Agent skill

Narrator AI CLI

by NarratorAI-Studio in NarratorAI-Studio/narrator-ai-cli

Create AI-narrated film/drama commentary videos via CLI. An agent skill from NarratorAI-Studio/narrator-ai-cli.

Install Narrator AI CLI

skills CLI

$ npx skills add NarratorAI-Studio/narrator-ai-cli --skill narrator-ai-cli -a claude-code

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

GitHub CLI

$ gh skill install NarratorAI-Studio/narrator-ai-cli narrator-ai-cli --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/NarratorAI-Studio/narrator-ai-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills .claude/skills/narrator-ai-cli && 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 "narrator-ai-cli" agent skill from https://github.com/NarratorAI-Studio/narrator-ai-cli/tree/main/.claude/skills into .claude/skills/narrator-ai-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrator-ai-cli", 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/NarratorAI-Studio/narrator-ai-cli/tree/main/.claude/skills

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 NarratorAI-Studio/narrator-ai-cli --skill narrator-ai-cli -a codex

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

GitHub CLI

$ gh skill install NarratorAI-Studio/narrator-ai-cli narrator-ai-cli --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/NarratorAI-Studio/narrator-ai-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills .agents/skills/narrator-ai-cli && 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 "narrator-ai-cli" agent skill from https://github.com/NarratorAI-Studio/narrator-ai-cli/tree/main/.claude/skills into .agents/skills/narrator-ai-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrator-ai-cli", 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 NarratorAI-Studio/narrator-ai-cli --skill narrator-ai-cli -a cursor

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

GitHub CLI

$ gh skill install NarratorAI-Studio/narrator-ai-cli narrator-ai-cli --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/NarratorAI-Studio/narrator-ai-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills .cursor/skills/narrator-ai-cli && 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 "narrator-ai-cli" agent skill from https://github.com/NarratorAI-Studio/narrator-ai-cli/tree/main/.claude/skills into .cursor/skills/narrator-ai-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrator-ai-cli", 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/NarratorAI-Studio/narrator-ai-cli.git --path .claude/skills

--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 NarratorAI-Studio/narrator-ai-cli --skill narrator-ai-cli -a gemini-cli

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

GitHub CLI

$ gh skill install NarratorAI-Studio/narrator-ai-cli narrator-ai-cli --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/NarratorAI-Studio/narrator-ai-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills .gemini/skills/narrator-ai-cli && 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 "narrator-ai-cli" agent skill from https://github.com/NarratorAI-Studio/narrator-ai-cli/tree/main/.claude/skills into .gemini/skills/narrator-ai-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrator-ai-cli", 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 NarratorAI-Studio/narrator-ai-cli narrator-ai-cli

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 NarratorAI-Studio/narrator-ai-cli --skill narrator-ai-cli -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/NarratorAI-Studio/narrator-ai-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills .github/skills/narrator-ai-cli && 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 "narrator-ai-cli" agent skill from https://github.com/NarratorAI-Studio/narrator-ai-cli/tree/main/.claude/skills into .github/skills/narrator-ai-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrator-ai-cli", 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 NarratorAI-Studio/narrator-ai-cli --skill narrator-ai-cli -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 NarratorAI-Studio/narrator-ai-cli narrator-ai-cli --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/NarratorAI-Studio/narrator-ai-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills .opencode/skills/narrator-ai-cli && 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 "narrator-ai-cli" agent skill from https://github.com/NarratorAI-Studio/narrator-ai-cli/tree/main/.claude/skills into .opencode/skills/narrator-ai-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrator-ai-cli", 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: narrator-ai-cli
GitHub stars: 137
Token cost: ~3.7k tokens
SKILL.md length: 735 words
Files: 2
Skills in repo: 1
Repo updated: Jul 27, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Create AI-narrated film/drama commentary videos via CLI. An agent skill from NarratorAI-Studio/narrator-ai-cli.

