Chinese Font Selector — guide skill for captions & subtitles
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the use-case page.
Pick Chinese fonts by license tier first (OFL, vendor-free, avoid), then by scene and mood, with Latin pairings.
- Type: Guide · Captions & subtitles
- Slug:
chinese-font-selector - Status: beta
- Publisher: Songzhi-lab (community)
- License: MIT
- Source: https://github.com/Songzhi-lab/chinese-font-selector/tree/main/chinese-font-selector
- Works in: Claude Code, Cursor, Codex
- Cost: Free — guidance only
- Adoption: 11 installs, 81 GitHub stars (skills.sh, 2026-10-26)
What it does
Chooses Chinese fonts with licensing first: T0 open-source OFL faces (Source Han Sans and Serif, Smiley Sans, LXGW WenKai and others), T1 faces their vendors declare free for commercial use (Alibaba PuHuiTi, MiSans, HarmonyOS Sans, ZCOOL and others), and T2 fonts to avoid (GPL WenQuanYi, Hanyi, and system fonts such as Microsoft YaHei or PingFang that may not be extracted for embedding). A scene-by-mood matrix covers social cards, brochures, web and UI, book interiors and posters, alongside Chinese–Latin pairing, type-scale and punctuation rules, and every recommendation must state its license and download source. The skill is written in Chinese and aimed at static design; for video it is a font-picking aid, not a renderer.
Use when
- Choose Chinese fonts that are free for commercial use
- Pair Chinese and Latin fonts for mixed typesetting
- Typography for Xiaohongshu cards, posters, brochures or web UI
Not for
- Fonts whose license cannot be found (the skill treats them as unusable)
- Rendering or animating the text (pair with a video or kinetic-type skill)
Install
- Claude Code:
npx skills add https://github.com/songzhi-lab/chinese-font-selector --skill chinese-font-selector - Codex:
npx skills add https://github.com/songzhi-lab/chinese-font-selector --skill chinese-font-selector - Cursor:
npx skills add https://github.com/songzhi-lab/chinese-font-selector --skill chinese-font-selector
More captions & subtitles skills
- 3D Camera Captions: Captions that live in 3D around a talking head: the camera flies through the words, heroes pass behind the speaker.
- Remotion Captions: Transcribe speech and burn in animated captions with Remotion, or import an existing SRT file.
- ElevenLabs Speech to Text: Transcribe audio and video with word timestamps, speaker labels and keyterms, ready for subtitles.
- ElevenLabs Speech to Text (inference.sh): Transcribe audio with ElevenLabs Scribe, speaker diarization and forced alignment, via inference.sh.
- Speech to Text: Transcribe audio with ElevenLabs Scribe v2 or Whisper V3 Large, with timestamps and speaker labels.
- Pretext Text Metrics: Measure and fit text without the DOM using pretext: auto-fit sizes, know line breaks before render, canvas/WebGL text.