Garden Skills is an open-source collection of reusable instructions for AI coding agents such as Claude Code, Cursor, and Codex, covering tasks including web design, image generation, and turning source material into articles or presentations. Developers use the skills to guide agents through these workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ConardLi/garden-skills --skill motion-showreelgit clone --depth 1 https://github.com/ConardLi/garden-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/conardli/garden-skills/motion-showreel)<a href="https://agentmods.dev/skills/conardli/garden-skills/motion-showreel"><img src="https://agentmods.dev/badge/skills/conardli/garden-skills/motion-showreel/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/conardli/garden-skills/motion-showreel"><img src="https://agentmods.dev/badge/skills/conardli/garden-skills/motion-showreel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00188 | $0.06058 |
| Opus 5.5 | $0.00075 | $0.02423 |
| Sonnet 5.5 | $0.00038 | $0.01212 |
| Haiku 4.5 | $0.00019 | $0.00606 |
Grade A, and why
motion-showreel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion Showreel
把一个想法做成一支以图形、文字或界面动画为主的短视频，交付 MP4 和能重建的源码。
原理：页面暴露确定性的 render(t)，脚本逐帧截图，再用 ffmpeg 合成 MP4。配乐和音效在代码里合成，和画面共用一张时间表 timeline.js，所以卡点可以精确到帧。
好片子从哪来：变化密度、运动质感、一个记忆点、音画关系，这四项通常决定观感。但具体怎么动、动多少，由风格和内容决定，不是每支片子都要多机位、弹簧和满屏音效。全局只守几条底线（见「底线」），其余都是给模型的起点，不是天花板。
适用范围
| 用户想要 | 用这个 Skill？ |
|---|---|
| 产品宣传短片、动效作品集、UI 动效、动态排版 / 卡点、Logo 演绎、片头、循环动图 | ✅ |
| 视频模型生成的绿幕人物 + 代码做的场景、大字、动效 | ✅ 人物由用户提供（references/formats.md H 类） |
| 有口播稿或文章、要逐句讲解的几分钟视频 | ❌ 用 web-video-presentation |
| 网页、落地页、交互原型、静态视觉稿 | ❌ 用 web-design-engineer |
| 写实人物表演、实拍质感、剪辑已有素材、用视频模型直接出画面 | ❌ |
时长：最适合 5–60 秒。纯音乐驱动、没有旁白的片子可以做到 2 分钟左右（比如 mixed-media-era 那种年代回顾）；超过 60 秒时按段落分别制作、分别检查，开工前跟用户说清楚渲染和审片的成本。需要旁白讲解的视频不在本 Skill 范围内。
Opus 的长处和默认坑
- 长处：一个文件里能混用 Canvas、SVG/DOM、WebGL、Three.js，甚至每段换一种媒介；运动可以用公式精确计算（闭式弹簧、节拍网格、子帧运动模糊）；声音和画面读同一张时间表；能长时间自主「渲静帧 → 看图 → 修改」；审美判断力强，一句「全力以赴」就可能出很惊艳的东西。
- 默认坑：没有约束时，画面会落到深色背景、居中大字、所有元素一起淡入、紫蓝渐变加发光、机位不动；配乐会落到 A 小调四踩、每个重拍 impact + crash、钟声落版，几支片子听起来像同一首歌。所以要先找对标（画面和声音都要）、写清风格和禁止清单。但约束也不能写死：这个 Skill 的风格库和手法库都是起点，主题需要时随时改造、混搭或自定义。
- 做不好的：写实人物、复杂的手部 / 布料 / 毛发、需要真实物理精度的东西、照片级产品（除非用户提供模型或图片）。遇到这些就风格化处理，或者换成绿幕人物 + 代码场景的分工。
工作流
0 环境检查（一次）
1 一次问清 ──────── 能从请求里推断的就不问
2 brief.md ──────── 对标 → 用途 + 风格 → Reel Read → 节拍网格 + 分镜 + 禁止清单
3 风格帧 ────────── 🛑 唯一的停顿点：已定风格 → 1 个方向 3 张帧；未定风格 → 3 个方向各 1 张帧
4 制作 ──────────── timeline → 逐镜头 → 静帧自检 → 确定性检查 → 小样 → 正片
5 声音（可选）────── 代码合成 / 用户曲子 / 无声
6 验收 ──────────── 技术检查（程序判定，必须全过）+ 审片（看图列问题，交给用户终审）
7 交付
工作目录：在用户当前目录下建 <slug>/，所有文件都放在里面：brief.md、index.html、motion.js、timeline.js、score.mjs 或 score.tone.js（按 scaffold 的 --audio 选择）、build.sh、fonts/、assets/、audio/、qa/、out/。
第 0 步：环境
第一次使用时运行 sh <skill>/scripts/setup.sh：它会安装 Playwright 和 Chromium，再跑 check-env.mjs。需要 Node 18+ 和 ffmpeg；缺了就告诉用户怎么装，不要替用户装系统软件。工具自带测试：cd <skill>/scripts && npm test。
第 1 步：一次问清
用一条消息问，最多 5 个问题，请求里已经回答过的就跳过。用户说「你看着办」，就全部用默认值，并在 brief 里注明。
| 问什么 | 默认值 |
|---|---|
| 主题和素材：logo、产品截图、文案、品牌色、字体 | 只用用户给的事实，不编功能、数据和客户 |
| 观众看完要记住的一句话或一个画面 | 从主题里提炼 |
| 时长、画幅、平台 | 15 秒 · 1920×1080 · 30fps；竖屏平台用 1080×1920；UI 动效可以用 60fps |
| 风格：有指定的风格、参考视频或截图吗？ | 没有就在第 3 步给 3 个方向，看图选 |