Works in 10 steps: Get learning_model_id → Generate Writing → Generate Clip Data → …
Creating narration videos
SKILL.md covers Prerequisites, Core Rules, Decision Points (ASK USER) and Workflow Path 1: 二创文案, plus 5 more sections
Reaches openapi.jieshuo.cn and ceex7z9m67.feishu.cn

What it does

Narrator AI CLI is an agent skill from NarratorAI-Studio/narrator-ai-cli. Create AI-narrated film/drama commentary videos via CLI. Two workflow paths (Original & Adapted narration), 93 movies, 146 BGM tracks, 63 dubbing voices in 11 languages, 90+ narration templates. Use when creating narration videos, film commentary, short drama dubbing, or video production.

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files.

It sits in Media & Creative, covering Text to speech and voice. It works with Python. The repository describes itself as: AI 解说大师 — CLI 客户端；用于终端调用视频解说生成 API. The licence is MIT.

When your agent uses it

Creating narration videos
Film commentary
Short drama dubbing
Video production

Example prompts

“/narrator-ai-cli”

Requirements

A credential in NARRATOR_APP_KEY

Workflow steps

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

Get learning_model_id
Generate Writing
Generate Clip Data
Video Composing
(Optional): Magic Video
Prepare
Fast Writing (原创文案)
Fast Clip Data
Video Composing
(Optional): Magic Video

What it can do on your machine

Read from SKILL.md and the folder at commit 2d8bb14. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- openapi.jieshuo.cn
- ceex7z9m67.feishu.cn
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

Narrator AI CLI loads about 3.7k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 735 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~76
When it runs · the whole SKILL.md, loaded when a task matches: ~3.7k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from NarratorAI-Studio/narrator-ai-cli at commit 2d8bb14, republished under its MIT licence (© NarratorAI-Studio). 735 words, ~3,742 tokens.

Download SKILL.mdSave it as .claude/skills/narrator-ai-cli/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: narrator-ai-cli
description: Create AI-narrated film/drama commentary videos via CLI. Two workflow paths (Original & Adapted narration), 93 movies, 146 BGM tracks, 63 dubbing voices in 11 languages, 90+ narration templates. Use when creating narration videos, film commentary, short drama dubbing, or video production.
version: 1.0.0
license: MIT
user-invocable: true
tags: video-narration, film-commentary, ai-video, short-drama, content-creation, dubbing, tts, video-production

narrator-ai-cli Skill

You have access to narrator-ai-cli, a CLI tool for the Narrator AI video narration API. Always use --json flag for all commands to get structured output you can parse.

Prerequisites

The CLI must be configured before use. Check with:

bash

narrator-ai-cli config show

If not configured, set up with:

bash

narrator-ai-cli config set app_key <app_key>

Server defaults to https://openapi.jieshuo.cn — no need to configure.

Need an app_key or help with setup? Contact us to get started:

📧 Email: merlinyang@gridltd.com
💬 WeChat:

Image: 联系客服

Core Rules

ALWAYS use --json for all commands. Parse the JSON output to extract values for next steps.
NEVER fabricate data — never guess file IDs, movie info, or voice IDs. Always query from CLI commands.
ASK user to choose when there are multiple options (pre-built vs custom, which template, which movie, etc.).
Poll task status — tasks are async. After creation, poll with narrator-ai-cli task query <task_id> --json until status is 2 (success) or 3 (failed).
video-composing order_num source differs by path:
- Standard Path: use generate-writing's task_order_num (NOT clip-data's)
- Fast Path: use fast-clip-data's task_order_num
dubbing list returns id and type — pass id as dubbing, pass type as dubbing_type. They are two separate fields.
negative_oss_key = video_oss_key — always set negative_oss_key to the same value as video_oss_key in episodes_data.
search-movie may take 60+ seconds — this is normal (Gradio backend).

Decision Points (ASK USER)

Before starting any workflow, you need to help the user make the following choices. Present the options and let the user decide. Do NOT pick for them.

