portfolio-detail — Chinese Studio / Lishu Portfolio (with Secondary Detail Page)
One-Line Feature
Horizontal text rows + hover to reveal a large image on the right + Alimama DaoLiTi art characters + black/white pure colors + light/dark theme + hash-routed detail pages + list/gallery dual view.
Differences from Other Portfolio Skills
| skill | core pattern | who it's for |
|---|---|---|
portfolio-gen | infinite drag canvas + tile tiling | photographers / graphic designers displaying samples |
portfolio-museum-gen | hero carousel + large cards + waterfall + detail page (cinematic curation feel) | video/film/installation artists |
industrial-archive-gen | black-framed flip cover + sidebar archive + Nordic industrial | physical products / objects / hardware |
lishu-portfolio-gen | horizontal text rows + hover reveals right thumbnail + lishu large characters + restrained Chinese style | bookbinding / typography / craft / Chinese atelier |
If the user's project is about "books / typefaces / exhibitions / still life / Chinese herbal medicine / tea / pottery / wood / paper / incense" — anything that requires a restrained, elegant character — use this one.
When to Trigger
The user says:
- "Make a Chinese / Eastern / classical style portfolio"
- "Make a lishu-style website / studio homepage"
- "Make a white-atelier style portfolio" / "Make a horizontal row list website like Gurgel D'Alfonso"
- "lishu-portfolio-gen ..."
And provide:
- Studio description (required): name, director, city, discipline, titles and stories of works
- Work images (optional): URL / upload / path. Works even without (uses picsum placeholders)
If the user gives no work titles at all → you must ask for at least which works to display. If the user gave only titles but no details → write them yourself: generate 1 lead sentence + 3 prose paragraphs + 6-8 spec lines + 3-6 picsum images + several credits per work. The tone should match the work type (book → bookbinding / typeface → typography / object → still life / exhibition → exhibition visual).
Two Operation Modes
Mode A · Claude Code / Local (has file system)
- Use
Bashto list folders,sipsto probe each image's dimensions - Output location:
~/Desktop/{slug}-portfolio.html(single file, all images via URL) - If the user gave local images: copy to
~/Desktop/{slug}-portfolio-images/and change src to relative paths
Mode B · GLM / Online Chat (no file system)
- The user unzips a dropped zip and sees 4 files
- Output only one complete HTML string, wrapped in a
```htmlcode block - If the user uploads images but gives no URL → use
https://picsum.photos/id/{id}/{w}/{h}placeholders (use known existing IDs) - Do not attempt to access local files, do not suggest command-line operations
Decision: If you cannot Read to see local images → default to mode B.
File Division
| file | role | how to use |
|---|---|---|
reference.html | Complete finished reference — BAIWU studio with 6 works | Look at: wording of list items, prose tone, spec vocabulary, JSON field density |
template.html | Empty skeleton — same CSS/JS/routing system, 2 example works + 20 SWAP markers | Modify on this basis, output final HTML |
README.md | User-facing usage instructions | Model doesn't need to look at it |
SKILL.md | Workflow for the model (this file) | Must read |
Core rule: All modifications are based on template.html; learn how to write from reference.html (tone, word count, tag usage), but do not copy specific content.
Work Steps
1. Read Both HTML Files
- Read
reference.htmlfirst to understand "what it looks like when complete" (especially the field density and prose tone in theworks-dataJSON) - Then read
template.htmlto find the 20 SWAP positions
Do not modify JS / CSS / detail page routing system / font inclusion. SWAPs are all in HTML text and JSON data.
2. Parse User Input — Extract Information
Extract:
- ATELIER_NAME_ZH — Studio Chinese name (2-4 characters optimal, e.g. "白屋" "素园" "墨记" "青庐" "拙轩")
- PINYIN — Pinyin (5-6 English letters, ALL CAPS: 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's name + pinyin
- DISCIPLINE — 3 discipline words ("装帧 · 字体 · 静物")
- TAGLINE — One-line positioning (20-40 characters, kai style tone)
- YEAR_FOUNDED — Founding year (can use stem-branch: 乙未冬 / 甲辰春)
For each work extract:
- slug — URL ID, lowercase English hyphenated (
kong-shan-ji/wu-ming-shu) - title_zh — Chinese title (2-5 characters optimal, the more concise the more character)
- title_en — English subtitle (title case style:
An Anthology of Empty Mountains) - year — Year or stem-branch year (
甲辰 / 2024/2025/乙巳 / 2025) - tag — Top category, enclosed in square brackets, e.g.
[ 诗集 · 装帧设计 ]/[ 字体设计 · 中草药图谱 ] - cover — Detail page large image URL
- list row location —
city, year · craft/specifications(appears on hover) - meta — 4 key-value pairs (detail page 4-column summary)
- lead — 30-70 character opening large text, can use
<em>keyword</em>to emphasize one point - prose — 3-4 prose paragraphs, each 80-150 characters
- specs — 6-10 specification lines (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 yourself: 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 feeling of "museum wall-text + studio notebook" (restrained, concrete, slow, traces of handcraft).
