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

Figure Drawing

by nanoAgentTeam in nanoAgentTeam/research-claw

MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper.

MITAuto-check passedDocuments & Office

Install Figure Drawing

skills CLI
$ npx skills add nanoAgentTeam/research-claw --skill figure-drawing -a claude-code

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

GitHub CLI
$ gh skill install nanoAgentTeam/research-claw figure-drawing --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/nanoAgentTeam/research-claw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/config/.skills/figure-drawing .claude/skills/figure-drawing && 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
figure-drawing
GitHub stars
293
Token cost
~1k tokens
SKILL.md length
351 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper.

  • Works in 5 steps: Plan the figure → Write the TikZ source → Compile to PDF, then convert to PNG → …
  • Tasks that involve LaTeX
  • SKILL.md covers CRITICAL RULES (read first), SOP, Layout & Anti-overlap Rules… and Style Guidelines
  • Calls pdftoppm

What it does

Figure Drawing is an agent skill from nanoAgentTeam/research-claw. MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper. Must be activated BEFORE writing any drawing code. Produces standalone .tex → compiled PDF/PNG → \includegraphics in paper. Never inline TikZ code directly into paper sections.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering LaTeX, PDF and Diagrams. The repository describes itself as: A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use. The licence is MIT.

When your agent uses it

  • Tasks that involve LaTeX
  • Tasks that involve PDF
  • Tasks that involve Diagrams

Example prompts

  • “/figure-drawing”

Requirements

  • Pre-approved tools (allowed-tools): read_file, write_file, str_replace, bash, latex_compile

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Plan the figure
  2. Write the TikZ source
  3. Compile to PDF, then convert to PNG
  4. Insert into paper
  5. Visual check

What it can do on your machine

Read from SKILL.md and the folder at commit ce3a4ac. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • read_file
    • write_file
    • str_replace
    • bash
    • latex_compile

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pdftoppm

    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

Figure Drawing loads about 1k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 351 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from nanoAgentTeam/research-claw at commit ce3a4ac, republished under its MIT licence (© nanoAgentTeam). 351 words, ~1,044 tokens.

Download SKILL.mdSave it as .claude/skills/figure-drawing/SKILL.md (or your agent's skills folder).
name
figure-drawing
description
MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper. Must be activated BEFORE writing any drawing code. Produces standalone .tex → compiled PDF/PNG → \includegraphics in paper. Never inline TikZ code directly into paper sections.
allowed-tools
read_file, write_file, str_replace, bash, latex_compile

Academic Figure Drawing

CRITICAL RULES (read first)

  1. NEVER inline TikZ code into paper sections. No \begin{tikzpicture} inside sections/*.tex or main.tex.
  2. NEVER \input{figures/xxx.tex} a raw .tex file. The paper must use \includegraphics.
  3. Every figure = standalone .tex → compile → PDF/PNG → \includegraphics.
  4. Always compile and verify the standalone figure before inserting into the paper.

SOP

Step 1: Plan the figure

Before writing any code, decide:

  • Type: taxonomy tree, architecture diagram, flowchart, bar/line chart, comparison table, timeline
  • Content: what nodes/elements to show (read the relevant paper sections first)
  • Layout direction: top-to-bottom or left-to-right (pick whichever avoids crowding)
  • Estimated element count: if > 20 nodes, split into multiple figures
Step 2: Write the TikZ source

Write a standalone .tex file in figures/:

latex
\documentclass[tikz,border=10pt]{standalone}
\usepackage[T1]{fontenc}
\usepackage{tikz}
\usetikzlibrary{positioning, arrows.meta, shapes, fit, backgrounds}
% Add other libraries as needed

\begin{document}
\begin{tikzpicture}[...]
  % figure content
\end{tikzpicture}
\end{document}
Step 3: Compile to PDF, then convert to PNG
bash
cd figures/
pdflatex -interaction=nonstopmode xxx.tex
# Convert PDF to PNG (try available tools in order)
pdftoppm -png -r 300 xxx.pdf xxx_fig  # produces xxx_fig-1.png
# OR: convert xxx.pdf -density 300 xxx.png
# OR: sips -s format png xxx.pdf --out xxx.png  (macOS)

If pdftoppm / convert / sips are all unavailable, keep the PDF and use \includegraphics{figures/xxx.pdf} as fallback.