Decision 1: Which workflow path?

ASK: "请选择工作流路径："

二创文案: 爆款学习 → 生成解说文案 → 生成剪辑数据 → 合成视频 → 视觉模板(可选)
- Based on existing reference video style, generates adapted narration
- Suitable when: user wants to recreate content based on reference material
原创文案 (faster & cheaper): 快速文案 → 快速剪辑数据 → 合成视频 → 视觉模板(可选)
- Generates original narration from movie info + narration template
- Three sub-modes: 热门影视(hot drama), 原声混剪(original mix), 冷门/新剧(new drama)
- Suitable when: user wants original narration, faster speed, lower cost

Decision 2: Narration style — pre-built template or custom learning?

ASK: "解说风格：使用预置模板还是自定义学习？"

Option A: Pre-built template (recommended, 90+ templates across 12 genres)
bash
```
narrator-ai-cli task narration-styles --json
# or filter: narrator-ai-cli task narration-styles --genre <genre> --json
```
Show the list to user, let them pick one. The id field is the learning_model_id.
Option B: Custom learning (popular-learning task, Standard Path only) Requires user to provide a reference video + SRT. The output learning_model_id is used in generate-writing.

Decision 3: Movie source files — pre-built material or user upload?

ASK: "电影素材：使用预置素材还是自己上传的文件？"

Option A: Pre-built materials (93 movies ready to use)
bash
```
narrator-ai-cli material list --json
# or search: narrator-ai-cli material list --search "<movie_name>" --json
# or filter: narrator-ai-cli material list --genre <genre> --json
```
Show results to user. Each entry has video_id and srt_id.
- Use video_id as video_oss_key AND negative_oss_key
- Use srt_id as srt_oss_key

Option B: User's uploaded files

bash

narrator-ai-cli file list --json
# or search: narrator-ai-cli file list --search "<keyword>" --json
# or transfer by link: narrator-ai-cli file transfer --link "<url>" --json

User picks video and SRT files from their cloud storage.

Show full SKILL.md (336 more words)Show less

Decision 4: BGM — pre-built track or user upload?

ASK: "背景音乐：使用预置BGM还是自己上传的音频？"

Option A: Pre-built BGM (146 tracks)

bash

narrator-ai-cli bgm list --json
# or search: narrator-ai-cli bgm list --search "<keyword>" --json

Show results to user. The id field is the bgm parameter value.

Option B: User's uploaded audio
bash
```
narrator-ai-cli file list --json
```
User picks an audio file. Use its file_id as the bgm parameter.

Decision 5: Dubbing voice — which voice and language?

ASK: "配音角色：请选择配音语言和角色"

bash

# First show available languages
narrator-ai-cli dubbing languages --json

# Then list voices for chosen language
narrator-ai-cli dubbing list --lang <language> --json

# Or filter by genre recommendation
narrator-ai-cli dubbing list --tag <genre_tag> --json

Show results to user. From the selected voice:

id field → pass as dubbing parameter
type field → pass as dubbing_type parameter

There is no "custom upload" option for dubbing — always pick from the pre-built list. (Users can create custom voices via voice-clone task separately.)

Decision 6: Visual template (optional)?

ASK: "是否需要应用视觉模板？（可选步骤）"

Yes: Pick a template
bash
```
narrator-ai-cli task templates --json
```
Show results to user, let them pick. The name field goes into template_name list.
No: Skip magic-video step.

