judged by its sections or LaTeX and Markdown structure, yields a Figure Plan, and early notes or outlines get only an overall framework figure.

When should I use Paper Figure Analyzer?

Paper Figure Analyzer fits situations like: planning the figures of a paper from its draft or manuscript; summarizing a code repository's architecture before drawing a method diagram; analyzing a reference figure's style and structure.

How do I install Paper Figure Analyzer in Claude Code?

Run `npx skills add Azhi-ss/academic-figure-skills --skill fig1-analyze -a claude-code`. Or copy the skill folder (fig1-analyze in Azhi-ss/academic-figure-skills) into .claude/skills/fig1-analyze in your project. Claude Code loads it when a task matches its description.

How do I install Paper Figure Analyzer in Codex?

Run `npx skills add Azhi-ss/academic-figure-skills --skill fig1-analyze -a codex`. Or copy the skill folder (fig1-analyze in Azhi-ss/academic-figure-skills) into .agents/skills/fig1-analyze in your project. Codex loads it when a task matches its description.

Can I use Paper Figure Analyzer 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 Azhi-ss/academic-figure-skills --skill fig1-analyze -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fig1-analyze, .gemini/skills/fig1-analyze, .github/skills/fig1-analyze and .opencode/skills/fig1-analyze in your project.

What does Paper Figure Analyzer need to run?

Going by SKILL.md and its folder, Paper Figure Analyzer needs Python for the scripts in its folder. Our summary lists: Python to run extract_pdf_figures.py for PDF figure candidates; A PDF reader for paper text and captions.

Does Paper Figure Analyzer 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 Analyzer 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 Analyzer use?

Paper Figure Analyzer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paper Figure Analyzer use?

About 388 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.4k tokens, read only when the agent opens those files.

What are the alternatives to Paper Figure Analyzer?

Skills that share tags, products or a category with Paper Figure Analyzer: Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars), Econ Write (hanlulong/econ-writing-skill, 651 stars), NSFC Grant Rationale Writer (huangwb8/ChineseResearchLaTeX, 2.9k stars) and Paper Orchestra (Ar9av/PaperOrchestra, 679 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper Figure Analyzer?

Azhi-ss (a GitHub user) maintains it in Azhi-ss/academic-figure-skills, which has 148 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.

Source: Azhi-ss/academic-figure-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.