Token导航 LogoToken导航

Agent Skill · 研究检索

pretext(pretext 搜索)

pretext 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

pretext 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 64,068。

总安装 306周安装 13GitHub Stars 12下载 107核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:pretext(pretext 搜索)
来源仓库:https://github.com/yaniv-golan/pretext-skill
仓库路径:skills/pretext
安装命令:
npx skills add https://github.com/yaniv-golan/pretext-skill --skill pretext
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/yaniv-golan/pretext-skill --skill pretext

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。支持基于关键词、任务场景或来源线索进行信息筛选,适用于研究类工作流程。通过 GitHub 仓库安装,需确认权限范围和命令执行能力后再使用。建议结合原始 README 和安装命令核验具体功能与限制条件。

注意维护状态及是否触发联网、文件读写等操作。

来源仓库内路径:skills/pretext

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/yaniv-golan/pretext-skill --skill pretext;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

pretext 怎么安装?

在终端执行 npx skills add https://github.com/yaniv-golan/pretext-skill --skill pretext。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

pretext 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

pretext 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

pretext 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

pretext 用的人多吗?

公开数据是累计安装 306 次,近一周安装 13 次,下载 107 次,GitHub 12 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

pretext 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
pretext

pretext 搜索 · 本页

30612操作浏览器未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Pretext Integration Guide

You are helping a developer use @chenglou/pretext — a 15KB TypeScript library by Cheng Lou that computes exact text metrics using pure math (no DOM reflows). It uses CanvasRenderingContext2D.measureText internally, segments text, measures once, caches, then does arithmetic for all subsequent layouts.

When Pretext Is the Right Tool

Use Pretext when the developer needs to:

  • Know text dimensions before rendering — virtual scrolling, masonry layouts, card height estimation
  • Auto-fit text to a container — find the largest font size that keeps text within N lines (CSS has no equivalent)
  • Flow text around obstacles — magazine-style layouts where text wraps around shapes, images, or interactive elements
  • Measure text in canvas/SVG/WebGL — Pretext's measurements are exact for fillText
  • Measure many text items fast — each layout() call is ~0.0002ms after the first prepare() per font

When NOT to Use Pretext

  • CSS float/flex already handles it — don't reimplement text flow that CSS does natively
  • Content is HTML, not plain text — Pretext measures plain text strings. Tables, code blocks, nested elements need DOM measurement
  • TanStack Virtual + Pretext height estimation — this integration is fragile. Height errors compound over many items, and measureElement correction loops cause desyncing. For <500 items, just render all and use CSS transitions. For 1000+, use Pretext estimates as seeds but rely on DOM correction
  • Accordion content height — if content has HTML structure, use off-screen DOM measurement (visibility: hidden; position: absolute)

Quick Start

npm install @chenglou/pretext
import { prepare, layout } from '@chenglou/pretext';

// 1. Prepare a text+font pair (measures & caches internally)
const prepared = prepare('Hello world', '16px Inter');

// 2. Layout at any width — returns height and line count
const result = layout(prepared, 400, 24); // maxWidth=400, lineHeight=24px
// → { lineCount: 1, height: 24 }

// Reuse for different widths (instant — pure arithmetic)
const narrow = layout(prepared, 120, 24); // → more lines, taller

Critical Gotchas

These are the bugs that will waste your time if you don't know about them. Read this section before writing any Pretext code.

1. lineHeight Must Be in Absolute Pixels

layout() expects lineHeight in CSS pixels, not a multiplier. This is the #1 integration bug.

// WRONG — will compute heights ~14x too small (silent error)
layout(prepared, 500, 1.5);

// CORRECT — convert multiplier to pixels
const fontSize = 14;
const lineHeightPx = fontSize * 1.5; // = 21
layout(prepared, 500, lineHeightPx);

The error is silent — Pretext happily computes with lineHeight: 1.5 pixels, producing plausible-looking lineCount values but tiny height values.

2. prepare() Takes Text First, Font Second

// WRONG — arguments swapped
prepare('16px Georgia', 'Hello world');

// CORRECT
prepare('Hello world', '16px Georgia');

3. Each Text+Font Pair Needs Its Own prepare()

You cannot cache a single prepare() token and reuse it for different text. The library caches segment metrics per font string internally, so repeated calls with the same font are fast.