Workflow Path 1: 二创文案

popular-learning(optional) -> generate-writing -> clip-data -> video-composing -> magic-video(optional)

Step 1: Get learning_model_id

Based on Decision 2:

bash

# Option A: Pre-built template (recommended)
narrator-ai-cli task narration-styles --json
# -> user picks one -> learning_model_id = selected item's "id"

# Option B: Custom learning
narrator-ai-cli task create popular-learning --json -d '{
  "video_srt_path": "<srt_file_id from material or file list>",
  "video_path": "<video_file_id from material or file list>"
}'
# Poll until done -> extract learning_model_id from results

Step 2: Generate Writing

bash

# 2a. Search movie info (for confirmed_movie_json / story_info)
narrator-ai-cli task search-movie "<movie_name>" --json
# Show 3 results to user, let them pick one

# 2b. Get source files (based on Decision 3)
# Option A: narrator-ai-cli material list --search "<movie_name>" --json
# Option B: narrator-ai-cli file list --json
# -> user picks video and SRT files

# 2c. Create task
narrator-ai-cli task create generate-writing --json -d '{
  "learning_model_id": "<from step 1>",
  "learning_srt": "",
  "native_video": "",
  "native_srt": "",
  "playlet_name": "<movie_name>",
  "playlet_num": "1",
  "target_platform": "抖音",
  "vendor_requirements": "",
  "task_count": 1,
  "target_character_name": "<ASK user for main character name>",
  "story_info": "",
  "episodes_data": [{"video_oss_key": "<video_id>", "srt_oss_key": "<srt_id>", "negative_oss_key": "<video_id>", "num": 1}]
}'
# Poll -> extract task_order_num and results.file_ids[0]

Step 3: Generate Clip Data

bash

# 3a. Get BGM (based on Decision 4)
# Option A: narrator-ai-cli bgm list --json -> user picks -> bgm = selected "id"
# Option B: narrator-ai-cli file list --json -> user picks audio -> bgm = selected "file_id"

# 3b. Get dubbing voice (Decision 5)
# narrator-ai-cli dubbing list --lang <lang> --json -> user picks
# -> dubbing = selected "id", dubbing_type = selected "type"

# 3c. Create task
narrator-ai-cli task create clip-data --json -d '{
  "order_num": "<task_order_num from step 2>",
  "bgm": "<from Decision 4>",
  "dubbing": "<id from Decision 5>",
  "dubbing_type": "<type from Decision 5>"
}'
# Poll -> extract results.file_ids[0]

Step 4: Video Composing

IMPORTANT: order_num is from step 2 (generate-writing), NOT step 3 (clip-data).

bash

narrator-ai-cli task create video-composing --json -d '{
  "order_num": "<task_order_num from step 2 (generate-writing)>",
  "bgm": "<same bgm as step 3>",
  "dubbing": "<same dubbing as step 3>",
  "dubbing_type": "<same dubbing_type as step 3>"
}'
# Poll -> extract video URLs from results

Step 5 (Optional): Magic Video

Based on Decision 6:

bash

# List visual templates
narrator-ai-cli task templates --json
# -> user picks template name

# Apply template
narrator-ai-cli task create magic-video --json -d '{
  "task_id": "<task_id from step 4>",
  "template_name": ["<selected template name>"]
}'

Workflow Path 2: 原创文案 (faster & cheaper)

search-movie -> fast-writing -> fast-clip-data -> video-composing -> magic-video(optional)

Step 0: Prepare

bash

# Get narration style template (Decision 2)
narrator-ai-cli task narration-styles --json
# -> user picks one -> learning_model_id

# Search movie info (required for target_mode=1)
narrator-ai-cli task search-movie "<movie_name>" --json
# -> show 3 results, user picks one -> confirmed_movie_json

Step 1: Fast Writing (原创文案)

ASK user to choose a mode:

Mode 1 - 热门影视 (Hot Drama): generates original narration from movie info. Requires confirmed_movie_json from search-movie.
Mode 2 - 原声混剪 (Original Mix): mixes original audio with narration. Requires episodes_data[{srt_oss_key, num}].
Mode 3 - 冷门/新剧 (New/Niche Drama): for lesser-known content. Requires episodes_data[{srt_oss_key, num}].

bash

# Mode 1 example (most common):
narrator-ai-cli task create fast-writing --json -d '{
  "learning_model_id": "<from Decision 2>",
  "target_mode": "1",
  "playlet_name": "<movie_name>",
  "model": "flash",
  "language": "Chinese (中文)",
  "perspective": "third_person",
  "confirmed_movie_json": <user-selected search result>
}'

