做什么
HyperFrames发射视频的家式超大macOS光标技术. 当一个场景涉及光标或指针引导的动作时,当踢出UI场景时,当用点击来点燃一个变形/过渡/打字跑去时,或者当一个场景读取为静态,已死或已死并需要一个廉价的高产运动源来携带取景者的眼睛并把它们从已死状态分出时,即装入. 覆盖光标大小/外观(包括品牌-motif光标),外屏入门法则,快取目标与点击自拍,点击-闪光-下拍,出出/交叉相接.
技能库 智客分类:媒体内容 oversized-cursor
HyperFrames发射视频的家式超大macOS光标技术. 当一个场景涉及光标或指针引导的动作时,当踢出UI场景时,当用点击来点燃一个变形/过渡/打字跑去时,或者当一个场景读取为静态,已死或已死并需要一个廉价的高产运动源来携带取景者的眼睛并把它们从已死状态分出时,即装入. 覆盖光标大小/外观(包括品牌-motif光标),外屏入门法则,快取目标与点击自拍,点击-闪光-下拍,出出/交叉相接.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
HyperFrames发射视频的家式超大macOS光标技术. 当一个场景涉及光标或指针引导的动作时,当踢出UI场景时,当用点击来点燃一个变形/过渡/打字跑去时,或者当一个场景读取为静态,已死或已死并需要一个廉价的高产运动源来携带取景者的眼睛并把它们从已死状态分出时,即装入. 覆盖光标大小/外观(包括品牌-motif光标),外屏入门法则,快取目标与点击自拍,点击-闪光-下拍,出出/交叉相接.
官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Oversized Cursor — the eye-carrier、Size & look (house convention)、Entry law — physical, never revealed、Tip-targeting & the click tap、The click IGNITES the next beat、Exit law & cross-scene handoff。
文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。
House-style oversized macOS cursor technique for HyperFrames launch videos. Load whenever a scene involves cursors or a pointer-led action, when kicking off a UI scene, when igniting a morph/transition/typing run with a click, or when a scene reads as static, dead, or stale and needs a cheap high-yield source of motion to carry the viewer's eye and segment them out of the stale state. Covers cursor size/look (incl. brand-motif cursors), the off-screen entry law, tip-targeting and the click tap, click-ignites-the-next-beat, and exit / cross-scene handoff.
Oversized Cursor — the eye-carrierSize & look (house convention)Entry law — physical, never revealedTip-targeting & the click tapThe click IGNITES the next beatExit law & cross-scene handoffChecklist
来源分类:skills.sh agent-skill
nameoversized-cursordescription具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「oversized-cursor」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-469dcba478c32779-%E8%B6%85%E5%A4%A7%E5%B0%8F%E5%85%89%E6%A0%87.html 请存为 .cursor/skills/oversized-cursor/SKILL.md 或 .claude/skills/oversized-cursor/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/heygen-com/hyperframes' --list
npx skills add 'https://github.com/heygen-com/hyperframes' --skill 'oversized-cursor'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
A deliberately oversized macOS-style pointer that travels the frame as a visible protagonist: it enters from off-screen, walks the viewer's eye to the next point of interest, clicks to cause the next thing that happens, and leaves. Production-proven across multiple launch films.
Why it exists. Big cursor movement is one of the cheapest high-yield motion sources in a launch video: one element, transform-only tweens, and it (1) brings the eye across the screen on scenes that would otherwise read as dead, (2) gives causal ignition to morphs/transitions ("the click did that"), and (3) segments the eye out of a stale state when kicking off a new scene or a complex animation sequence. Bigger is better — an actual-size cursor disappears at video scale.