4. Fonts Must Be Loaded First

Pretext measures using currently loaded fonts. If you measure before web fonts load, you get fallback font metrics. Either await document.fonts.ready or accept slight inaccuracy.

5. system-ui Is Unreliable

On macOS, Canvas resolves system-ui to a different optical variant than DOM rendering. Use explicit font names for guaranteed accuracy.

6. No Canvas = No Pretext

Pretext requires CanvasRenderingContext2D.measureText. It works in all browsers and OffscreenCanvas workers, but NOT in Node.js without node-canvas.

7. Border in Height Estimates

When computing DOM element heights, don't forget border-width. A 1px border adds 2px total (top + bottom). Easy to miss, causes cumulative drift in layouts.

Which API Do I Need?

Start here. Match the developer's goal to the right API path — this avoids the most common mistake (using prepare when prepareWithSegments is needed, or vice versa).

Developer wants to...prepare variantlayout function
Get text height/line count at a given widthpreparelayout
Auto-fit font size (binary search over sizes)prepare (in a loop)layout
Auto-height a textareaprepare with {whiteSpace: 'pre-wrap'}layout
Get per-line text content (render, animate)prepareWithSegmentslayoutWithLines
Find widest line (shrink-wrap containers)prepareWithSegmentswalkLineRanges
Flow text around obstacles (variable width/line)prepareWithSegmentslayoutNextLine in a loop

The key decision is prepare vs prepareWithSegments:

  • prepare → only gives you layout() (height + line count). Fastest path.
  • prepareWithSegments → gives you ALL layout functions including layout(). Use this the moment you need per-line data or variable widths. There is no reason to call both for the same text.

Common API selection mistakes:

  • Using prepare then calling layoutWithLines → crashes at runtime (no .segments)
  • Using layoutWithLines when only widths are needed → walkLineRanges is cheaper (no string allocation)
  • Using layoutWithLines when width varies per line → must use layoutNextLine instead
  • Re-calling prepare on container resize → just call layout again with the new width (it's pure arithmetic)

For full signatures, types, and examples, see the API Reference.

Integration Patterns

For detailed code examples of each pattern, see Patterns Reference. Here's when to reach for each:

Wrapper Module (Recommended First Step)

Create a thin wrapper that converts lineHeight from CSS multiplier to pixels and returns null on failure. This prevents the critical lineHeight bug and enables progressive enhancement.

Auto-Fit Font Size

Binary search for the largest font that keeps text within N lines. This is Pretext's killer feature — CSS has no equivalent. Use for hero headlines, card titles, quote displays.

Height Estimation for Card Layouts

Measure variable text parts with Pretext, add fixed parts (padding, border, gaps) manually. Good for simple cards. Remember: this is inherently approximate — don't use for pixel-perfect virtualization.

Text Around Obstacles (layoutNextLine)

The creative powerhouse. Feed a different maxWidth per line based on obstacle position. This enables magazine layouts, text flowing around images, and all the impressive community demos.

Progressive Enhancement

Always load Pretext as enhancement — the page should work without it. Use type="module" as a natural feature gate.

Vendoring (No Build Step)

If you don't use a bundler, bundle Pretext into a single ESM file with esbuild first. It ships as multiple ES modules with relative imports that won't work standalone.

Creative Demos & Advanced Patterns

The Patterns Reference also covers creative patterns from the community:

  • Fluid ASCII art — full-screen fluid sim rendered as proportional ASCII characters
  • 3D wireframe text — torus/sphere drawn through a character grid
  • Text-based games — brick-breaker built entirely with Pretext text
  • Splat editor — text wrapping around 3D objects in real time
  • Dragon text reflow — text flowing around a moving 80-segment dragon
  • Accessible editorial engine — WCAG-compliant magazine layout

All use the same core API (prepare + layout / layoutNextLine) — the difference is how creatively you use obstacle-aware line routing and per-frame reflow.

Performance Notes

  • First prepare() per font: ~1-5ms (measures character segments)
  • Subsequent prepare() with same font: fast (cached segments)
  • Each layout() call: ~0.0002ms (pure arithmetic)
  • 500 texts: ~19ms prepare, ~0.09ms layout
  • Safe to call in requestAnimationFrame, scroll handlers, workers

Key Resources

平台分布

Codex

37.04%
按下载量换算40

Claude

27.6%
按下载量换算30

Cursor

19.56%
按下载量换算21

Gemini CLI

10.2%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills