pretext – skill Agent & Tự động hóa cho agent AI
Xây dựng bản demo trình duyệt sáng tạo với bố cục văn bản không dùng DOM.
Cài skill pretext bằng một lệnh
Chọn công cụ bạn đang dùng, copy lệnh và dán vào terminal. Skill sẽ nằm trong thư mục skills của công cụ đó và sẵn sàng dùng ở phiên làm việc tiếp theo.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/pretext-2091b.tgz | tar xz -C ~/.claude/skills
Gọi trong Claude Code: /pretext – rồi mô tả công việc bạn muốn làm.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/pretext-2091b.tgz | tar xz -C ~/.codex/skills
Gọi trong Codex: $pretext – rồi mô tả công việc bạn muốn làm.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/pretext-2091b.tgz | tar xz -C ~/.hermes/skills
Gọi trong Hermes Agent: /pretext – rồi mô tả công việc bạn muốn làm.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/pretext-2091b.tgz | tar xz -C ~/.deepcode/skills
Gọi trong DeepSeek: /pretext – rồi mô tả công việc bạn muốn làm.
Nội dung SKILL.md
Nội dung SKILL.md gốc bằng tiếng Anh.
Pretext Creative Demos
Overview
[@chenglou/pretext](https://github.com/chenglou/pretext) is a 15KB zero-dependency TypeScript library by Cheng Lou (React core, ReasonML, Midjourney) for DOM-free multiline text measurement and layout. It does one thing: given (text, font, width), return the line breaks, per-line widths, per-grapheme positions, and total height — all via canvas measurement, no reflow.
That sounds like plumbing. It is not. Because it is fast and geometric, it is a creative primitive: you can reflow paragraphs around a moving sprite at 60fps, build games whose level geometry is made of real words, drive ASCII logos through prose, shatter text into particles with exact per-grapheme starting positions, or pack shrink-wrapped multiline UI without any getBoundingClientRect thrash.
This skill exists so Hermes can make cool demos with it — the kind people post to X. See pretext.cool and chenglou.me/pretext for the community demo corpus.
When to Use
Use when the user asks for:
- A "pretext demo" / "cool pretext thing" / "text-as-X"
- Text flowing around a moving shape (hero sections, editorial layouts, animated long-form pages)
- ASCII-art effects using real words or prose, not monospace rasters
- Games where the playfield / obstacles / bricks are made of text (Tetris-from-letters, Breakout-of-prose)
- Kinetic typography with per-glyph physics (shatter, scatter, flock, flow)
- Typographic generative art, especially with non-Latin scripts or mixed scripts
- Multiline "shrink-wrap" UI (smallest container width that still fits the text)
- Anything that would require knowing line breaks *before* rendering
Don't use for:
- Static SVG/HTML pages where CSS already solves layout — just use CSS
- Rich text editors, general inline formatting engines (pretext is intentionally narrow)
- Image → text (use
ascii-art/ascii-videoskills) - Pure canvas generative art with no text role — use
p5js
Creative Standard
This is visual art rendered in a browser. Pretext returns numbers; you draw the thing.
- Don't ship a "hello world" demo. The
hello-orb-flow.htmltemplate is the *starting* point. Every delivered demo must add intentional color, motion, composition, and one visual detail the user didn't ask for but will appreciate. - Dark backgrounds, warm cores, considered palette. Classic amber-on-black (CRT / terminal) works, but so do cold-white-on-charcoal (editorial) and desaturated pastels (risograph). Pick one and commit.
- Proportional fonts are the point. Pretext's whole vibe is "not monospaced" — lean into it. Use Iowan Old Style, Inter, JetBrains Mono, Helvetica Neue, or a variable font. Never default sans.
- Real source/text, not lorem ipsum. The corpus should mean something. Short manifestos, poetry, real source code, a found text, the library's own README — never
lorem ipsum. - First-paint excellence. No loading states, no blank frames. The demo must look shippable the instant it opens.
Stack
Single self-contained HTML file per demo. No build step.
| Layer | Tool | Purpose |
|-------|------|---------|
| Core | @chenglou/pretext via esm.sh CDN | Text measurement + line layout |
| Render | HTML5 Canvas 2D | Glyph rendering, per-frame composition |
| Segmentation | Intl.Segmenter (built-in) | Grapheme splitting for emoji / CJK / combining marks |
| Interaction | Raw DOM events | Mouse / touch / wheel — no framework |
<script type="module">
import {
prepare, layout, // use-case 1: simple height
prepareWithSegments, layoutWithLines, // use-case 2a: fixed-width lines
layoutNextLineRange, materializeLineRange, // use-case 2b: streaming / variable width
measureLineStats, walkLineRanges, // stats without string allocation
} from "https://esm.sh/@chenglou/[email protected]";
</script>Pin the version. @0.0.6 at time of writing — check [npm](https://www.npmjs.com/package/@chenglou/pretext) for the latest if demo behavior is off.
The Two Use Cases
Almost everything reduces to one of these two shapes. Learn both.
