@XAMTO_AI: There is an open-source project called narrator-ai-cli-skill. Plug it into an agent like Claude Code, and just say 'Help me make a commentary video for The Shawshank Redemption', and the AI handles everything: automatically generates commentary script without you lifting a finger, precisely matches corresponding movie clips, …

X AI KOLs Timeline Tools

Summary

Introducing an open-source project called narrator-ai-cli-skill, which can be integrated into AI agents like Claude Code. With just one sentence, users can automatically complete the entire process of creating a movie commentary video — script, voiceover, editing, background music, etc. — greatly reducing the production cost of film commentary channels.

There is an open-source project called narrator-ai-cli-skill. Plug it into an agent like Claude Code, and just say 'Help me make a commentary video for The Shawshank Redemption', and the AI handles everything: Automatically generates commentary script—no thinking required. Precisely matches corresponding movie clips—no editing required. 63 voice styles with voice cloning support—no recording required. 90+ visual templates auto-applied—no designing required. 146 BGM tracks intelligently matched—no music searching required. Directly outputs the final product—no post-production required. Built-in library of 93 classic movies, plus it calculates costs in advance. The engineering level is quite solid—not a toy project. Previously, making a film commentary channel required manual work for script, voiceover, editing, and music. Now that entire pipeline is gone. Labor costs going to zero is not an exaggeration; it's literal. If you want to start film commentary channels in bulk, this project is worth a serious look. https://github.com/NarratorAI-Studio/narrator-ai-cli-skill…
Original Article
View Cached Full Text

Cached at: 06/10/26, 07:56 PM

There’s an open-source project called narrator-ai-cli-skill that you can drop into agents like Claude Code. Just say “Make a narration video for The Shawshank Redemption,” and the AI handles everything end-to-end:

  • Auto-generates the script – no brainpower needed
  • Precisely matches movie clips – no editing required
  • 63 voice options, plus voice cloning – no recording
  • 90+ visual templates apply automatically – no design work
  • 146 background tracks matched intelligently – no searching for music
  • Delivers the final video – no post-production
  • Comes with a built-in library of 93 classic movies and even estimates costs upfront

The engineering is solid – not a toy project.

Before, running a movie narration channel meant handling scriptwriting, voiceover, editing, and music separately – each step needed a human. Now that whole chain is broken. Saying “labor cost drops to zero” isn’t an exaggeration; it’s literal.
If you want to batch-launch movie narration accounts, this project is worth a serious look.

https://github.com/NarratorAI-Studio/narrator-ai-cli-skill…


NarratorAI-Studio/narrator-ai-cli-skill

Source: https://github.com/NarratorAI-Studio/narrator-ai-cli-skill

🧠 Narrator AI CLI Skill — Teach Your AI Agent to Create Movie Narration Videos

中文文档

Install this Skill in your AI agent (OpenClaw, Windsurf, WorkBuddy, etc.), then just say “create a movie narration video” — the AI handles the rest.

What is this?

A machine-readable skill file (SKILL.md) that teaches AI agents how to use the narrator-ai-cli (https://github.com/NarratorAI-Studio/narrator-ai-cli) tool for automated video narration production.

You say: "Create a narration video for Pegasus in a comedy style" AI executes: Search movie → Select template → Choose BGM → Pick voice → Generate script → Compose video → Return download link

How CLI and Skill work together

CLI (command-line tool)Skill (capability description)
What it isA set of executable commandsInstructions that teach AI how to use those commands
AnalogyKitchen toolsA recipe book
Works alone?Yes, in terminal manuallyNo, requires CLI

In short: CLI is the hands. Skill is the brain. Together, the AI agent can produce videos end-to-end.


Quick Start

Step 1: Install the CLI tool

pip install "narrator-ai-cli @ git+https://github.com/NarratorAI-Studio/narrator-ai-cli.git"

See narrator-ai-cli (https://github.com/NarratorAI-Studio/narrator-ai-cli) for detailed installation options.

Step 2: Configure API key

narrator-ai-cli config set app_key <your_app_key>

📧 Need an API key? Email [email protected] or scan the QR code at the bottom of this page.

Step 3: Install the Skill

The skill consists of SKILL.md and the references/ directory — both are required.

Clone the repo directly into your agent’s skills folder:

OpenClaw:

mkdir -p ~/.openclaw/skills
git clone https://github.com/NarratorAI-Studio/narrator-ai-cli-skill.git \
  ~/.openclaw/skills/narrator-ai-cli

Windsurf / Claude Code:

mkdir -p /path/to/your/project/.skills
git clone https://github.com/NarratorAI-Studio/narrator-ai-cli-skill.git \
  /path/to/your/project/.skills/narrator-ai-cli

Cursor:

mkdir -p /path/to/your/project/.cursor/rules
git clone https://github.com/NarratorAI-Studio/narrator-ai-cli-skill.git \
  /path/to/your/project/.cursor/rules/narrator-ai-cli

Any markdown-reading agent:

mkdir -p /path/to/agent/skills
git clone https://github.com/NarratorAI-Studio/narrator-ai-cli-skill.git \
  /path/to/agent/skills/narrator-ai-cli

WorkBuddy / QClaw (Tencent): Upload SKILL.md and the entire references/ folder through the skill management UI, keeping the directory structure intact (references/ must remain a subfolder alongside SKILL.md — do not flatten the files).

