메뉴
Anthropic visual style for plots, diagrams, slides, and web. Use when creating any visual output that should have Anthropic's look-and-feel — matplotlib charts, TikZ diagrams, HTML/CSS, or presentations.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/yulonglin/dotfiles --skill anthropic-style명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | anthropic-style |
| description | Anthropic visual style for plots, diagrams, slides, and web. Use when creating any visual output that should have Anthropic's look-and-feel — matplotlib charts, TikZ diagrams, HTML/CSS, or presentations. |
Use this skill when generating any visual output that should look Anthropic-branded: plots, charts, diagrams, slides, or web pages.
from anthro_colors import use_anthropic_defaults
use_anthropic_defaults()
import matplotlib.pyplot as plt
fig, ax = plt.subplots()
# All plots now use Anthropic style automatically
This loads ~/.config/matplotlib/stylelib/anthropic.mplstyle which sets:
#FFFFFF)references/colors.md)Load the relevant reference for your output type:
| Domain | Reference | When |
|---|---|---|
| matplotlib | references/matplotlib.md | Python plots, charts, figures |
| Colors | references/colors.md | Color palette lookup for any domain — accent colors have AA text-tier variants; check it before coloring text (brand accents fail AA as text on Ivory) |
| HTML/CSS | references/web-css.md | Web pages, HTML artifacts |
| TikZ | references/tikz.md | LaTeX diagrams for papers |
| Annotations & layout | ~/.claude/docs/visual-layout-quality.md | Arrow anchoring, label placement in empty space, spacing minimums — read whenever adding annotations (callouts, gap markers, brackets) to any chart |
| Name | Hex | Use |
|---|---|---|
| DARK_ORANGE (BOOK_CLOTH) | #B86046 | Primary accent, first in cycle |
| GREY | #656565 | Secondary, neutral elements |
| DARK_BLUE | #40668C | Tertiary accent |
| SLATE (GREY_950) | #141413 | Text, axes |
| IVORY (GREY_050) | #FAF9F5 | Light backgrounds (brand) |
| CLAY | #D97757 | Warm accent |
| SKY | #6A9BCC | Cool accent |
| OLIVE | #788C5D | Nature/green accent |
Full palette with all 9 hue ramps (orange through red, 100-900 each) in references/colors.md.
All color values come from lib/plotting/anthro_colors.py — that file is the single source of truth. If a hex code here conflicts with that file, the file wins.
Spawn a detached tmux session running Claude Code in a chosen directory, seeded with an initial prompt, optionally reachable by Remote Control.
A human-facing index of every skill and agent in this repo, grouped by category, with a one-line trigger for each. Use only when the user explicitly asks "what skills do I have", "what can you do", "is there a skill for X", or invokes `/catalog` directly — never fires on its own.
House plot styling — pastel matplotlib defaults + annotation helpers. Use when making publication-quality figures, when the user asks to "style my plots", "use house style", "use pastelplot/anthroplot", or when generating any matplotlib figure for reports, papers, or decks.