| 声音：无声 / 代码合成 / 你提供曲子（需能商用） | 代码合成 |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/starter/build.sh 3.9 KB runs code
- assets/starter/index.html 4.6 KB
- assets/starter/motion.js 13 KB runs code
- assets/starter/package.json 64 B
- assets/starter/score.layer.mjs 1.4 KB runs code
- assets/starter/score.mjs 2.3 KB runs code
- assets/starter/score.tone.js 2.7 KB runs code
- assets/starter/timeline.js 1.8 KB runs code
- manifest.json 1007 B
- README.md 15 KB
- README.zh-CN.md 15 KB
- references/brief-template.md 5.5 KB
- references/craft.md 20 KB
- references/field-notes.md 2.0 KB
- references/formats.md 8.1 KB
- references/recipes.md 17 KB
- references/review.md 12 KB
- references/sound.md 27 KB
- references/stack.md 9.8 KB
- references/styles/_template.md 3.4 KB
- references/styles/cinematic-title.md 6.0 KB
- references/styles/comic-pop.md 7.6 KB
- references/styles/crayon-storybook.md 5.6 KB
- references/styles/crt-vhs.md 6.0 KB
- references/styles/dark-keynote.md 5.9 KB
- references/styles/data-motion.md 6.3 KB
- references/styles/editorial-collage.md 5.6 KB
- references/styles/flat-vector.md 7.2 KB
- references/styles/generative-geometry.md 5.4 KB
- references/styles/glass-material.md 7.1 KB
- references/styles/glitch-digital.md 7.6 KB
- references/styles/guochao.md 7.6 KB
- references/styles/INDEX.md 8.0 KB
- references/styles/ink-wash.md 5.7 KB
- references/styles/isometric-infographic.md 5.7 KB
- references/styles/kinetic-brutalist.md 5.9 KB
- references/styles/liquid-shader.md 5.7 KB
- references/styles/minimal-ui.md 6.1 KB
- references/styles/mixed-media-era.md 9.0 KB
- references/styles/painterly.md 7.4 KB
- references/styles/paper-cut.md 5.6 KB
- references/styles/particle-field.md 5.7 KB
- references/styles/pixel-game.md 6.0 KB
- references/styles/risograph-print.md 5.9 KB
- references/styles/soft-3d-toy.md 5.5 KB
- references/styles/soft-organic.md 7.0 KB
- references/styles/swiss-editorial.md 6.8 KB
- references/styles/synthwave-neon.md 8.5 KB
- references/styles/terminal-ascii.md 5.6 KB
- scripts/audio.mjs 19 KB runs code
- scripts/check-env.mjs 2.2 KB runs code
- scripts/inspect.mjs 23 KB runs code
- scripts/lib/browser.mjs 8.1 KB runs code
- scripts/lib/fft.mjs 1.5 KB runs code
- scripts/lib/frames.mjs 10.0 KB runs code
- scripts/lib/project.mjs 2.7 KB runs code
- scripts/lib/synth.mjs 40 KB runs code
- scripts/lib/text-hook.mjs 7.2 KB runs code
- scripts/lib/tone-render.mjs 5.8 KB runs code
- scripts/package-lock.json 3.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 220 lines · 188 tokens per session scan A dca0fd8d037e
motion-showreel is a skill published in the GitHub repository ConardLi/garden-skills (12,920 stars, last pushed 5d ago), licensed MIT. It adds 188 tokens to every session and 6,058 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
new
Create a new project to start development quickly.
oss-upload
Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
windbg-user-heap-corruption-investigation
Use when an app, service, or user-mode driver host heap fails or Application Verifier detects corruption; inspect history and bounds. Not for kernel pool corruption or ordinary OOM.
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…