💡 Tip: To update the skill later, just run git pull inside the cloned directory.

Step 4: Start talking!

Once installed, use natural language:

  • “Create a narration video for The Shawshank Redemption”
  • “Show me what movies are available”
  • “Make 5 narration videos for different action movies”
  • “Use a comedy template and generate a narration”


Tested Platforms

PlatformSetupStatus
OpenClawgit clone into skills directory✅ Verified
Windsurfgit clone into .skills directory✅ Verified
WorkBuddy (Tencent)Upload SKILL.md + all files in references/✅ Verified
QClaw (Tencent)Upload SKILL.md + all files in references/✅ Verified
Youdao Lobstergit clone into skills directory✅ Verified
Yuanqi AIgit clone into skills directory✅ Verified
Claude Codegit clone into project .skills directory✅ Verified
Cursorgit clone into .cursor/rules directory✅ Verified
Any markdown-skill agentgit clone repo, point agent to SKILL.md✅ Compatible

Capabilities

FeatureDetails
Two workflow pathsAdapted Narration and Original Narration
Three creation modesHot Drama / Original Mix / New Drama
Built-in resources~100 movies, 146 BGM tracks, 63 dubbing voices, 90+ narration templates
Full pipelineScript → Clip data → Video composing → Visual template
Standalone tasksVoice cloning, text-to-speech
Data flow mappingWhich output feeds into which input
Error handlingAll 18 API error codes with recommended actions
Cost estimationBudget verification before task creation

What’s in SKILL.md

SectionDescription
FrontmatterSkill metadata (name, description, requirements)
Reference IndexPointers to detailed lookup tables in references/ (resources, workflows, magic-video, operations)
Pipeline at a GlanceASCII diagram of Fast Path and Standard Path
Agent RulesMandatory rules: confirm before acting, language chain, polling pattern, etc.
PrerequisitesAssumes narrator-ai-cli is installed and NARRATOR_APP_KEY is set
Core ConceptsKey terms: file_id, task_id, task_order_num, etc.
Conversation InitiationHow to open a session and the decision sequence
Two Workflow PathsFast Path (Original Narration) vs Standard Path (Adapted Narration)
Resource Selection ProtocolBGM, dubbing, template selection order and rules
Fast PathSteps 0–4 with parameter notes
Standard PathSteps 0–5 with parameter notes
Standalone TasksVoice clone and TTS
Important Notes7 critical gotchas and best practices
Data & PrivacyAPI endpoint, file handling, credentials scope

Requirements

  • CLI: narrator-ai-cli v1.0.0+
  • Python: 3.10+
  • Dependencies: typer, httpx[socks], httpx-sse, pyyaml, rich
  • API key: Contact us to get one

Links

  • 📦 narrator-ai-cli CLI repo (https://github.com/NarratorAI-Studio/narrator-ai-cli)
  • 📖 Resource preview (Feishu Docs) (https://ceex7z9m67.feishu.cn/wiki/WLPnwBysairenFkZDbicZOfKnbc)
  • 🦞 OpenClaw agent framework (https://github.com/openclaw/openclaw)

Contact

Need an API key or help?

Contact us

License

MIT

Similar Articles

@jinchenma_ai: https://x.com/jinchenma_ai/status/2061835131107860582

X AI KOLs Timeline

The article proposes an engineering methodology based on AI Agent (Skill), suggesting that deterministic tasks be solidified into scripts to reduce new decisions made by the large model at runtime, thereby improving stability and token efficiency. Taking video subtitle processing as an example, it demonstrates a four-step engineering process.

@yhslgg: Old Yang shares another gem open-source tool—KrillinAI, 10,000 stars on GitHub, a must-see for multilingual audio/video content! In a nutshell: from video download to subtitle translation, AI dubbing, video compositing, the entire pipeline is covered, and it can even auto-generate platform covers, supporting Bilibili, Douyin, Xiaohongshu, YouTube…

X AI KOLs Timeline

KrillinAI is an open-source tool that integrates the entire workflow of video downloading, subtitle translation, AI dubbing, and video compositing. It supports context-aware translation, voice cloning, auto layout, and cover generation, and is compatible with multiple AI models, suitable for multilingual audio/video content creation and distribution.

@Russell3402: Alibaba International's open-source AI-powered fully automated short video engine, Pixelle-Video. Simply input a topic, and it automatically generates a complete short video. From copywriting and voiceovers to image selection and editing, everything is handled by AI. GitHub:

X AI KOLs Timeline

Alibaba International has open-sourced the AI-powered fully automated short video engine Pixelle-Video, allowing users to generate complete short videos—including copywriting, voiceovers, images, and editing—by simply inputting a topic.