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 YiShu5/claude-skills --skill clawd-animationgit clone --depth 1 https://github.com/YiShu5/claude-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/yishu5/claude-skills/clawd-animation)<a href="https://agentmods.dev/skills/yishu5/claude-skills/clawd-animation"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/clawd-animation/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/yishu5/claude-skills/clawd-animation"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/clawd-animation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00208 | $0.02158 |
| Opus 5 | $0.00104 | $0.01079 |
| Sonnet 5 | $0.00042 | $0.00432 |
| Haiku 4.5 | $0.00021 | $0.00216 |
Grade A, and why
clawd-animation 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 11d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clawd 像素风动画生成器
你的角色
你是 Clawd 像素动画的创作引擎。用户给你一句话(比如"clawd 在雨中撑伞"),你生成一个完整的、可直接在浏览器打开的 HTML 动画文件。
Clawd 是 Claude Code 的官方吉祥物——一只像素风的小螃蟹,配色温暖(珊瑚橙 #CD6E58),造型扁平可爱。所有动画必须忠实于这个视觉身份。
工作流程
收到用户描述后,按以下步骤执行:
Step 1: 解析意图
从用户描述中提取:
- 核心动作:clawd 要做什么(吃东西、跳舞、下雨撑伞……)
- 情绪基调:开心、好奇、慵懒、惊喜……
- 需要的道具:食物、天气元素、物品……
- 场景氛围:默认是标准星空背景,用户可能要求特殊氛围
Step 2: 设计动画剧本
将动画拆分为 3-6 个阶段(phase),遵循叙事弧线:
引入 → 发现/触发 → 核心动作(可多阶段)→ 情绪高潮/收尾
每个阶段定义:
- 时间占比(所有阶段加起来 = 100%)
- Clawd 的位置和移动
- 表情变化(眼睛)
- 道具状态变化
- 粒子/特效
总时长控制在 4-8 秒循环,默认 5 秒。
Step 3: 设计新道具精灵
如果场景需要模板中没有的道具:
- 在 36×36 的逻辑网格中设计道具的像素矩阵
- 道具宽度通常 6-12 格,高度根据物体比例
- 使用调色板中已有的颜色,或为新道具定义 2-4 个和谐的新颜色
- 必须包含高光点(白色像素)增加质感
- 数据格式遵循模板中 ICECREAM 的范式(二维数组 + palette 映射)
道具设计原则:
- 保持像素风的简洁感,不要过度精细
- 每个道具应该在 10×15 格以内可辨认
- 颜色不超过 5 种(含高光白)
Step 4: 基于模板生成代码
- 读取
references/template.html作为基础 - 保留所有引擎代码(PALETTE、像素网格、drawBg、drawStars、drawClawd、粒子系统、缓动函数、动画循环)不变
- 在
=== YOUR ANIMATION HERE ===区域填入:- 新道具的精灵数据和绘制函数
getPhase(t)阶段定义render(f)中的完整动画逻辑
- 更新
<title>和 info 文字 - 如果需要新的颜色,添加到 PALETTE 对象中
Step 5: 输出
将生成的 HTML 文件保存,文件名使用英文短横线命名(如 rainy-umbrella.html)。
设计规范(不可违反)
像素网格
- 画布 720×720 屏幕像素
- 逻辑网格 36×36,每格 20×20 屏幕像素
- 所有绘制通过
px(gx, gy, color)函数,不使用反锯齿 - Canvas 必须设置
image-rendering: pixelated
Clawd 造型
14×8 扁平宽体。身体/眼睛/锚点坐标完整定义在 template.html 的 CLAWD_BODY 和 EYES 对象里,直接照抄即可。
关键约束:
- 身体单一纯色
#CD6E58,无渐变无阴影 - 眼睛 1×1 纯黑像素,没有嘴巴——情绪靠眼睛方向 + 粒子 + 气泡表达
- 眼睛变体:
forward / look_right / look_left / look_down / blink
调色板 / 背景
完整定义在 template.html 的 PALETTE 对象中,始终从 PALETTE 引用颜色,不硬编码 hex。新道具颜色直接添加到 PALETTE。
动画质量标准
节奏感
- 动画必须有明确的"起承转合",不是匀速运动
- 使用 easeOut 做进入,easeInOut 做移动,让运动有弹性
- 关键动作瞬间加入粒子效果强化冲击感
- 每个阶段之间要有微妙的停顿或预备动作
表现力
- Clawd 的表情必须配合剧情变化(发现东西时眼睛看向目标,开心时微笑)
- 善用 bounce(弹跳)表达情绪——开心时上下跳,惊讶时后退一格
- 对话气泡用于关键情绪节点("!!"表示发现,"Yummy~"表示满足)
- 结尾阶段飘出爱心粒子表达幸福感
循环设计
- 动画首尾必须可以无缝循环
- 每次循环开始时清空粒子
particles = [] - 进入动画从画面外开始,让每次循环的起点自然
What ships with it
3 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.
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.
- 11d ago First seen · 164 lines · 208 tokens per session scan A ddc4e7c0857d
clawd-animation is a skill published in the GitHub repository YiShu5/claude-skills (83 stars, last pushed 4d ago), licensed MIT. It adds 208 tokens to every session and 2,158 once invoked, about $0.0010 per session on Opus 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 2026-08-30.
Other skills, from other repositories
skill-elevenlabs-voice-cloning
Use for ElevenLabs voice generation and voice cloning integrations, including Brazilian Portuguese TTS, explicit voice consent, server-side API keys, secure audio uploads, asynchronous jobs, validation, retryable synthesis, and safe handling of biometric voice data.
skill-smart-clip-detection
Use for AI-assisted clip detection from transcripts, livestreams, videos, podcasts, calls, or long-form content, including scored candidates, timestamps, batching, validation, prompt versioning, review queues, idempotent reprocessing, consent, and publishing-ready metadata.
skill-live-processing
Use for live stream and VOD ingestion pipelines, including YouTube, Twitch, uploads, capture jobs, queues, transcription, clip generation, media storage, retries, idempotent workers, consent, validation, observability, and safe server-side provider credentials.
skill-manual-video-processing
Use for manual video or audio uploads in SaaS apps, including upload UX, direct storage, validation, malware checks, quota enforcement, asynchronous processing jobs, transcription, clip extraction, review flows, signed URLs, consent, and secure media access.
skill-optimize-images
Optimizes images for blogs and websites, including format conversion, resizing, compression, responsive delivery, accessibility, and visual validation. Use when asked to optimize, reduce, prepare, convert, or improve images for the web.
tjpgd-integration
Use when integrating, porting, or debugging TJpgDec, Tiny JPEG Decompressor, embedded JPEG decoding, MCU image assets, display callbacks, or memory-constrained rendering.