Agent skill

AI Video Production Assistant

by wanghui2323 in wanghui2323/ai-video-maker

Turns an idea, article, outline or audio file into a sourced, reviewable AI video, tracking whether narration uses a human, synthetic or cloned voice.

MITAuto-check passedMedia & Creative

SKILL.md written in Chinese; this summary is our English description.

Install AI Video Production Assistant

skills CLI

$ npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install wanghui2323/ai-video-maker make-ai-video --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/wanghui2323/ai-video-maker.git skills-src && mkdir -p .claude/skills && cp -r skills-src/make-ai-video .claude/skills/make-ai-video && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "make-ai-video" agent skill from https://github.com/wanghui2323/ai-video-maker/tree/main/make-ai-video into .claude/skills/make-ai-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-ai-video", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/wanghui2323/ai-video-maker/tree/main/make-ai-video

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install wanghui2323/ai-video-maker make-ai-video --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wanghui2323/ai-video-maker.git skills-src && mkdir -p .agents/skills && cp -r skills-src/make-ai-video .agents/skills/make-ai-video && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "make-ai-video" agent skill from https://github.com/wanghui2323/ai-video-maker/tree/main/make-ai-video into .agents/skills/make-ai-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-ai-video", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install wanghui2323/ai-video-maker make-ai-video --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wanghui2323/ai-video-maker.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/make-ai-video .cursor/skills/make-ai-video && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "make-ai-video" agent skill from https://github.com/wanghui2323/ai-video-maker/tree/main/make-ai-video into .cursor/skills/make-ai-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-ai-video", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/wanghui2323/ai-video-maker.git --path make-ai-video

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install wanghui2323/ai-video-maker make-ai-video --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wanghui2323/ai-video-maker.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/make-ai-video .gemini/skills/make-ai-video && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "make-ai-video" agent skill from https://github.com/wanghui2323/ai-video-maker/tree/main/make-ai-video into .gemini/skills/make-ai-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-ai-video", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install wanghui2323/ai-video-maker make-ai-video

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/wanghui2323/ai-video-maker.git skills-src && mkdir -p .github/skills && cp -r skills-src/make-ai-video .github/skills/make-ai-video && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "make-ai-video" agent skill from https://github.com/wanghui2323/ai-video-maker/tree/main/make-ai-video into .github/skills/make-ai-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-ai-video", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install wanghui2323/ai-video-maker make-ai-video --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wanghui2323/ai-video-maker.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/make-ai-video .opencode/skills/make-ai-video && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "make-ai-video" agent skill from https://github.com/wanghui2323/ai-video-maker/tree/main/make-ai-video into .opencode/skills/make-ai-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-ai-video", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: make-ai-video
GitHub stars: 101
Token cost: ~924 tokens
SKILL.md length: 177 words
Files: 32 (incl. scripts, references, assets)
Skills in repo: 1
Repo updated: Aug 16, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Turns an idea, article, outline or audio file into a sourced, reviewable AI video, tracking whether narration uses a human, synthetic or cloned voice.

Works in 9 steps: 建立 video-brief.json → 检查声音依赖 → 建立 content-decision.json → …
Turning a written idea or article into a planned video with narration and visuals
SKILL.md covers 启动即执行, 读取所需合同, 使用两条时钟 and 执行工作流, plus 2 more sections
Calls node

What it does

Runs a diagnostic script on activation to check what already exists in the current production package, then writes whatever the user has provided into a video brief and keeps moving forward until it reaches the next real approval point that needs a human decision, rather than just listing steps or handing commands back to the user. Reversible local actions such as checking files, creating folders, and validating the brief proceed on their own; installing dependencies or downloading a large voice model requires explaining size and purpose first and getting approval.

Two separate cycles govern the work: an infrequent voice-setup cycle that only runs when the user explicitly wants a cloned voice and no usable voice profile exists yet, covering consent, reference recordings and calibration candidates; and a per-video production cycle that goes from the brief through a content decision, a content plan, locked narration, generated audio, and on to rendering. Content decisions are generated as several candidates that each answer one question, with only one recommended at a time while the rest are kept.