# Mode 2/3 example:
narrator-ai-cli task create fast-writing --json -d '{
  "learning_model_id": "<from Decision 2>",
  "target_mode": "2",
  "playlet_name": "<movie_name>",
  "episodes_data": [{"srt_oss_key": "<srt_file_id>", "num": 1}]
}'
# Poll -> extract task_id and results.file_ids[0]

Step 2: Fast Clip Data

bash

# 2a. Get BGM (Decision 4)
# Option A: narrator-ai-cli bgm list --json -> user picks
# Option B: narrator-ai-cli file list --json -> user picks audio

# 2b. Get dubbing voice (Decision 5)
# narrator-ai-cli dubbing list --lang <lang> --json -> user picks

# 2c. Get source files (Decision 3)
# Option A: narrator-ai-cli material list --search "<movie_name>" --json
# Option B: narrator-ai-cli file list --json

# 2d. Create task
narrator-ai-cli task create fast-clip-data --json -d '{
  "task_id": "<task_id from step 1>",
  "file_id": "<results.file_ids[0] from step 1>",
  "bgm": "<from Decision 4>",
  "dubbing": "<id from Decision 5>",
  "dubbing_type": "<type from Decision 5>",
  "episodes_data": [{"video_oss_key": "<video_id>", "srt_oss_key": "<srt_id>", "negative_oss_key": "<video_id>", "num": 1}]
}'
# Poll -> extract task_order_num

Step 3: Video Composing

IMPORTANT: In 原创文案 path, order_num comes from fast-clip-data's task_order_num.

bash

narrator-ai-cli task create video-composing --json -d '{
  "order_num": "<task_order_num from step 2 (fast-clip-data)>",
  "bgm": "<same bgm as step 2>",
  "dubbing": "<same dubbing as step 2>",
  "dubbing_type": "<same dubbing_type as step 2>"
}'
# Poll -> extract video URLs from results

Step 4 (Optional): Magic Video

Based on Decision 6:

bash

narrator-ai-cli task templates --json
# -> user picks template

narrator-ai-cli task create magic-video --json -d '{
  "task_id": "<task_id from step 3>",
  "template_name": ["<selected template name>"]
}'

Standalone Tasks

bash

# Voice Clone — clone a voice from audio sample
narrator-ai-cli task create voice-clone --json -d '{"audio_file_id": "<file_id from file list>"}'

# Text to Speech — convert text using cloned voice
narrator-ai-cli task create tts --json -d '{"voice_id": "<id>", "audio_text": "text"}'

Utility Commands

bash

# Account
narrator-ai-cli user balance --json

# Tasks
narrator-ai-cli task list --json
narrator-ai-cli task list --status 2 --type 9 --json   # filter: status 0-4, type 1-10
narrator-ai-cli task query <task_id> --json
narrator-ai-cli task budget --json -d '{...}'           # estimate points
narrator-ai-cli task verify --json -d '{...}'           # verify materials

# Writing management
narrator-ai-cli task get-writing --task-id <id> --file-id <id> --json
narrator-ai-cli task save-writing --json -d '{"task_id":"...", "file_id":"...", "content":[{"type":"解说","text":"..."}]}'

# Files (user's uploaded files)
narrator-ai-cli file list --json
narrator-ai-cli file list --search "<keyword>" --json
narrator-ai-cli file upload ./file.mp4 --json
narrator-ai-cli file transfer --link "<url>" --json          # transfer by HTTP/Baidu/PikPak link
narrator-ai-cli file info <file_id> --json
narrator-ai-cli file download <file_id> --json
narrator-ai-cli file storage --json
narrator-ai-cli file delete <file_id> --json

