cs-pixel-explainer

cs-pixel-explainer is a skill for Codex from ChenShuo2004/cs-skills. It costs 143 tokens per session (5,157 once invoked), scanned A, original, MIT.

A workflow for turning Chinese spoken scripts into pixel-art animated explainer videos. It plans scenes, creates coded visuals, adds text-to-speech narration, and renders a 1080p MP4.

In plain words
What is it for?
Use it to make pixel-style educational or explanatory videos with coordinate-system, network-graph, or slot-machine metaphors.
Why use it?
It replaces an open-ended video task with a reviewable process for planning, approving key frames, synchronising subtitles with narration, and checking each scene.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to make pixel-style educational or explanatory videos with coordinate-system, network-graph, or slot-machine metaphors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenshuo2004/cs-skills/cs-pixel-explainer
Install

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.

Any agent
npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer
Clone the repo
git clone --depth 1 https://github.com/ChenShuo2004/cs-skills

Made for: Codex.

Wrote 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.

agentmods badge for cs-pixel-explainer

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-pixel-explainer/github.svg)](https://agentmods.dev/skills/chenshuo2004/cs-skills/cs-pixel-explainer)
Your own site
<a href="https://agentmods.dev/skills/chenshuo2004/cs-skills/cs-pixel-explainer"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-pixel-explainer/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.

agentmods 80×15 button for cs-pixel-explainer

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenshuo2004/cs-skills/cs-pixel-explainer"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-pixel-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00143 $0.05157
Opus 5.5 $0.00057 $0.02063
Sonnet 5.5 $0.00029 $0.01031
Haiku 4.5 $0.00014 $0.00516

Measured 18d ago against content hash 1ffc33260ab1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cs-pixel-explainer 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 18d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (engine/render.mjs, engine/timeline.mjs, engine/tts.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

cs-pixel-explainer/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cs-pixel-explainer:像素风动画解说视频

参考风格:夜晚像素街道 + 左上角「关系坐标」HUD + 打字机字幕 + 把道理抽象成坐标系/老虎机/网络图。 全部画面由代码绘制(Canvas),页面暴露 window.render(t),Playwright 逐帧截图 + FFmpeg 合成 1080p MP4;配音用 edge-tts,每句真实时长驱动整条时间轴,字幕和动画自动对齐配音。

流程总览:问 5 项输入 → 设计隐喻 → 分镜表(等确认)→ 3 张关键帧(等确认)→ 配音 → 逐场景制作自检 → 整片 → 交付。

0. 引擎在哪

引擎 = engine/ 目录下 5 个文件:engine.html(场景库)timeline.mjs render.mjs tts.py 配音.bat。 按顺序找,找到一处即可,复制到工作目录 ~/pxe/engine/:

  1. 本 skill 目录:engine/(从 GitHub 安装时就在这里;没有就 git clone https://github.com/ChenShuo2004/cs-skills,目录 cs-pixel-explainer/engine/)
  2. 用户电脑(已关联时):读取用户提供的 engine 目录,通过当前可用文件工具获取;不假设固定电脑路径。
  3. Project「陈硕 video」文档:claude/pixel-explainer/engine.html 等 → project_read 后写入文件

像素纯度参考实现:assets/reference-wizard.html(施法巫师,128×96 调色板索引缓冲、整数倍放大、10 张/秒姿势量化、预分配粒子池、固定步长重放的 render(t)、无缝循环)。新场景、新角色从它的写法起步。

运行依赖:node + playwright、ffmpeg、Noto CJK 字体;Playwright 需有 Chromium 浏览器,若未安装其自带浏览器,渲染脚本会尝试使用本机 Chrome。Claude Cowork 环境若已预装这些依赖,无需重复安装。配音需要 Python、edge-tts 和可访问语音服务的网络;tts.py 缺少 edge-tts 时会自动安装。 配音.bat 缺了就按下面内容重建(必须 CRLF 换行,UTF-8):

@echo off
chcp 65001 >nul
cd /d %~dp0
where python >nul 2>nul && (python tts.py) || (py tts.py)
echo.
echo 配音完成后回到 Claude 说一声「配音好了」即可
pause

示例 spec:assets/example-spec.json(10 个场景全覆盖,写新 spec 前先读它)。

1. 开工先问 5 项输入(一条消息问完,没给的不编)

原材料里已经能确定的项直接写出来请用户确认,不重复问:

  1. 主题,以及看完以后希望观众记住的一句话(主题和这句话必须由用户给,可以帮忙改写,不能代填)
  2. 时长和画幅:__ 秒(本系列常见 90–180 秒),1920×1080 / 1080×1920 / 1080×1080,30 / 60 帧
  3. 风格:本系列锁定像素风;问有没有参考视频或截图、这支要不要换场景主题(夜晚街道 / 别的地点)
  4. 配色和字体:沿用系列调色板(黄=正向、红=负向、青=主角),还是这支换主色 #……
  5. 声音:用户提供的音乐文件(放项目目录,bgm)/ 代码合成芯片配乐 / 无配乐;要不要配音(默认要,男声 zh-CN-YunxiNeural)

用户回答「你定」的项才用默认值,并在分镜表顶部标注。无人值守时主题取自文案,其余用默认值,并在报告最前面列出假设。

2. 导演规则(每支都遵守)

  • 整片一套风格、一套调色板;主角、NPC、HUD 在每个场景里长得一样。
  • 每个场景只讲一件事;画面上的字少而大,每段文字(标题、标签、大字)至少停 2.5 秒;字幕每句 ≤ 22 字。
  • 动画用缓动或弹簧,不用匀速(路人行走除外)。
  • 转场从画面内容里长出来:地面塌陷 → 坠入 abyss、落地线变成 axes 的横轴、坐标点放大成下一场的角色。pixelDissolve 只作兜底,不要每场都用。
  • 镜头跟着内容动:推近主角、拉远看全局、跟随奔跑;主体至少占画面三分之一。
  • 禁止:居中大字 + 渐变背景的默认风格、所有元素同时淡入、满屏小字、任何看起来像模板的东西。

Read the full file on GitHub · 168 lines

Files

What ships with it

8 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.

Changes

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.

  1. 18d ago Changed · -5 lines 1ffc33260ab1
  2. 22d ago First seen · 173 lines · 143 tokens per session scan A 568f85e06ce4

Subscribe to this mod's changes

cs-pixel-explainer is a skill published in the GitHub repository ChenShuo2004/cs-skills (204 stars, last pushed 18d ago), licensed MIT. It adds 143 tokens to every session and 5,157 once invoked, about $0.0006 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 2026-10-03.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.

microsoft/vscode · 53 tokens