Communitygithub.com

Lishu Studio Portfolio Generator (中式工作室 / 隶书作品集)

Generates a single-file Chinese atelier-style portfolio website with horizontal row list, hover-reveal thumb interaction, art lishu typography via CDN, light/dark theme, and hash-routed detail pages. Takes a natural-language description and outputs one working .html file.

What is 隶书作品集)?

This skill generates a complete, single-file HTML portfolio website tailored for Chinese ateliers, studios, or craftspeople—such as bookbinders, calligraphers, ceramicists, tea masters, or herbalists—who need a refined, understated online presence. The site features a horizontal row of work titles; hovering over a title reveals a thumbnail on the right side. It uses the Alimama DaoLiTi lishu script font loaded via CDN for an artistic, historical feel, supports both light and dark themes, and includes hash-routed detail pages for each work with rich metadata, galleries, and credits. The skill works in two modes: in Claude Code it writes the file to ~/Desktop; in GLM or online chat it outputs the HTML inline within a code block. It accepts natural-language descriptions of the studio and its works, automatically generating prose, specifications, and gallery images (using picsum placeholders) if the user provides only titles. The skill is triggered by phrases like "做个中式工作室作品集", "做个隶书作品集", "lishu-portfolio-gen", or "做个白屋风格的作品集".

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/ARYAN2302/liquid_researcher/tree/HEAD/skills/design/design-templates/portfolio-detail

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

portfolio-detail — Chinese Studio / Lishu Portfolio (with Detail Pages)

One-sentence Description

Horizontal text rows + hover to reveal large image on the right + Alimama DaoLiTi artistic large characters + black-and-white pure color + light/dark theme + hash-routed detail pages + list/gallery dual views.

Differences from Other Portfolio Skills

skillcore modebest for
portfolio-geninfinite drag canvas + tile layoutPhotographers / graphic designers showing samples
portfolio-museum-genhero carousel + large cards + waterfall + detail pages (curated feel)Video / projection / installation artists
industrial-archive-genblack-bordered flip cover + sidebar archive + Nordic industrialPhysical products / artifacts / hardware
lishu-portfolio-genhorizontal text rows + hover shows right-side thumbnail + lishu large characters + restrained Chinese styleBookbinding / typeface / exhibition / still life / Chinese herbs / tea / ceramics / wood / paper / incense

If the user's project is about "books / typefaces / exhibitions / still lifes / Chinese herbs / tea / ceramics / wood / paper / incense" and requires a restrained, elegant aesthetic—use this one.

When to Trigger

The user says:

  • "Create a Chinese / Eastern / classical style portfolio"
  • "Create a lishu-style website / studio homepage"
  • "Create a white-house style portfolio" / "Create a horizontal list website like Gurgel D'Alfonso"
  • "lishu-portfolio-gen ..."

And provides:

  • Studio description (required): name, director, city, discipline, titles and stories for several works
  • Work images (optional): URL / upload / path. Can run without them (uses picsum placeholders)

If the user gives no work titles at all → you must ask at least which works to display. If the user gives only titles with no details → write them yourself: generate 1 lead sentence + 3 prose paragraphs + 6-8 spec rows + 3-6 picsum images + a few credits for each work. The tone should match the work type (book → bookbinding / typeface → typeface / object → still life / exhibition → exhibition visuals).

Two Operation Modes

Mode A · Claude Code / Local (with filesystem)

  • Use Bash to list folders, sips to probe image dimensions
  • Output location: ~/Desktop/{slug}-portfolio.html (single file, all images via URL)
  • If the user provides local images: copy them to ~/Desktop/{slug}-portfolio-images/ and update src to relative paths

Mode B · GLM / Online Chat (no filesystem)

  • The user drags in a zip; after decompression, 4 files are visible
  • Output only one complete HTML string, wrapped in a ` html code block
  • If the user uploads images but gives no URLs → use https://picsum.photos/id/{id}/{w}/{h} placeholders (use known good IDs)
  • Do not attempt to access local files, do not suggest command-line operations

Rule: If you cannot Read to see local images → default to mode B.