# Pre-built Resources
narrator-ai-cli task narration-styles --json            # 90+ narration style templates
narrator-ai-cli task narration-styles --genre <g> --json
narrator-ai-cli material list --json                     # 93 pre-built movies (video + SRT)
narrator-ai-cli material list --genre <g> --json
narrator-ai-cli material list --search "<name>" --json
narrator-ai-cli material genres --json
narrator-ai-cli bgm list --json                          # 146 pre-built BGM tracks
narrator-ai-cli bgm list --search "<name>" --json
narrator-ai-cli dubbing list --json                      # 63 pre-built dubbing voices
narrator-ai-cli dubbing list --lang <lang> --json
narrator-ai-cli dubbing list --tag <tag> --json
narrator-ai-cli dubbing languages --json
narrator-ai-cli dubbing tags --json
narrator-ai-cli task templates --json                    # visual templates (magic-video)
narrator-ai-cli task search-movie "<name>" --json        # movie info search

# All pre-built resources can be previewed at:
# https://ceex7z9m67.feishu.cn/wiki/WLPnwBysairenFkZDbicZOfKnbc

Task Status Codes

0 = init
1 = in_progress
2 = success (done, extract results)
3 = failed (check error_message_slug)
4 = cancelled

Error Codes

10001 = failed (generic)
10004 = invalid app key

10009 = insufficient balance — notify the user:

⚠️ 账户余额不足，请联系客服充值或获取 App Key：
📧 Email: merlinyang@gridltd.com

Then display: ![联系客服](imgs/contact.png)

10010 = task not found
60000 = retryable error (retry the operation)

Files

SKILL.md and 1 other file in .claude/skills of NarratorAI-Studio/narrator-ai-cli.

SKILL.md
imgs/contact.png

Open the folder on GitHubat commit 2d8bb14

Compare with similar skills

Narrator AI CLI 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.

Narrator AI CLI compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Narrator AI CLI this skillNarratorAI-Studio/narrator-ai-cli	137	—	~3.7k	Automated safety check: Pass	MIT	2 mo ago
Edu Math Videowy51ai/edulab	1.4k	—	~2.5k	Automated safety check: Notes	Apache-2.0	11 days ago
Book Video Factorybytec-ai/book-video-factory	322	—	~1.4k	Automated safety check: Notes	None	2 mo ago
AI Text To Speechgodot-fun/gai	182	—	~2k	Automated safety check: Pass	MIT	today
Iflytek Voiceclone Ttsiflytek/iFly-Skills	209	—	~2.1k	Automated safety check: Pass	Apache-2.0	yesterday
U2 TtsLeoYeAI/openclaw-master-skills	2.2k	—	~4.7k	Automated safety check: Notes	MIT	2 mo ago

Similar skills

Edu Math Video
wy51ai/edulab
A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a math problem (数学题, geometry, algebra, functions, motion/行程 problems), from a problem screenshot…
1.4k GitHub stars~2.5k tokensUpdated 11 days ago
Media & CreativeAuto-check: notes
Book Video Factory
bytec-ai/book-video-factory
通用的多账号图书短视频生产工作流。用于用户希望建立图书号项目目录、配置账号级片头/声音/BGM/视觉规范，或只提供一本书后依次完成资料研究、口播稿、分镜、图片、配音、字幕、预览与成片导出。适用于新建工作区、批量管理多个账号、继续已有单书任务和检查生产状态；不绑定特定研究、图片、TTS、转录或视频渲染供应商。
322 GitHub stars~1.4k tokensUpdated 2 mo ago
Media & CreativeAuto-check: notes
AI Text To Speech
godot-fun/gai
Zero-shot text-to-speech with voice cloning via IndexTTS2 (index-tts).
182 GitHub stars~2k tokensUpdated today
Media & CreativeAuto-check passed
Iflytek Voiceclone Tts
iflytek/iFly-Skills
A skill your agent uses when user asks to clone a voice, train a custom voice model, or synthesize speech with a cloned voice.
209 GitHub stars~2.1k tokensUpdated yesterday
Media & CreativeAuto-check passed
U2 Tts
LeoYeAI/openclaw-master-skills
Text-to-speech conversion using UniSound's TTS WebSocket API for generating high-quality Chinese Mandarin audio from text.
2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
Media & CreativeAuto-check: notes
MoneyPrinterTurbo Video Generator
harry0703/MoneyPrinterTurbo
Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.
129k GitHub stars~2.1k tokensUpdated today
Media & CreativeAuto-check: warnings

Works with

Python

Questions about Narrator AI CLI

What does Narrator AI CLI do?

