Skip to content
mcp/skillhub

Agent Skill

Narrator AI CLI skill

narrator-ai-cliNarratorAI-Studio/narrator-ai-cli-skillSKILL.md

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.

3.1kMIT

always on

132 tokname + description

once used

4,539 tokSKILL.md body

bundled files

445 KB

repo stars

3.1kGitHub

Install the Narrator AI CLI skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/NarratorAI-Studio/narrator-ai-cli-skill --skill narrator-ai-cli

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/NarratorAI-Studio/narrator-ai-cli-skill.git /tmp/narrator-ai-cli-skill
mkdir -p ~/.claude/skills
cp -R /tmp/narrator-ai-cli-skill ~/.claude/skills/narrator-ai-cli

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description132 tok
When the agent uses itThe SKILL.md instructions4,539 tok
Only if opened4 bundled files (45 KB)varies

Until it is used, narrator-ai-cli costs about 10× less than the median MCP server we measured (1,363 tokens on every turn). Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • narrator-ai-cli — AI Video Narration CLI Skill
  • Reference Index
  • Pipeline at a Glance
  • Agent Rules (mandatory — apply across all steps)
  • Prerequisites
  • Core Concepts
  • Conversation Initiation
  • Two Workflow Paths
  • Fast Path internal: targetmode (ask only after path=Fast is confirmed)
  • Resource Selection Protocol
  • Fast Path — High-Level Flow
  • Standard Path — High-Level Flow
  • Standalone Tasks
  • Important Notes
  • Data & Privacy