Use-case 1 — measure, then render with CSS/DOM
const prepared = prepare(text, "16px Inter");
const { height, lineCount } = layout(prepared, 320, 20);You still let the browser draw the text. Pretext just tells you how tall the box will be at a given width, without a DOM read. Use for:
- Virtualized lists where rows contain wrapping text
- Masonry with precise card heights
- "Does this label fit?" dev-time checks
- Preventing layout shift when remote text loads
Keep font and letterSpacing exactly in sync with your CSS. The canvas ctx.font format (e.g. "16px Inter", "500 17px 'JetBrains Mono'") must match the rendered CSS, or measurements drift.
Use-case 2 — measure *and* render yourself
const prepared = prepareWithSegments(text, FONT);
const { lines } = layoutWithLines(prepared, 320, 26);
for (let i = 0; i < lines.length; i++) {
ctx.fillText(lines[i].text, 0, i * 26);
}This is where the creative work lives. You own the drawing, so you can:
- Render to canvas, SVG, WebGL, or any coordinate system
- Substitute per-glyph transforms (rotation, jitter, scale, opacity)
- Use line metadata (width, grapheme positions) as geometry
For variable-width-per-line flow (text around a shape, text in a donut band, text in a non-rectangular column):
let cursor = { segmentIndex: 0, graphemeIndex: 0 };
let y = 0;
while (true) {
const lineWidth = widthAtY(y); // your function: how wide is the corridor at this y?
const range = layoutNextLineRange(prepared, cursor, lineWidth);
if (!range) break;
const line = materializeLineRange(prepared, range);
ctx.fillText(line.text, leftEdgeAtY(y), y);
cursor = range.end;
y += lineHeight;
}This is the most important pattern in the whole library. It's what unlocks "text flowing around a dragged sprite" — the demo that went viral on X.
Helpers worth knowing
measureLineStats(prepared, maxWidth)→{ lineCount, maxLineWidth }— the widest line, i.e. multiline shrink-wrap width.walkLineRanges(prepared, maxWidth, callback)— iterate lines without allocating strings. Use for stats/physics over graphemes when you don't need the characters.@chenglou/pretext/rich-inline— the same system but for paragraphs mixing fonts / chips / mentions. Import from the subpath.
Demo Recipe Patterns
The community corpus (see references/patterns.md) clusters into a handful of strong patterns. Pick one and riff — don't invent a new category unless asked.
| Pattern | Key API | Example idea |
|---|---|---|
| Reflow around obstacle | layoutNextLineRange + per-row width function | Editorial paragraph that parts around a dragged cursor sprite |
| Text-as-geometry game | layoutWithLines + per-line collision rects | Breakout where each brick is a measured word |
| Shatter / particles | walkLineRanges → per-grapheme (x,y) → physics | Sentence that explodes into letters on click |
| ASCII obstacle typography | layoutNextLineRange + measured per-row obstacle spans | Bitmap ASCII logo, shape morphs, and draggable wire objects that make text open around their actual geometry |
| Editorial multi-column | layoutNextLineRange per column + shared cursor | Animated magazine spread with pull quotes |
| Kinetic type | layoutWithLines + per-line transform over time | Star Wars crawl, wave, bounce, glitch |
| Multiline shrink-wrap | measureLineStats | Quote card that auto-sizes to its tightest container |
See templates/donut-orbit.html and templates/hello-orb-flow.html for working single-file starters.
Workflow
1. Pick a pattern from the table above based on the user's brief.
2. Start from a template:
templates/hello-orb-flow.html— text reflowing around a moving orb (reflow-around-obstacle pattern)templates/donut-orbit.html— advanced example: measured ASCII logo obstacles, draggable wire sphere/cube, morphing shape fields, selectable DOM text, and dev-only controlswrite_fileto a new.htmlin~/.hermes/cache/scratch/or the user's workspace.
3. Swap the corpus for something intentional to the brief. Real prose, 10-100 sentences, no lorem.
4. Tune the aesthetic — font, palette, composition, interaction. This is the work; don't skip it.
5. Verify locally:
cd <dir-with-html> && python -m http.server 8765
# then open http://localhost:8765/<file>.html
6. Check the console — pretext will throw if prepareWithSegments is called with a bad font string; Intl.Segmenter is available in every modern browser.
7. Show the user the file path, not just the code — they want to open it.
Performance Notes
prepare()/prepareWithSegments()is the expensive call. Do it once per text+font pair. Cache the handle.- On resize, only rerun
layout()/layoutWithLines()— never re-prepare. - For
… (nội dung đầy đủ có trong gói tải về)
Skill liên quan
- computer-use-agents – Xây dựng agent AI tương tác với máy tính như con người — xem màn hình, di chuyển con…
- conductor-implement – Thực thi các tác vụ từ kế hoạch triển khai của một track theo quy trình TDD.
- review-agent-setup – Cấu hình cổng kiểm soát có con người tham gia (human-in-the-loop) cho các hành động…
- conductor-setup – Cấu hình dự án Rails để làm việc với Conductor (các coding agent chạy song song)
- confluence-automation – Tự động hóa việc tạo trang Confluence, tìm kiếm nội dung, quản lý space, nhãn và điều…
- connection-auth-rules – Xây dựng Connection Auth Rules cho loại kết nối Monte Carlo. Lấy schema connector và các…
- context-agent – Agent ngữ cảnh giúp duy trì tính liên tục giữa các phiên. Lưu bản tóm tắt, quyết định…
- context-compression – Khi phiên làm việc của agent tạo ra lịch sử hội thoại hàng triệu token, việc nén ngữ…