AI Animation Skills is a collection of agent instructions and templates for generating single-file HTML animations, including presentations, diagrams, protocol visualizations, phone interfaces, and video-style scenes. People use the skills with AI coding agents to create animated web pages from descriptions or templates. The catalogue entries are the collection's individual generation 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 Unclecheng-li/AI_Animation --skill video-qa-frameproofgit clone --depth 1 https://github.com/Unclecheng-li/AI_AnimationWrote 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/unclecheng-li/ai_animation/video-qa-frameproof)<a href="https://agentmods.dev/skills/unclecheng-li/ai_animation/video-qa-frameproof"><img src="https://agentmods.dev/badge/skills/unclecheng-li/ai_animation/video-qa-frameproof/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/unclecheng-li/ai_animation/video-qa-frameproof"><img src="https://agentmods.dev/badge/skills/unclecheng-li/ai_animation/video-qa-frameproof.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 | $0.00082 | $0.01165 |
| Opus 5.5 | $0.00033 | $0.00466 |
| Sonnet 5.5 | $0.00016 | $0.00233 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
video-qa-frameproof 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 2d 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.
What it actually says
FrameProof Video QA
你是什么
你是 FrameProof 的生成后 QA 接入导航。它扫描最终 MP4、可选字幕/音频和 Render Manifest，产出机器可读问题、源码定位与修复包；它不是创作工具、渲染器或人工看图/听审的替代品。
- 上游：https://github.com/yocchi12345jp/frameproof-video-qa
- 扫描与修复闭环：references/verify-and-repair.md
- 本目录不 vendor CLI、Studio 或 Agent Skill，实际验收需安装/调用上游工具。
支持的内容/类型
| 层级 | 能发现的问题 |
|---|---|
| 帧与画面 | 空帧、非预期冻结、边缘活动、宽高比；manifest 可断言运动/可见性 |
| 字幕 | 过短/过快、行数/行宽、重叠、间隙、越界、与已声明 UI 区域碰撞 |
| 音频 | 音轨缺失、异常静音、综合响度、true peak；需显式启用音频分析 |
| 元数据与平台 | 分辨率、容器、编码、像素格式、fps、时长、文件大小与平台预设 |
| 源码定位 | Render Manifest 将帧区间映射到 composition、组件和源文件 |
| 回归 | 新出现、恶化、改善、已解决、不变、已接受问题及 Fix Packets |
核心工作流
Step 1 — 准备最终导出与声明意图
要求 Node.js 20+，FFmpeg 与 FFprobe 在 PATH。输入应是准备交付的实际 MP4，不是只用 HTML 预览代替。准备画幅、平台、时长、字幕文件、音频预期等验收条件。
npx frameproof-video-qa doctor
npx frameproof-video-qa init --video out/video.mp4
npx frameproof-video-qa verify
init 非破坏性生成 .frameproof/ 配置；verify 输出 JSON、HTML、Fix Packets、SARIF、JUnit 与摘要。先阅读项目已有配置，不用默认配置覆盖用户已声明的验收标准。
Step 2 — 需要源码定位时加入 manifest
核心扫描器不依赖 Remotion；有 React/Remotion 或其他源码映射需求时，增加 Render Manifest。manifest 声明帧区间、源码位置、元素区域及 motion/text/visible/audio/safe-area 等期望。
边缘活动不是 OCR，声明的字体大小也不是实际字形识别。对“文字写了什么”“是否美观”“表演是否自然”等，仍需人工查看关键帧。平台 UI overlay 是近似预览，不是所有设备/App 版本的像素保证。
Step 3 — 从报告回到最小修复
- 按 Finding / Fix Packet 的源文件、帧区间、expected/actual 与复现命令定位。
- 实际打开受影响帧、时间带或 1:1 裁切，区分真实缺陷、有意静止和检测误报。
- 优先修复源头，同输入、同种子、同配置重渲；不要只修改报告、阈值或 baseline 来制造通过。
- 修复后再次扫描最终 MP4，并复核相邻镜头、字幕和音画同步，防止局部修复引入回归。
Step 4 — 人工验收后建立 baseline
npx frameproof-video-qa baseline set .frameproof/artifacts/latest/report.json
npx frameproof-video-qa baseline status
只有看过成片和报告、确认当前状态可作为基准时才 set。CI 的 revision gate 默认阻止新增/恶化 error，不等于旧问题自动消失；已接受例外要有明确理由并可审计。
交付要求
交付报告路径、视频路径、实际检查范围、未解决 error/warning 和人工复核结论。无法听音时不能声称已完成听审；自动报告通过也不能声称不存在所有视觉或叙事问题。
来源与许可
上游 MIT。视频、字幕、字体、音乐和第三方素材的许可独立处理。FrameProof 是渲染器无关的通用 QA 工具，不是 Opus 5.5 专属项目。预览图来源见本目录 README.md。
What ships with it
4 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.
- 2d ago First seen · 78 lines · 82 tokens per session scan A 63ab1641a19f
video-qa-frameproof is a skill published in the GitHub repository Unclecheng-li/AI_Animation (1,662 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 1,165 once invoked, about $0.0003 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 2026-10-27.
Other skills, from other repositories
fund-holding-viewer
A deployment guide for a Chinese fund-holdings analysis web app. It covers running the app on Alibaba Cloud ECS, a virtual server service, with HTTPS through either a subdomain or a path on an existing domain.
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
insta-snapshots
Review and update Oxc Insta snapshots non-interactively after expected output changes or snapshot test failures.
output-dev-eval-testing
Create offline evaluation tests for Output SDK workflows using @outputai/core/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI.
output-eval-validate-judge
Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.