NarratorAI-Studio/narrator-ai-cli-skill

AI 解说大师 — Agent skill;封装 narrator-ai-cli 供 Claude/Codex 等工具调用

View on GitHub ↗Jump to charts ↓Open shareable report →

NarratorAI-Studio/narrator-ai-cli-skill has 3k+ stars and 400+ forks on GitHub and was last pushed on Jul 5, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 4 minutes ago
Added to GitGenius on September 30th, 2026
Created on March 19th, 2026
Open Issues & Pull Requests: 6 (+0)
GitHub issues: Enabled
Number of forks: 405
Total Stargazers: 3,052 (+0)
Total Subscribers: 9 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 0.1 hours
Mean response time: 2.3 days
90th percentile: 3.9 days
Tracked items: 23

Maintainer activity

3 people did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 2
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 106 days
Stale 30+ days: 2
Stale 90+ days: 2

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • enhancement (2)
  • area:agent (1)
  • bug (1)
  • priority:p2 (1)
  • question (1)
  • stale-auto (1)
  • task (1)
  • type:cross-cutting (1)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Narrator AI CLI Skill is an AI agent capability file that teaches language models and AI coding assistants how to use the narrator-ai-cli tool to generate movie narration videos automatically.

The skill solves the problem of making video narration production accessible to AI agents by providing machine-readable instructions that bridge the gap between the underlying CLI tool and natural language requests. When an AI agent receives a user request like "create a narration video for this movie," the skill file teaches it which CLI commands to invoke, in what order, and how to handle the data flow between steps. The approach separates concerns: the CLI provides the executable commands and API integrations, while the skill provides the procedural knowledge and error handling logic that allows an agent to orchestrate those commands end-to-end.

Adoption makes sense for teams building AI agent applications that need video content generation capabilities, particularly those working with OpenClaw, Windsurf, Claude Code, Cursor, or other markdown-skill-compatible agents. The tool is most useful when you want to automate narration video production at scale—generating multiple videos from movie clips with different templates, voices, and styles. Installation requires both the CLI tool and the skill file with its references directory, and the setup process varies slightly by agent platform but generally involves cloning the repository into the agent's skills folder. The project includes built-in resources covering approximately 100 movies, 146 background music tracks, 63 dubbing voices, and 90 or more narration templates, supporting both adapted and original narration workflows.

Development activity shows consistent maintenance with verified compatibility across multiple agent platforms including OpenClaw, Windsurf, WorkBuddy, QClaw, Youdao Lobster, Yuanqi AI, Claude Code, and Cursor. The project includes comprehensive error handling documentation covering all API error codes with recommended actions, and provides cost estimation features to verify budgets before task creation. Documentation is bilingual with both English and Chinese versions available, and the skill file incorporates detailed data flow mapping to clarify which outputs feed into subsequent inputs throughout the video generation pipeline.