Step 4: Insert into paper
latex
\begin{figure}[t]
  \centering
  \includegraphics[width=\columnwidth]{figures/xxx.png}
  \caption{Descriptive caption.}
  \label{fig:xxx}
\end{figure}
Step 5: Visual check

After compiling the full paper, verify the figure renders correctly and is referenced in the text with \ref{fig:xxx}.

Show full SKILL.md (205 more words)Show less

Layout & Anti-overlap Rules (CRITICAL)

These rules prevent the most common failure — elements overlapping each other:

  1. Use relative positioning, never absolute coordinates.

    latex
    \node[right=2cm of A] (B) {...};   % GOOD
\node at (3,2) (B) {...};          % BAD — will overlap when content changes

  2. Minimum spacing between nodes:

    • Siblings (same level): ≥ 1.2cm vertical, ≥ 2.0cm horizontal
    • Parent-child: ≥ 1.8cm
    • If text is long, increase spacing proportionally

  3. Set minimum node size to fit content:

    latex
    minimum width=3cm, minimum height=0.9cm, text width=2.6cm, align=center

    Use text width to force line-wrapping for long labels.

  4. For tree/taxonomy diagrams with many leaves:

    • Use grow=right or grow=down with level distance=2.5cm, sibling distance=1.5cm
    • If > 5 siblings at one level, increase sibling distance or stack in two columns

  5. Test for overlap: after compilation, check the PDF visually. If any elements overlap, increase spacing and recompile before finalizing.

Style Guidelines

Colors — use muted, professional tones:

  • Branch A: fill=blue!10, draw=blue!40
  • Branch B: fill=teal!10, draw=teal!40
  • Branch C: fill=orange!10, draw=orange!40
  • Branch D: fill=violet!10, draw=violet!40
  • Backgrounds: fill=gray!3

Text — minimum \footnotesize for any label. Use \small for node text, \normalsize\bfseries for titles. Never use \tiny.

Lines — draw=gray!50, arrow tip -{Stealth[length=5pt]}, line width 0.5pt.

Overall — generous whitespace. A figure that breathes is better than one that packs everything in. When in doubt, make it wider/taller.

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

Files

Just SKILL.md in config/.skills/figure-drawing of nanoAgentTeam/research-claw.

Open the folder on GitHubat commit ce3a4ac

Compare with similar skills

Figure Drawing 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.

Figure Drawing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Figure Drawing this skillnanoAgentTeam/research-claw293—~1kAutomated safety check: PassMIT
Paper Interpreterchujianyun/skills740—~810Automated safety check: PassCustom licence
Extract Tikzbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~498Automated safety check: NotesCustom licence
Harness Book Best Practicewquguru/harness-books3.2k—~4.1kAutomated safety check: PassNone
Research To Diagramwshuyi/research-to-diagram1561 repos~1.1kAutomated safety check: PassMIT
AI Review SkillNeuroDong/Ai-Review626—~2.5kAutomated safety check: PassMIT

Similar skills

  • Paper Interpreter

    chujianyun/skills

    论文解读助手。适用于用户发送 arXiv 论文链接，并希望下载论文、解读论文、生成读书笔记、做论文拆解或输出详细报告时使用。会在工作目录创建论文文件夹、下载 PDF 与 TeX Source（如有）、生成中文 Markdown 报告。默认先交付初稿，不自动复查；如果用户明确同意，再安排后续复查。不适用于只要简短推荐语的情况。

    740 GitHub stars~810 tokensUpdated today
    Documents & OfficeAuto-check passed

  • Extract Tikz

    brycewang-stanford/Auto-Empirical-Research-Skills

    Extract TikZ diagrams from Beamer source, compile to PDF, convert to SVG with 0-based indexing.

    4.5k GitHub stars~498 tokensUpdated 3 days ago
    Documents & OfficeAuto-check: notes

  • Harness Book Best Practice

    wquguru/harness-books

    Best practices for working on the Harness books repo. An agent skill from wquguru/harness-books.

    3.2k GitHub stars~4.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed

  • Research To Diagram

    wshuyi/research-to-diagram

    深度调研主题并自动生成知识关系图谱PDF。接收研究主题后自动进行网络调研、信息收集、知识整理，最终生成专业的可视化关系图谱。适用于"研究...并做图"、"深度分析...并可视化"、"生成知识图谱"等场景。

    156 GitHub starsUsed in 1 repo~1.1k tokens
    Documents & OfficeAuto-check passed

  • AI Review Skill

    NeuroDong/Ai-Review

    Generates structured AI paper reviews (SoT style) for LaTeX, PDF, and Word manuscripts.