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 vertical images for list thumbnails (4:3 container, vertical images look better).
4. Replace 20 SWAPs
| SWAP | location | content |
|---|---|---|
| 1 | <title> | {ATELIER_NAME} {PINYIN} — {DIRECTOR} Portfolio / Studio |
| 2 | meta description | One-sentence website description |
| 3 | curtain single character | First character of studio name (e.g. "白") |
| 4 | logo SVG inner character | Same as SWAP-3 |
| 5 | logo SVG inner pinyin | {PINYIN} uppercase |
| 6 | main navigation li | Usually 3 items: Works / About / Contact |
| 7 | brand-block Chinese name | {ATELIER_NAME} split with space (e.g. 白 屋) |
| 8 | brand-block English | {PINYIN} Studio · {CITY} |
| 9 | tagline | Kai-style one-line positioning, 20-40 characters, can use <br> for line break |
| 10 | list items N works | Each <a class="item" href="#work/{slug}"> including num/project-name/en-name/location/photo-thumb |
| 11 | gallery items N works | Same N works, more compact grid — slug must match list |
| 12 | About title | 关 于 {name}<span class="en">About</span> |
| 13 | About paragraphs | 1-3 kai-style paragraphs (founding background / director / design philosophy), each 60-120 characters |
| 14 | About facts table | 4-6 li items (Founded/Location/Discipline/Director/Hours) |
| 15 | Contact title | 来 信<span class="en">Get in Touch</span> |
| 16 | Contact paragraphs | 1-2 paragraphs inviting contact + reply time commitment |
| 17 | Contact facts table | 4-6 items (E-mail/Phone/Address/Instagram/WeChat Official Account) |
| 18 | rotating credit | Site by {WHO} (usually the studio name) |
| 19 | footer three blocks | © / ICP filing / social links |
| 20 | works-data JSON | Full detail data for N works (critical!) |
5. Write works-data JSON (Most Critical Step)
Each work must have one entry in the JSON array, and the slug must exactly match #work/SLUG in the list/gallery card href.
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 1: Source of poems / design context. 80—150 characters.",
"Paragraph 2: Key decisions during production — typeface, paper, binding choices.",
"Paragraph 3: Final presentation / the feeling left 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 containing quotes → must use full-width
「...」or"..."(U+201C / U+201D), cannot use ASCII"(will break JSON) - Do not write actual newlines inside JSON strings; to indicate a new paragraph, add another item in the prose array
<em>word</em>in lead — write the HTML tag directly — it will be rendered as innerHTML- gallery
layoutmust 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/Xform instead ofseed/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 - For cover / gallery of the same work, use adjacent IDs to create a consistent color tone
- Do not use
?grayscaleparameter (users want color images)
7. Chinese Studio Name Inspiration (if user doesn't provide)
If the user says "make one up" → pick 2 characters with an antique feel:
- Object category: 白屋 / 素园 / 墨记 / 青庐 / 拙轩 / 听雨 / 一勺 / 半亩
- Character line category: 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 poetry
8. Video Support
If a work's cover is .mp4 / .webm / .mov, the detail page will automatically use <video autoplay muted loop> instead of <img>. The model just 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 rows to see thumbnails, click to enter detail page. Light/Dark at bottom-left, list/gallery toggle at top-center.
Mode B: Directly output the complete HTML code block + one-line instruction.
Save the above as
index.htmland double-click to open. Hover 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.
Must Preserve (Do Not Change)
- Font inclusion:
@font-faceloading Alimama DaoLiTi woff2 URL (do not change the font source) - CSS variable system: light/dark dual theme
- All JS: theme toggle, view mode toggle, hover-row interaction, rotating credit, detail page hash routing
applyRoute(),renderDetail() <script id="works-data">node must remain<main id="detail-root">must remain (detail page mount point)body[data-view="home/detail"]andbody[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 identical - JSON quotes: quotes inside Chinese content must be full-width «» or
"...", not ASCII" - Too many gallery: maximum 6 images per work, more will break the layout
- prose too long: each paragraph 80-150 characters, over 200 reduces readability
- list / gallery out of sync: must contain the same set of works (one-to-one correspondence)
- picsum seed: use
id/Xnotseed/X, to avoid random IDs hitting deleted images - works < 3: acceptable, minimum 2 works to run
- works > 8: recommend splitting into two batches; too many list rows make the page very long
- First character drop cap: detail page's
.detail__prose p:first-of-type::first-letteruses DaoLiTi — first paragraph must start with Chinese text (not<em>or English) - Removing picsum color: images should remain color; do not add
filter: grayscale()in CSS