Video length follows fixed bands by content density, from a 35-to-50-second single correction up to a multi-section deep piece, and full rendering or cloned narration is blocked until both the content plan and the narration have been explicitly reviewed. A bundled example package shows the complete set of objects for reference, and the skill is told never to invent personal experience, data or examples to fill a gap.

When your agent uses it

Turning a written idea or article into a planned video with narration and visuals
Checking current production status before resuming an in-progress video
Setting up a cloned voice profile before using it in a video
Reviewing a locked content plan and narration before rendering starts

Example prompts

“帮我把这篇文章做成一个课程视频，先检查一下现有素材。”
“Continue the video for the product launch idea up to the next approval point.”
“Set up my cloned voice profile first, then start today's video production.”

Requirements

Node.js, to run the bundled production scripts

Workflow steps

9 steps, taken from the step headings in SKILL.md.

建立 video-brief.json
检查声音依赖
建立 content-decision.json
建立 video-content-plan.json
冻结内容和口播
生成本次声音
建立正式时序与 video-unit.json
预览、渲染与检查
记录真实状态

What it can do on your machine

Read from SKILL.md and the folder at commit 1e6d869. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
- node
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Video Production Assistant loads about 924 tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 177 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~45
When it runs · the whole SKILL.md, loaded when a task matches: ~924
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~4.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from wanghui2323/ai-video-maker at commit 1e6d869, republished under its MIT licence (© wanghui2323). 177 words, ~924 tokens.

Download SKILL.mdSave it as .claude/skills/make-ai-video/SKILL.md (or your agent's skills folder). This skill also uses 31 other files; get the full folder from GitHub.

name: make-ai-video
description: 协助把想法、文章、提纲、已有口播、资料包或音频制作成有来源、可审核、可恢复的 AI 视频，并可选接入本地声音克隆。适用于用户提出“帮我把这个思路做成视频”“文章转视频”“整理口播和分镜”“用我的声音生成”“制作课程视频或短视频”“检查字幕、渲染或发布状态”等任务；也适用于需要区分首次声纹建档、本次配音、视频渲染和人工发布门禁的场景。

AI 视频制作助手

从用户已有的想法或素材开始，先判断输入和当前阶段，再协助完成内容、声音、画面与审核。不要把文章当作默认入口，也不要把首次声音建档、本次正式配音和整片发布合并成一次生成。

启动即执行

触发 Skill 后，立即进入工作流并执行当前可安全完成的步骤，不要只复述流程、列菜单或让用户自己拼命令。

先运行 node scripts/doctor.mjs --json 检查基础能力。定位或创建本次生产包，检查已有文件、设备、运行时和当前状态；没有生产包时运行 node scripts/create-package.mjs --dir <目录> --input-mode <类型> --summary <摘要>，不要临时拼接一套不可复用目录。
把用户现有输入写入 video-brief.json，明确缺失项，并继续执行到下一个真实人工门禁。
可逆的本地检查、建目录、生成合同对象和校验应主动执行。安装依赖、下载大模型或需要额外系统权限时，说明体积、目录和用途后发起所需批准；获准后继续，不要退回成教程。
只有授权/权利不明、核心事实待核验、口播确认、声音所有者选声、整片审核和发布授权等人工门禁才暂停。
每次暂停或交付都报告：当前阶段 / 已完成动作 / 产物路径 / 校验结果 / 需要用户做的一个决定 / 批准后下一步。

用户说“帮我做成视频”代表持续推进到下一个人工门禁；用户明确要求本人克隆声音且没有可用 Profile 时，按下文时钟 A 先执行本地声音建档，然后自动回到时钟 B。不要把“给一句开始话术”当作完成。