    626 GitHub stars~2.5k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed

  • Ky Markdown Rebuilder

    KyrieCheungYep/ky-markdown-rebuilder

    Rebuild visual documents into reliable Markdown by combining text extraction with page or screenshot alignment.

    117 GitHub stars~5.7k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed

More from nanoAgentTeam/research-claw

All 14 skills in this repo

  • Aaai

    nanoAgentTeam/research-claw

    AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.

    293 GitHub stars~2.1k tokensUpdated 4 mo ago
    Auto-check passed

  • Acl Venues

    nanoAgentTeam/research-claw

    ACL-family venue paper formatting (ACL, EMNLP, NAACL, EACL, AACL, COLING, ARR, Findings) — activate when the user wants any ACL-series template setup, migration, or format fixes.

    293 GitHub stars~2.3k tokensUpdated 4 mo ago
    Auto-check passed

  • Colm

    nanoAgentTeam/research-claw

    COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.

    293 GitHub stars~2.2k tokensUpdated 4 mo ago
    Auto-check passed

  • Conference Research

    nanoAgentTeam/research-claw

    Academic venue paper discovery — activate when you need to find papers accepted at specific conferences or journals (ACL, EMNLP, NeurIPS, ICML, ICLR, MLSys, etc.), analyze venue acceptance…

    293 GitHub stars~823 tokensUpdated 4 mo ago
    Auto-check passed

  • Cvpr Iccv Eccv

    nanoAgentTeam/research-claw

    CVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences.

    293 GitHub stars~3.2k tokensUpdated 4 mo ago
    Auto-check passed

  • Iclr

    nanoAgentTeam/research-claw

    ICLR (International Conference on Learning Representations) paper formatting — activate when the user wants to submit to ICLR, follow ICLR template, or fix ICLR format issues.

    293 GitHub stars~2.7k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Figure Drawing

What does Figure Drawing do?

MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper. Figure Drawing is an agent skill from nanoAgentTeam/research-claw. MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper.

When should I use Figure Drawing?

Figure Drawing fits situations like: tasks that involve LaTeX; tasks that involve PDF; tasks that involve Diagrams.

How do I install Figure Drawing in Claude Code?

Run `npx skills add nanoAgentTeam/research-claw --skill figure-drawing -a claude-code`. Or copy the skill folder (config/.skills/figure-drawing in nanoAgentTeam/research-claw) into .claude/skills/figure-drawing in your project. Claude Code loads it when a task matches its description.

How do I install Figure Drawing in Codex?

Run `npx skills add nanoAgentTeam/research-claw --skill figure-drawing -a codex`. Or copy the skill folder (config/.skills/figure-drawing in nanoAgentTeam/research-claw) into .agents/skills/figure-drawing in your project. Codex loads it when a task matches its description.

Can I use Figure Drawing 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 nanoAgentTeam/research-claw --skill figure-drawing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/figure-drawing, .gemini/skills/figure-drawing, .github/skills/figure-drawing and .opencode/skills/figure-drawing in your project.

What does Figure Drawing need to run?

Going by SKILL.md and its folder, Figure Drawing needs the command-line tools its instructions call (pdftoppm). Its frontmatter pre-approves these tools: read_file, write_file, str_replace, bash, latex_compile.

Does Figure Drawing 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 Figure Drawing 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. Review the folder before installing.

What licence does Figure Drawing use?

Figure Drawing 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 Figure Drawing use?

About 1k tokens (SKILL.md is roughly 4.2k 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 Figure Drawing?

Skills that share tags, products or a category with Figure Drawing: Paper Interpreter (chujianyun/skills, 740 stars), Extract Tikz (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Harness Book Best Practice (wquguru/harness-books, 3.2k stars) and Research To Diagram (wshuyi/research-to-diagram, 156 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Figure Drawing?

nanoAgentTeam (a GitHub organization) maintains it in nanoAgentTeam/research-claw, which has 293 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on June 8, 2026.

Source: nanoAgentTeam/research-claw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.