Narrator AI CLI Skill
A skill that teaches the agent to build narrated videos through narrator-ai-cli: source, template, music, voice, script and composing
- 3,195 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs a command line and calls an external API
- Spends paid points, and some operations are irreversible
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/narrator-ai-cli-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs a command line and calls an external API
- Spends paid points, and some operations are irreversible
This is third-party code. Review the repository files before installing.
What it does
The skill is a SKILL.md file with reference tables that tells the agent how to drive the narrator-ai-cli command line to assemble narrated videos automatically. The agent walks a chain: find or upload the source, pick background music, a voice and a narration template, generate the script and compose the final clip. It documents two routes, a fast one on original script and a standard one on adapted script, plus standalone voice cloning and text to speech. The skill requires confirming each resource choice before paid points are spent and forbids inventing movie data, taking it from the CLI response instead. The composing and API code lives in the separate narrator-ai-cli package; the skill only orchestrates its calls.
Who it is for. For creators and editors of short clips and film recaps who assemble narrated videos through an agent.
Good fit when
- You need to assemble a narrated clip from the built-in material library
- You want the agent to run the whole pipeline: source, music, voice, script and composing
- You need to clone a voice or synthesize speech as a standalone task
Not a fit when
- You have no access key to the Narrator AI service
- You need editing without calling an external paid API
Example request
Show me what movies are in the library and build a narrated clip in a comedy styleLimitations
The skill is useless without the narrator-ai-cli package and a NARRATOR_APP_KEY key, which the vendor issues on email request, and access runs on paid points, some spent irreversibly. It needs Python 3.10 or newer and the typer, httpx, pyyaml and rich dependencies. All requests go to the openapi.jieshuo.cn service, and part of the interface and references are in Chinese and English.
How to disable. Remove the narrator-ai-cli folder from the agent's skills directory. The command line package can be removed with pip uninstall narrator-ai-cli if needed.
FAQ
Where do I get the access key?
The NARRATOR_APP_KEY key is issued by the Narrator AI vendor on request to the email in the README. Access is paid and points based.
Does the skill compose the video itself?
No. Composing and API calls are done by the separate narrator-ai-cli package. The skill only tells the agent how to call its commands correctly.
Discussion
No questions or reviews yet.
Related
SkillsA skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks
A set of SKILL.md skills for short-video and content production: topic, script, voice, avatar, editing, covers and motion graphics
A skill for vidu-cli: generates Vidu video, images and speech and manages tasks, references, cloned voices and credit estimates
A skill that turns a topic into a narrated 4K video: research, script, local TTS, Remotion composition and an FFmpeg mix
video-production-skill takes an agent from script to video: slides, speech-verified narration, subtitles and a cover.
The Video by Reference skill learns style from a sample clip and builds an animated short from code with an original soundtrack
README in short
The README calls the skill a machine readable file that teaches the agent to use the narrator-ai-cli command line, and stresses that the CLI is the hands while the skill is the brain. It shows a quick start: install the package via pip, set the key and clone the repository into the agent's skills folder together with the references directory. It lists tested platforms: OpenClaw, Windsurf, Claude Code, Cursor and other markdown reading agents. The library holds roughly a hundred movies, music tracks, voices and narration templates, while SKILL.md describes the pipeline, agent rules and API error handling. MIT licensed.
README badge
Original SKILL.md
--- name: narrator-ai-cli version: "1.0.5" license: MIT description: >- AI 电影/短剧解说视频自动生成（AI 解说大师 CLI Skill）。当用户需要创建电影解说视频、短剧解说、影视二创、AI 配音旁白视频、film commentary、video narration、drama dubbing、movie narration 时触发。内置电影素材库、BGM、多语种配音、解说模板。通过 narrator-ai-cli 命令行实现：搜片→选模板→选 BGM→选配音→生成文案→合成视频的全流程自动化。CLI client for Narrator AI video narration API. user-invocable: true tags: - video-narration - film-commentary - ai-video - short-drama - content-creation - dubbing - tts - video-production --- # narrator-ai-cli — AI Video Narration CLI Skill CLI client for Narrator AI video narration API. Designed for AI agents and developers. ## Reference Index This file covers decision flow, the common workflow, and pointers. Detailed lookups live in `references/`: | Topic | File | |---|---| | Resource selection (material / BGM / dubbing / templates) | `references/resources.md` | | Full workflow steps with parameter tables and JSON examples | `references/workflows.md` | | Magic Video — optional visual template step | `references/magic-video.md` | | Polling pattern, task types, file ops, user account, error codes | `references/operations.md` |