读取所需合同

先读 references/input-routing.md，把用户输入整理为 VideoBrief。
设计内容时读 references/content-contract.md。
选择画幅和分镜时读 references/visual-routing.md。
使用声音、渲染或报告状态前读 references/production-gates.md。
只有用户要求克隆或复用克隆声音时，才读 references/voice-cloning.md。
进入画面与渲染阶段时读 references/rendering-adapter.md。如果当前项目没有渲染适配器，继续交付内容、声音、字幕和 video-unit.json，但不得声称已经可以生成正式 MP4。
assets/example-package/ 只用于理解完整对象和测试，不作为新项目直接改写；需要首次本地声纹建档时，再复制 assets/voice-clone-starter/。

使用两条时钟

时钟 A：低频声音能力建立

仅在用户明确选择克隆声音且没有可用 VoiceProfile 时执行：

text

授权与私有范围
→ 参考录音和准确逐字稿
→ 三个校准候选
→ 机器 QA
→ 声音所有者选择
→ production-pilot VoiceProfile

这条链通常只在首次建档、参考或模型漂移、授权范围变化时重跑。它先于完整视频生产，但不生成本次正式口播。

时钟 B：每条视频自己的生产

每个视频项目都执行：

text

VideoBrief
→ ContentDecision
→ VideoContentPlan
→ 口播人工确认
→ 本次 VoiceRun 或其他配音
→ 正式时序
→ 视觉预检
→ 渲染与技术检查
→ 整片人工审核
→ 发布候选

如果已有可用声音档案，在项目开始时做一次 preflight，口播确认后再生成本次三个候选。不要在口播未冻结时提前生成正式音频。

执行工作流

1. 建立 `video-brief.json`

识别 idea、article、outline、script、source-pack 或 audio 输入。记录受众、期望变化、来源、权利、证据成熟度、时长/画幅偏好和声音意图。

用户只有想法时，协助展开方向，但把假设与待核验事实写入 verificationNeeds；不要编造个人经历、数据或案例。

2. 检查声音依赖

none、human 或普通 synthetic：按相应合同继续。
cloned 且已有 Profile：立即 preflight；漂移则阻断。
cloned 且没有 Profile：读取 references/voice-cloning.md，先做设备与本地模型预检；缺少模型时按该参考执行下载与锁定，随后走时钟 A，再自动进入完整生产。

3. 建立 `content-decision.json`

根据输入成熟度生成 2–6 个候选，每个候选只回答一个问题，包含核心判断、观众动作、来源锚点、待核验项、时长建议和画幅建议。一次只推荐一个；保留其余候选。

4. 建立 `video-content-plan.json`

按内容密度选择时长：

quick：35–50 秒，一个纠偏或动作；
standard：60–85 秒，一个机制、比较或诊断；
deep：90–120 秒，一个带证据的案例；
course-master：130–180 秒，只用于一个需要 3–5 个相互依赖章节的问题。

每段绑定来源、时间预算、口播职责、情绪和唯一视觉任务。先建立具体冲突，再引入术语；结尾给出动作或边界。

5. 冻结内容和口播

向用户展示主问题、核心判断、事实边界、时长、画幅和完整口播。content_plan_reviewed 与 narration_reviewed 未通过时，不生成本次克隆配音，也不做完整渲染。

6. 生成本次声音

克隆声音时先重新 preflight，再按认知章节整段生成三个候选。机器淘汰坏音频；声音所有者明确选择其中一个。本次选择只批准该 VoiceRun，不批准整片或发布。

7. 建立正式时序与 `video-unit.json`

把已审内容和选定声音翻译成连续 beat。每个 beat 只使用一个 visualJob：conflict、mechanism、comparison、evidence、action 或 conclusion。

估算字幕只能用于草案。使用转写或人工对齐后，才能把 timing_ready 标为通过。

8. 预览、渲染与检查

先检查当前项目是否存在可用的 Remotion、剪辑工程或其他渲染适配器。存在时，先检查开场、核心解释、证据/动作和结尾代表帧，再渲染完整视频；检查尺寸、帧率、编码、音频、字幕范围、缺失资产和隐私残留。不存在时，明确报告 rendering_adapter_required，保留已完成产物，不得把视觉计划写成已经生成成片。