Create AI-narrated film/drama commentary videos via CLI. An agent skill from NarratorAI-Studio/narrator-ai-cli. Narrator AI CLI is an agent skill from NarratorAI-Studio/narrator-ai-cli. Create AI-narrated film/drama commentary videos via CLI.

When should I use Narrator AI CLI?

Narrator AI CLI fits situations like: creating narration videos; film commentary; short drama dubbing; video production.

How do I install Narrator AI CLI in Claude Code?

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

How do I install Narrator AI CLI in Codex?

Run `npx skills add NarratorAI-Studio/narrator-ai-cli --skill narrator-ai-cli -a codex`. Or copy the skill folder (.claude/skills in NarratorAI-Studio/narrator-ai-cli) into .agents/skills/narrator-ai-cli in your project. Codex loads it when a task matches its description.

Can I use Narrator AI CLI 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 NarratorAI-Studio/narrator-ai-cli --skill narrator-ai-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/narrator-ai-cli, .gemini/skills/narrator-ai-cli, .github/skills/narrator-ai-cli and .opencode/skills/narrator-ai-cli in your project.

What does Narrator AI CLI need to run?

SKILL.md names no scripts, command-line tools or credentials: Narrator AI CLI is instructions for the agent only. Our summary lists: A credential in NARRATOR_APP_KEY.

Does Narrator AI CLI access the network?

SKILL.md names 2 domains. In commands or code: openapi.jieshuo.cn and ceex7z9m67.feishu.cn; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Narrator AI CLI 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. Review the folder before installing.

What licence does Narrator AI CLI use?

Narrator AI CLI is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Narrator AI CLI use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Narrator AI CLI?

Skills that share tags, products or a category with Narrator AI CLI: Edu Math Video (wy51ai/edulab, 1.4k stars), Book Video Factory (bytec-ai/book-video-factory, 322 stars), AI Text To Speech (godot-fun/gai, 182 stars) and Iflytek Voiceclone Tts (iflytek/iFly-Skills, 209 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Narrator AI CLI?

NarratorAI-Studio (a GitHub organization) maintains it in NarratorAI-Studio/narrator-ai-cli, which has 137 GitHub stars. The repository was last updated on July 27, 2026.

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

Install Narrator AI CLI

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

narrator-ai-cli Skill

Prerequisites

Core Rules

Decision Points (ASK USER)

Decision 1: Which workflow path?

Decision 2: Narration style — pre-built template or custom learning?

Decision 3: Movie source files — pre-built material or user upload?

Decision 4: BGM — pre-built track or user upload?

Decision 5: Dubbing voice — which voice and language?

Decision 6: Visual template (optional)?

Workflow Path 1: 二创文案

Step 1: Get learning_model_id

Step 2: Generate Writing

Step 3: Generate Clip Data

Step 4: Video Composing

Step 5 (Optional): Magic Video

Workflow Path 2: 原创文案 (faster & cheaper)

Step 0: Prepare

Step 1: Fast Writing (原创文案)

Step 2: Fast Clip Data

Step 3: Video Composing

Step 4 (Optional): Magic Video

Standalone Tasks

Utility Commands

Task Status Codes

Error Codes

Files

Compare with similar skills

Similar skills

Edu Math Video

Book Video Factory

AI Text To Speech

Iflytek Voiceclone Tts

U2 Tts

MoneyPrinterTurbo Video Generator

Related

Questions about Narrator AI CLI