anthropic-brand-typography
Use this skill when selecting and applying fonts for Anthropic brand materials. Specifies the official heading and body typefaces with correct fallback chains.
- License 许可
- MIT
- 最近更新
- 2026-10-02
- Stars
- ★ 93
- Forks
- 7
01 前言 Front Matter
- name
- anthropic-brand-typography
- description
- Use this skill when selecting and applying fonts for Anthropic brand materials. Specifies the official heading and body typefaces with correct fallback chains.
03 SKILL.md 正文
Anthropic Brand Typography
Heading Font
- Primary: Poppins (geometric sans-serif)
- Fallback: Arial
- Usage: All headings, product titles (e.g., "NOVA"), section headers
- Weight: Bold (700) for primary titles; SemiBold (600) for subheadings
- Style: Typically uppercase or title-case for product names
Body Font
- Primary: Lora (serif)
- Fallback: Georgia
- Usage: Body text, annotations, technical descriptions, captions
- Weight: Regular (400) for body; Medium (500) for emphasized annotations
Font Discovery Logic (Python / Pillow)
When rendering with Pillow, use this search order:
import os
from PIL import ImageFont
def find_font(font_names, size=48):
"""Search for fonts in common system paths, return first found."""
search_paths = [
"/usr/share/fonts",
"/usr/local/share/fonts",
"/root/.fonts",
"/root/.local/share/fonts",
"/System/Library/Fonts",
]
for font_name in font_names:
# Try direct load
for ext in [".ttf", ".otf"]:
try:
return ImageFont.truetype(font_name + ext, size), font_name
except (OSError, IOError):
pass
# Walk search paths
for base in search_paths:
if not os.path.isdir(base):
continue
for root, dirs, files in os.walk(base):
for f in files:
if font_name.lower().replace(" ", "") in f.lower().replace(" ", ""):
if f.endswith((".ttf", ".otf")):
try:
path = os.path.join(root, f)
return ImageFont.truetype(path, size), font_name
except (OSError, IOError):
pass
# Ultimate fallback: Pillow default
return ImageFont.load_default(), "default"
# For headings:
heading_font, heading_font_name = find_font(["Poppins-Bold", "Poppins", "Arial-Bold", "Arial"], size=72)
# For body/annotations:
body_font, body_font_name = find_font(["Lora-Regular", "Lora", "Georgia", "Arial"], size=24)
Important Notes
- The
applied_heading_fontfield indesign_parameters.jsonmust reflect whichever font was actually loaded — "Poppins" if found, otherwise the fallback name (e.g., "Arial"). - Never use Styrene A, Inter, or IBM Plex Sans as Anthropic brand fonts.
- Install Poppins via
pip install fonts-poppinsor download from Google Fonts if not present on the system. Attemptapt-get install -y fonts-poppinsor manually download to/root/.fonts/.
04 同仓库更多 Skills
object_counter
Count occurrences of an object in the image using computer vision algorithm.
travel-planning-workflow
Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.
bundled-dataset-search-tool
invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.
glm-output
Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final /root/metrics.json.
glm-calibration
Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.
glm-basics
A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.