File Division

FileRoleHow to use
reference.htmlComplete finished reference — BAIWU studio with 6 worksStudy: wording of list items, prose tone, spec vocabulary, JSON field density
template.htmlEmpty skeleton — same CSS/JS/routing system, with 2 example works + 20 SWAP markersModify based on it to output the final HTML
README.mdInstructions from user perspectiveModel does not need to read
SKILL.mdWorkflow for the model (this file)Required reading

Core rule: All modifications based on template.html; learn how to write from reference.html (tone, word count, tag vocabulary), but do not copy specific content.

Work Steps

1. Read Both HTML Files

  • First read reference.html to understand “what it looks like when complete” (especially the field density and prose tone of the works-data JSON)
  • Then read template.html to find the 20 SWAP locations

Do not modify JS / do not modify CSS / do not modify the detail page routing system / do not modify the font import. SWAPs are all in HTML text and JSON data.

2. Parse User Input and Extract Information

Extract:

  • ATELIER_NAME_ZH — Chinese name of the studio (2-4 characters best, e.g., 「白屋」「素园」「墨记」「青庐」「拙轩」)
  • PINYIN — Pinyin (5-6 uppercase English letters: BAIWU / SUYUAN / MOJI)
  • CHAR — Single character for logo (usually the first character of the studio name: 白 / 素 / 墨 / 青 / 拙)
  • CITY — City
  • DIRECTOR_ZH / DIRECTOR_EN — Director name + pinyin
  • DISCIPLINE — 3 discipline words ("装帧 · 字体 · 静物")
  • TAGLINE — One-line positioning (20-40 characters, kai-shu style)
  • YEAR_FOUNDED — Year founded (may use Ganzhi: 乙未冬 / 甲辰春)

For each work, extract:

  • slug — URL ID, lowercase hyphenated English (e.g., kong-shan-ji / wu-ming-shu)
  • title_zh — Chinese title (2-5 characters best, the more refined the better)
  • title_en — English subtitle (book-title style, e.g., An Anthology of Empty Mountains)
  • year — Year or Ganzhi year (甲辰 / 2024 / 2025 / 乙巳 / 2025)
  • tag — Top category, wrapped in square brackets, e.g., [ 诗集 · 装帧设计 ] / [ 字体设计 · 中草药图谱 ]
  • cover — URL for the large detail page image
  • list row location — City, Year · Craft/Specs (shown on hover)
  • meta — 4 key-value pairs (4-column summary on detail page)
  • lead — 30-70 character opening large text, may use <em>keyword</em> to emphasize one point
  • prose — 3-4 prose paragraphs, each 80-150 characters
  • specs — 6-10 rows of specs (format/paper/binding/typeface/print run/printing/craft/price, etc.)
  • gallery — 3-6 images, layout one of three: g-wide / g-half / g-third
  • credits — 4-7 pairs of role/name

If the user gives only one sentence / no story → make it up: based on the work title and type, write lead and prose that match the work's character. Refer to reference.html for tone — not marketing language, but a feel of "museum wall-text + studio notes" (restrained, concrete, slow, tangible).

3. List Works + Probe Dimensions (Mode A only)

ls -la "{works_path}"
sips -g pixelWidth -g pixelHeight "{works_path}/{file}" 2>/dev/null

Get (filename, w, h, aspect) for each image. Prefer portrait images for list thumbnails (4:3 container, portraits look better).

4. Replace 20 SWAPs

SWAPLocationContent
1<title>{ATELIER_NAME} {PINYIN} — {DIRECTOR} Portfolio / Studio
2meta descriptionOne-sentence site description
3Curtain single characterFirst character of studio name (e.g., 「白」)
4Logo SVG inner characterSame as SWAP-3
5Logo SVG pinyin{PINYIN} uppercase
6Main navigation liUsually 3 items: Works / About / Contact
7brand-block Chinese name{ATELIER_NAME} with spaces between characters (e.g., 白&nbsp;&nbsp;屋)
8brand-block English{PINYIN} Studio · {CITY}
9taglineOne-line kai-shu positioning, 20-40 characters, may use <br> for line break
10list items N worksEach <a class="item" href="#work/{slug}"> contains num/project-name/en-name/location/photo-thumb
11gallery items N worksSame N works, more compact grid — slug must match list
12About title关&nbsp;于&nbsp;{name}<span class="en">About</span>
13About paragraphs1-3 kai-shu paragraphs (founding background / director / design philosophy), each 60-120 characters
14About facts table4-6 items li (Founded/Location/Discipline/Director/Hours)
15Contact title来&nbsp;信<span class="en">Get in Touch</span>
16Contact paragraphs1-2 paragraphs inviting correspondence + reply cycle commitment
17Contact facts table4-6 items (E-mail/Phone/Address/Instagram/WeChat Official Account)
18rotating creditSite by {WHO} (usually the studio name)
19Footer three blocks© / ICP / Social links
20works-data JSONComplete detail data for N works (key!)

