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 S1mpleSonny/neon-vibe-motion --skill neon-replicategit clone --depth 1 https://github.com/S1mpleSonny/neon-vibe-motionWrote 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/s1mplesonny/neon-vibe-motion/neon-replicate)<a href="https://agentmods.dev/skills/s1mplesonny/neon-vibe-motion/neon-replicate"><img src="https://agentmods.dev/badge/skills/s1mplesonny/neon-vibe-motion/neon-replicate/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/s1mplesonny/neon-vibe-motion/neon-replicate"><img src="https://agentmods.dev/badge/skills/s1mplesonny/neon-vibe-motion/neon-replicate.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 | $0.00042 | $0.03586 |
| Opus 5 | $0.00021 | $0.01793 |
| Sonnet 5 | $0.00008 | $0.00717 |
| Haiku 4.5 | $0.00004 | $0.00359 |
Grade A, and why
neon-replicate scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L -o replicate-<效果名>/source.mp4 "<url>" How it starts
The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neon Replicate — 动效复刻工作流
从参考视频分析运动规律,生成 .neon 文件复刻效果,截帧对比迭代优化。
复刻目标:形似而非像素级一致。抓住效果的"灵魂特征",而不是描摹每一个细节。
Prerequisites
{skill_dir}is the directory where this SKILL.md file is located.
neonskill 已安装(neon命令可用)- FFmpeg 已安装(
ffmpeg命令可用)
验证:
neon --version && ffmpeg -version | head -1
Workflow Overview
1. 准备 → 创建工作目录,放入源视频
2. 分析 → 智能截帧 → 识别阶段灵魂 → 生成分析报告
3. 生成 → 基于报告创建 .neon → neon render
4. 对比 → 按阶段检查灵魂特征 → 定位问题
5. 迭代 → 每轮只修一个阶段 → 重新渲染 → 循环
Step 1: 准备工作目录
mkdir -p replicate-<效果名>/analysis/frames
输入源可以是本地文件或 URL:
# 本地文件
cp /path/to/effect.mp4 replicate-<效果名>/source.mp4
# URL 下载
curl -L -o replicate-<效果名>/source.mp4 "<url>"
Step 2: 智能截帧分析
第一阶段:粗扫描
以 2fps 截取全局概览帧:
bash {skill_dir}/scripts/extract-frames.sh coarse replicate-<效果名>/source.mp4 replicate-<效果名>/analysis/frames/
查看粗扫描帧,建立整体认知:
- 动效分几个阶段?每个阶段的"身份"是什么?
- 哪些时间段需要密集采样?
第二阶段:密集采样
对关键区间以 10fps 截帧(start 和 duration 单位为秒):
bash {skill_dir}/scripts/extract-frames.sh dense replicate-<效果名>/source.mp4 replicate-<效果名>/analysis/frames/ <start> <duration>
可对多个区间分别执行。
输出分析报告
查看所有截帧后,将分析写入 replicate-<效果名>/analysis/report.md。
分析报告模板
核心原则:先识别"灵魂"(定义效果身份的特征),再补充细节。灵魂必须可量化、可验证。
# 动效分析报告
## 基本信息
- 视频时长: Xms
- 分辨率: WxH(分析使用相对值,不依赖绝对分辨率)
- 背景色: #XXXXXX
- 阶段数: N
---
## 效果灵魂(时间线)
### 阶段 1: [阶段名] (0-Xms)
**灵魂特征**(定义这个阶段身份的可观测特征):
- 运动方向: [具体描述,如"所有元素指向中心,角度误差 < 20°"]
- 运动曲线: [如"easeOutCubic,前 50% 时间完成 80% 位移"]
- 空间变化: [如"半径从 5% cMin 扩展到 25% cMin"]
- 视觉变化: [如"透明度从 100% 线性衰减到 0%"]
**验证方法**:
- [如何在截帧上确认这个特征存在]
- [测量哪几帧的什么数据]
**缺失后果**:
- [如果没有这个特征,效果会变成什么样]
**权重**: 🔴 关键 / 🟡 重要 / 🟢 锦上添花
---
### 阶段 2: [阶段名] (X-Yms)
**灵魂特征**:
- ...
**验证方法**:
- ...
**缺失后果**:
- ...
**权重**: 🔴/🟡/🟢
---
(继续添加更多阶段...)
---
## 特征分级总览
### 🔴 必须对齐(丢了就不是这个效果)
- 阶段 X 的 [具体特征]
- 阶段 Y 的 [具体特征]
### 🟡 尽量接近(影响质感)
- [具体特征]
### 🟢 可自由发挥(随机细节)
- 单个粒子的具体轨迹
- 精确的随机分布位置
- 微小的时间偏移
---
## 技术实现要点
### 渲染模式
- canvas 2D / WebGL / hybrid
### 核心算法
- [生成机制:粒子系统 / 数学曲线 / 噪声场 / 物理模拟]
### 后处理
- [bloom / blur / 混合模式等]
### 关键参数(相对单位)
| 参数 | 值 | 来源 |
|------|-----|------|
| 粒子数量 | ~100 | 从帧 X 密度估算 |
| 扩散速度 | 30% cW/s | 从帧 N→N+1 位移计算 |
| 初始半径 | 5% cMin | 从帧 X 测量 |
| ... | ... | ... |
What ships with it
1 file 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 · 414 lines · 42 tokens per session scan A eaff130a6b14
neon-replicate is a skill published in the GitHub repository S1mpleSonny/neon-vibe-motion (57 stars, last pushed 6mo ago), licensed BSD-3-Clause. It adds 42 tokens to every session and 3,586 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.