<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs
Devsly

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated 2w ago

by kangarooking

director-skills

导演Skill：面向 AI 视频创作的开源 Agent Skills | Director Skills: Open-source Agent Skills for AI video creation.

Works with
  • Claude
  • Codex
View on GitHub (opens in a new tab)

266 GitHub stars (266)

+95 in 30 days

Stars gained per day · daily snapshots since Sep 30
Stars gained per day, Sep 30 to Nov 6: +110 in total; the busiest day was Oct 21 with +17 stars.Oct 1: +1 starsOct 2: +6 starsOct 3: +1 starsOct 4: 0 starsOct 5: +6 starsOct 6: +1 starsOct 7: 0 starsOct 8: 0 starsOct 9: +2 starsOct 10: +5 starsOct 11: +6 starsOct 12: +2 starsOct 13: +4 starsOct 14: +3 starsOct 15: +2 starsOct 16: +2 starsOct 17: +7 starsOct 18: 0 starsOct 19: +4 starsOct 20: +1 starsOct 21: +17 starsOct 22: +2 starsOct 23: +4 starsOct 24: +4 starsOct 25: +3 starsOct 26: 0 starsOct 27: +5 starsOct 28: +2 starsOct 29: +3 starsOct 30: +3 starsOct 31: +1 starsNov 1: +4 starsNov 2: 0 starsNov 3: 0 starsNov 4: +1 starsNov 5: +4 starsNov 6: +4 stars
Stars gained between daily snapshots
PeriodNew stars
Oct 1+1
Oct 2+6
Oct 3+1
Oct 40
Oct 5+6
Oct 6+1
Oct 70
Oct 80
Oct 9+2
Oct 10+5
Oct 11+6
Oct 12+2
Oct 13+4
Oct 14+3
Oct 15+2
Oct 16+2
Oct 17+7
Oct 180
Oct 19+4
Oct 20+1
Oct 21+17
Oct 22+2
Oct 23+4
Oct 24+4
Oct 25+3
Oct 260
Oct 27+5
Oct 28+2
Oct 29+3
Oct 30+3
Oct 31+1
Nov 1+4
Nov 20
Nov 30
Nov 4+1
Nov 5+4
Nov 6+4
  • 7 skills (7 skills found in its SKILL.md files)
  • 38 forks (38 forks)
  • 2w ago last update (Last updated 2w ago)

Install

Skills CLI

npx skills add kangarooking/director-skills

Asks which skills and agents to install. Just one: npx skills add kangarooking/director-skills --skill action-fight-prompt — add -g for every project.

Claude Code

git clone https://github.com/kangarooking/director-skillscp -r "director-skills/action-fight-prompt" ~/.claude/skills/

Copies the action-fight-prompt skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add kangarooking/director-skills

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md.

  • action-fight-prompt

    动作打戏 AI 视频提示词设计技能。当用户需要设计具备电影级运镜、节奏感、打击感的武打/战斗片段提示词时使用——覆盖双角色对打、女主 vs 怪兽、近身格斗、载具追逐战、群战、一镜到底、巨型生物/机甲大场面等场景。核心方法论：时序拆段（15 秒拆成 2-3 秒阶段）、动作因果链、环境反馈、视觉资产锁定与参考图映射、音效层。触发词：动作打戏、打戏提示词、武打镜头、战斗片段、打击感、fight scene、对打、动作设计、追车战、群殴、一镜到底。

    action-fight-prompt/SKILL.md on GitHub (opens in a new tab)

  • cinematic-asset-prompts

    影视概念美术专家 & 视觉导演技能——从剧本/故事/世界观文字中提取并设计 AI 视频所需的标准化视觉资产提示词。当用户要求"从剧本提取角色/场景/道具/载具提示词"、"生成角色定妆照 prompt"、"生成场景空镜 prompt"、"生成道具/载具/机械资产设定图 prompt"、"为 AI 视频做视觉资产设计"、"拆解剧本出图清单"时使用本技能。产出角色定妆（全身/半身）、场景空镜、道具/载具/机械资产设定图四类提示词，中英双语，含影调定调与色彩科学方案。

    cinematic-asset-prompts/SKILL.md on GitHub (opens in a new tab)

  • emotion-performance-director

    Use when the user wants to design, rewrite, refine, or vary emotional acting prompts for live-action AI video characters. Translate abstract emotions, dialogue, subtext, and scene context into concise, observable, temporally ordered micro-performance directions. Preserve the user's existing character, scene, camera, and dialogue requirements unless they explicitly ask to change them. Do not use f…

    emotion-performance-director/SKILL.md on GitHub (opens in a new tab)

  • miora-video-studio

    miora 视频生成的可靠性与规格层——补内置技能未覆盖的部分：四必填参数闸门（模式/分辨率/时长/画幅缺一不可提交）、时长区间闸门、完成信号的判定与轮询等待、官方规格口径与本通道实测差异（时长/分辨率/参考图上限）、文生/首尾帧/参考生三种模式的参数事实、提示词的自动修正边界、生成状态向用户的同步。当用户要生成视频、动效、短视频，或提到参考生视频/首尾帧/图生视频、miora 视频、minimax h3、视频生成进度、视频怎么还没出来时使用。

    miora-video-studio/SKILL.md on GitHub (opens in a new tab)

  • seedance-motion-studio

    Use when planning, prompting, producing, reviewing, or improving professional Seedance 2.0 videos, especially product explainers, news explainers, science explainers, and brand films. Turns creative intent into a structured production workflow with shot design, multimodal reference mapping, prompt compilation, continuity management, iteration, post-production planning, and quality gates.

    seedance-motion-studio/SKILL.md on GitHub (opens in a new tab)

  • travel-photo-to-video

    根据用户提供的 1–10 张真实旅拍照片和旅游地点，设计文旅宣传片的推荐分镜顺序、统一视觉母版与逐镜头首帧图生视频提示词。适用于让旅拍照片自然动起来、设计克制运镜和后期剪辑连续性的请求；输出可独立复制的提示词，不直接提交视频生成任务。

    travel-photo-to-video/SKILL.md on GitHub (opens in a new tab)

  • travel-skill

    规划、编写、审阅和修复由真实授权素材与 AI 生成镜头混合制作的电影级文旅宣传片。用于文旅短片创意简报、场景图筛选、首帧空间分析、分镜脚本、画面内容提示词、人物动作、导演级运镜、自然动机布光、转场与尾帧衔接、Seedance 2.0/可灵/Midjourney 提示词、生成结果诊断、时间线与合规风险检查；尤其适用于需要写实、辽阔、自由感和角色剧情连续性的项目。

    travel-skill/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.