9. 记录真实状态

分别记录 local_package、review_candidate、release_candidate，以及各平台 draft、previewed、scheduled、published。自动校验、文件存在、本人选声和整片发布是不同事实。

校验生产包

在 Skill 目录运行：

bash

node scripts/validate-package.mjs --dir <生产包>

加 --json 获取机器可读结果。修复错误后再推进状态；警告必须在交付说明中解释。

停止条件

遇到以下情况时停止并报告精确阻塞点：

用户意图、输入类型或权利边界不明确；
待核验事实会改变核心结论；
请求时长会删除结论边界；
声音授权、Profile、模型、参考或哈希漂移；
口播未审却准备生成本次克隆音频；
估算字幕被当成正式时序；
渲染命令结束但目标文件不存在；
自动检查被用来推断人工批准。

保留已完成对象，从失败阶段恢复，不要重做整条链。

Files

SKILL.md and 31 other files (scripts, references, assets) in make-ai-video of wanghui2323/ai-video-maker.

SKILL.md
agents/openai.yaml
assets/example-package/captions.json
assets/example-package/content-decision.json
assets/example-package/narration-and-rhythm.md
assets/example-package/source-notes.md
assets/example-package/video-brief.json
assets/example-package/video-content-plan.json
assets/example-package/video-unit.json
assets/example-package/workflow-state.json
assets/voice-clone-starter/gitignore.snippet
assets/voice-clone-starter/narration.txt
assets/voice-clone-starter/reference-transcript.txt
assets/voice-clone-starter/voice-consent.json
assets/voice-clone-starter/voice-provider.json
references/content-contract.md
… and 16 more

Open the folder on GitHubat commit 1e6d869

Compare with similar skills

AI Video Production Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AI Video Production Assistant compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
AI Video Production Assistant this skillwanghui2323/ai-video-maker	101	—	~924	Automated safety check: Pass	MIT	1 mo ago
Ergo Remotion Videoitwanger/toBeBetterJavaer	18k	—	~1.1k	Automated safety check: Pass	None	today
Media Genclacky-ai/openclacky	1.2k	—	~7.3k	Automated safety check: Pass	MIT	today
Stage EditOrkas-AI/Orkas-VideoStudio	499	—	~2.4k	Automated safety check: Pass	MIT	18 days ago
Pneuma Clipcraftpandazki/pneuma-skills	161	—	~7.5k	Automated safety check: Notes	MIT	yesterday
Clean Audiohassancs91/claude-youtube-editor	328	—	~1.8k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Ergo Remotion Video
itwanger/toBeBetterJavaer
把口播稿做成二哥风格的 Remotion 视频，包括整理视频用稿、火山 TTS 配音、音画对齐、逐章动画预览和导出带配音的 MP4。用户说“做视频”“口播稿转视频”“Remotion”“继续做下一章”“出片”“渲染”“改读音”“配音读错了”，或给出 docs/src/ai/video/ 下的稿子要做成视频时使用。共享工具、配置和素材在…
18k GitHub stars~1.1k tokensUpdated today
Media & CreativeAuto-check passed
Media Gen
clacky-ai/openclacky
Generate or edit images, videos, or audio in the current task.
1.2k GitHub stars~7.3k tokensUpdated today
Media & CreativeAuto-check passed
Stage Edit
Orkas-AI/Orkas-VideoStudio
Intelligent editing of real user-supplied footage—understand it with transcript/inspected-frame/scene/silence/quality evidence, then choose deterministic timeline operations or a constrained…
499 GitHub stars~2.4k tokensUpdated 18 days ago
Media & CreativeAuto-check passed
Pneuma Clipcraft
pandazki/pneuma-skills
AI-orchestrated video production on @pneuma-craft. An agent skill from pandazki/pneuma-skills.
161 GitHub stars~7.5k tokensUpdated yesterday
Media & CreativeAuto-check: notes
Clean Audio
hassancs91/claude-youtube-editor
Voice/audio cleanup step of the AI Video Editor pipeline — diagnose a video's background noise, pick the right denoise method, and produce a cleaned master (voice isolated, levels preserved, video…
328 GitHub stars~1.8k tokensUpdated 1 mo ago
Media & CreativeAuto-check passed
Video Director
Jamailar/Beav
Canonical entrypoint for every AI chat request that asks to make, generate, plan, or edit a video, including promotional films, ads, short videos, product videos, reference-image videos…
1.8k GitHub stars~9.6k tokensUpdated yesterday
Media & CreativeAuto-check passed

Questions about AI Video Production Assistant

What does AI Video Production Assistant do?