7cqw (≈134px at 1920). In-mock / small-frame variants:
4.6–5.5cqw. Never smaller.#1c1c1c) + white stroke (1.4px). Pick per scene contrast, keep it
constant per film.filter: drop-shadow(0 4px 6px rgba(0,0,0,.3)), pointer-events: none,
z-index above all scene content, will-change: transform.#root .cursor {
position: absolute;
left: 48%;
top: 115%; /* off-screen below — the resting pose IS off-screen */
width: 7cqw;
height: 7cqw;
z-index: 20;
filter: drop-shadow(0 4px 6px rgba(0, 0, 0, 0.3));
pointer-events: none;
will-change: transform;
}
The cursor always enters from off-screen (canonical: from below, top:115–120%)
and travels to its first target in one decelerating glide. It must feel like it
entered the room. Never opacity-fade it in at a resting position, never mask-reveal
it — that reads as a glitch (a real, repeatedly observed failure mode).
duration: 0.4–0.92s, ease: power3.out, immediateRender: false on the fromTo.tl.fromTo(
cursor,
{ left: "48.6%", top: "115%" },
{ left: "48.6%", top: "55%", duration: 0.85, ease: "power3.out", immediateRender: false },
0.25,
);
The hot-spot is the arrow TIP, not the box center. Land the tip on the target's
center, and pivot all press scaling on the tip: transformOrigin: '21% 14%' (for the
house arrow path in a 24-unit viewBox).
Click = asymmetric compress/expand (1:2 ratio reads as a real tap):
tl.to(cursor, { scale: 0.84, duration: 0.1, ease: "power2.in", transformOrigin: "21% 14%" }, t);
tl.to(
cursor,
{ scale: 1, duration: 0.22, ease: "power2.out", transformOrigin: "21% 14%" },
t + 0.1,
);
The target's reaction is a separate, parallel tween (button: scale: 0.94 + press
color/shadow, starting at the same t). Cursor-only taps (e.g. focusing a text input)
get NO target reaction. Pair with cursor-click-ripple / press-release-spring for
the target side.
Never let a morph, typing run, window transform, or scene-defining animation simply start. Park the cursor on the trigger and let the click cause it, same-frame:
During long beats it doesn't own (typing, narration), the cursor drifts aside
(0.5–0.9s, power2.out) — never sits frozen on top of the action, never wobbles idly.
Two sanctioned exits — both physical, never an opacity fade in place:
power2.in
(left:'118%', left:'-12%', or top:'116%'), 0.5–0.7s.power2.in) toward the NEXT scene's first click point, covering the
first ~1/3 of that path; the next composition gsap.sets the cursor at the
handoff pose and continues with power2.out at matched velocity. The cursor itself
becomes the carrier element that stitches the seam:// scene A, last 0.3s — start the journey:
tl.to(cursor, { left: "40.7%", top: "63.7%", duration: 0.3, ease: "power2.in" }, CUT - 0.3);
// scene B, t=0 — finish it at matched velocity:
gsap.set(cursorB, { left: "40.7%", top: "63.7%" });
tl.to(cursorB, { left: "22%", top: "45%", duration: 0.6, ease: "power2.out" }, 0);
transformOrigin: '21% 14%'媒体内容
以纳米·香蕉Pro(Gemini 3 Pro Image)来生成/编辑图像. 用于创建/修改请求,包括编辑。 支持文本到图像+图像到图像; 1K/2K/4K; 使用 -- input-image.
媒体内容
从YouTube视频中获取并读取文字记录. 需要汇总视频时使用,回答有关视频内容的问题,或者从中提取信息.
媒体内容
Access ATXP支付API工具用于网页搜索,AI图像生成,音乐创建,视频生成,X/Twitter搜索,电子邮件,代理账户管理. 当用户需要实时网络搜索时使用,AI生成的媒体(图像,音乐,视频),X/Twitter搜索,发送/接收电子邮件,或创建和资助代理账户. 需要通过“ …
媒体内容
YouTube Data API与管理的OAuth的集成. 搜索视频,管理播放列表,访问频道数据,并与评论互动. 用户想与YouTube互动时使用此技能. 对于其他第三方应用,使用api-gateway技能(https://clawhub.ai/byungkyu/api-gate…