5. Write works-data JSON (most critical step)

Each work must have one entry in the JSON array, and the slug must exactly match the #work/SLUG in list/gallery card hrefs.

JSON fields:

{
  "slug": "kong-shan-ji",
  "title_zh": "空山集",
  "title_en": "An Anthology of Empty Mountains",
  "year": "甲辰 / 2024",
  "tag": "[ 诗集 · 装帧设计 ]",
  "cover": "https://picsum.photos/id/143/1800/1100",
  "meta": [
    {"label": "Type / 类型", "value": "诗集装帧"},
    {"label": "Year / 年份", "value": "2024"},
    {"label": "Edition / 印量", "value": "首印 320 本"},
    {"label": "Format / 开本", "value": "130 × 195 毫米"}
  ],
  "lead": "三十六首关于山的诗。我们想做一本——读者翻开后,先听见<em>风声</em>,再读见字的书。",
  "prose": [
    "Paragraph one: poem source / design context. 80—150 characters.",
    "Paragraph two: key decisions during production — typeface, paper, binding choices.",
    "Paragraph three: final presentation / feelings for the reader."
  ],
  "specs": [
    ["开本 / Format", "130 × 195 毫米"],
    ["页数 / Pages", "144 页"],
    ["纸张 / Paper", "本色棉纸 90gsm"],
    ["装订 / Binding", "线装四目"],
    ["字体 / Typeface", "老宋(标题)· 楷体(正文)"],
    ["印刷 / Printing", "单色凸印"],
    ["印量 / Edition", "首印 320 本"],
    ["定价 / Price", "¥ 388"]
  ],
  "gallery": [
    {"src": "...", "layout": "g-wide", "caption": "封面"},
    {"src": "...", "layout": "g-half"},
    {"src": "...", "layout": "g-half"},
    {"src": "...", "layout": "g-third"},
    {"src": "...", "layout": "g-third"},
    {"src": "...", "layout": "g-third"}
  ],
  "credits": [
    ["设计 / Design", "周墨白"],
    ["手工装订 / Binding", "陈漱石(杭州·订书坊)"]
  ]
}

JSON pitfalls ⚠️:

  • Chinese prose using quotation marks → must use full-width 「...」 or "..." (U+201C / U+201D), cannot use ASCII " (will break JSON)
  • Do not write real line breaks inside JSON strings; to separate paragraphs, add another item in the prose array
  • <em>word</em> in lead directly write the HTML tag — rendered as innerHTML
  • gallery layout must be one of three: g-wide (full width) / g-half (half width) / g-third (one-third width)

6. Image Source Selection

  • picsum placeholders: use id/X form rather than seed/X (more stable). Known good IDs: 0, 20, 40, 51, 64, 76, 88, 91, 96, 119, 121, 130, 143, 145, 158, 164, 165, 175, 177, 180, 187, 195, 200
  • Use adjacent IDs for cover and gallery images of the same work to create consistent color tones
  • Do not use the ?grayscale parameter (users expect color images)

7. Chinese Studio Name Inspiration (if user doesn't provide)

If the user asks you to "come up with one" → choose 2 characters with an ancient, rustic feel:

  • Object names: 白屋 / 素园 / 墨记 / 青庐 / 拙轩 / 听雨 / 一勺 / 半亩
  • Script-styled: 素白 / 子衿 / 砚池 / 半山 / 寻常 / 浮云
  • Avoid functional words like "工作室 / 设计 / Studio" — let the name itself be poetic

8. Video Support

If the work cover is .mp4 / .webm / .mov, the detail page will automatically use <video autoplay muted loop> instead of <img>. The model only needs to provide the video path in the cover URL.

9. Report

Mode A: One-sentence report.

Generated ~/Desktop/baiwu-portfolio.html — 6 works, hover over rows to view thumbnails, click to enter detail pages. Light/Dark toggle at bottom left, list/gallery view at top center.

Mode B: Directly provide the full HTML code block + one-line explanation.

Save the above as index.html and double-click to open. Move the mouse over any work name to see the thumbnail appear on the right, click to jump to the detail page. To change images, replace the picsum URLs with your own image addresses.

Mandatory Preserved Elements (Cannot Modify)

  • Font import: @font-face loading the Alimama DaoLiTi woff2 URL (do not change the font source)
  • CSS variable system: light/dark dual themes
  • All JS: theme toggle, view mode toggle, hover-row interaction, rotating credit, detail page hash routing applyRoute(), renderDetail()
  • <script id="works-data"> node must be preserved
  • <main id="detail-root"> must be preserved (detail page mount point)
  • body[data-view="home/detail"] and body[data-mode="list/gallery"] state system
  • #logo / #main-menu / .theme-toggle / #project-view / #svp-credit five fixed-position elements

Quick Error Checklist

  • slug mismatch: list item #work/kong-shan-ji ↔ gallery item #work/kong-shan-ji ↔ JSON "slug": "kong-shan-ji" — all three must be exactly the same
  • JSON quotes: Chinese content quotation marks must be full-width 「」 or "...", not ASCII "
  • Too many gallery images: max 6 images per work; exceeding that will mess up the layout
  • prose too long: each paragraph 80-150 characters; readability drops above 200
  • list / gallery out of sync: must contain the same set of works (one-to-one correspondence)
  • picsum seed: use id/X not seed/X, to avoid random IDs hitting deleted images
  • Works < 3: allowed, minimum 2 works can run
  • Works > 8: recommend splitting into two batches; too many list rows makes the page too long
  • First character drop cap: detail page's .detail__prose p:first-of-type::first-letter uses DaoLiTi — the first paragraph must start with a Chinese character (not <em> or English)
  • Removing picsum color: images should remain in color; do not add filter: grayscale() in CSS

Individual skills in this repo

This repo contains 8 individual skills — each has its own dedicated page.

ARYAN2302/liquid_researcher

Chinese-market SaaS pricing page template — soft sky-blue glass-morphism, 4-tier card grid with one elevated "recommended" tier, monthly/annual toggle, FAQ accordion, ¥ pricing with Inter numerals, careful CJK linebreaking, ICP filing footer.

ARYAN2302/liquid_researcher

Premium calm-tech SaaS landing template — bilingual (CN/EN) literary voice over a dark forest-night palette with warm gold accent, Cormorant + Noto Serif SC, Three.js procedural forest hero, station-based scrolling narrative, custom cursor. Built for ambient-AI / creative-tool / philosophical SaaS, not loud commercial launch.

ARYAN2302/liquid_researcher

Pro-camera HUD mockup template — full-viewport black canvas wrapping a real video with monospace overlays (corner brackets, top status bar, side AF/exposure columns, bottom timecode + aperture/shutter/ISO row, vertical 8-filter wheel, animated reticle). For cinematographer portfolios, camera-app demos, LUT pack previews, filter-look auditions. NOT a TikTok/Reels mockup, NOT a storyboard, NOT a shot list, NOT a script document. The chrome wraps real footage — never a div placeholder.

ARYAN2302/liquid_researcher

Premium pre-launch waitlist page template — dark charcoal canvas with subtle vignette, drifting portrait video-thumbnail cards, fade-up cascades, glass nav, live-updating join counter, single email form with success/error states. Built for creative-tool / AI / niche-SaaS invite-only launches with hushed exclusive tone, not loud growth-marketing.

ARYAN2302/liquid_researcher

Route design-related HTML artifact tasks to the right artifact skill, reference, design system generation, or export skill.

ARYAN2302/liquid_researcher

Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, or generate spoken audio files. Supports multiple voices, adjustable speed, and various audio formats.

ARYAN2302/liquid_researcher

Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.

ARYAN2302/liquid_researcher

Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.

Related Skills