Turns an idea, article, outline or audio file into a sourced, reviewable AI video, tracking whether narration uses a human, synthetic or cloned voice. Runs a diagnostic script on activation to check what already exists in the current production package, then writes whatever the user has provided into a video brief and keeps moving forward until it reaches the next real approval point that needs a human decision, rather than just listing steps or handing commands back to the user. Reversible local actions such as checking files, creating folders, and validating the brief proceed on their own; installing dependencies or downloading a large voice model requires explaining size and purpose first and getting approval.

When should I use AI Video Production Assistant?

AI Video Production Assistant fits situations like: turning a written idea or article into a planned video with narration and visuals; checking current production status before resuming an in-progress video; setting up a cloned voice profile before using it in a video; reviewing a locked content plan and narration before rendering starts.

How do I install AI Video Production Assistant in Claude Code?

Run `npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a claude-code`. Or copy the skill folder (make-ai-video in wanghui2323/ai-video-maker) into .claude/skills/make-ai-video in your project. Claude Code loads it when a task matches its description.

How do I install AI Video Production Assistant in Codex?

Run `npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a codex`. Or copy the skill folder (make-ai-video in wanghui2323/ai-video-maker) into .agents/skills/make-ai-video in your project. Codex loads it when a task matches its description.

Can I use AI Video Production Assistant in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wanghui2323/ai-video-maker --skill make-ai-video -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/make-ai-video, .gemini/skills/make-ai-video, .github/skills/make-ai-video and .opencode/skills/make-ai-video in your project.

What does AI Video Production Assistant need to run?

Going by SKILL.md and its folder, AI Video Production Assistant needs the command-line tools its instructions call (node). Our summary lists: Node.js, to run the bundled production scripts.

Does AI Video Production Assistant access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI Video Production Assistant safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does AI Video Production Assistant use?

AI Video Production Assistant is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Video Production Assistant use?

About 924 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.7k tokens, read only when the agent opens those files.

What are the alternatives to AI Video Production Assistant?

Skills that share tags, products or a category with AI Video Production Assistant: Ergo Remotion Video (itwanger/toBeBetterJavaer, 18k stars), Media Gen (clacky-ai/openclacky, 1.2k stars), Stage Edit (Orkas-AI/Orkas-VideoStudio, 499 stars) and Pneuma Clipcraft (pandazki/pneuma-skills, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Video Production Assistant?

wanghui2323 (a GitHub user) maintains it in wanghui2323/ai-video-maker, which has 101 GitHub stars. The repository was last updated on August 16, 2026.

Source: wanghui2323/ai-video-maker on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install AI Video Production Assistant

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

AI 视频制作助手

启动即执行

读取所需合同

使用两条时钟

时钟 A：低频声音能力建立

时钟 B：每条视频自己的生产

执行工作流

1. 建立 video-brief.json

2. 检查声音依赖

3. 建立 content-decision.json

4. 建立 video-content-plan.json

5. 冻结内容和口播

6. 生成本次声音

7. 建立正式时序与 video-unit.json

8. 预览、渲染与检查

9. 记录真实状态

校验生产包

停止条件

Files

Compare with similar skills

Similar skills

Ergo Remotion Video

Media Gen

Stage Edit

Pneuma Clipcraft

Clean Audio

Video Director

Related

Questions about AI Video Production Assistant

1. 建立 `video-brief.json`

3. 建立 `content-decision.json`

4. 建立 `video-content-plan.json`

7. 建立正式时序与 `video-unit.json`