HyperFrames Animation
heygen-com/hyperframes
Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.
导演并制作多类型视频,从创意、研究、剧本、视觉开发、人物与声音设计、分镜和生成 Prompt,一直推进到素材生成、任务追踪与交付。适用于 Storytime Animation、Animated Explainer 与 Cinematic Drama,三个 Mode 均已完成实际作品验证。尚未建立专属 Mode 的类型不得冒充已支持流程。
$ npx skills add s1dashu/director --skill director -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install s1dashu/director director --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "director" agent skill from https://github.com/s1dashu/director/tree/main into .claude/skills/director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "director", 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.
$ npx skills add s1dashu/director --skill director -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install s1dashu/director director --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "director" agent skill from https://github.com/s1dashu/director/tree/main into .agents/skills/director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "director", 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.
$ npx skills add s1dashu/director --skill director -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install s1dashu/director director --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "director" agent skill from https://github.com/s1dashu/director/tree/main into .cursor/skills/director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "director", 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.
$ npx skills add s1dashu/director --skill director -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install s1dashu/director director --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "director" agent skill from https://github.com/s1dashu/director/tree/main into .gemini/skills/director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "director", 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.
$ gh skill install s1dashu/director directorInstalls 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).
$ npx skills add s1dashu/director --skill director -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "director" agent skill from https://github.com/s1dashu/director/tree/main into .github/skills/director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "director", 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.
$ npx skills add s1dashu/director --skill director -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install s1dashu/director director --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "director" agent skill from https://github.com/s1dashu/director/tree/main into .opencode/skills/director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "director", 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.
director导演并制作多类型视频,从创意、研究、剧本、视觉开发、人物与声音设计、分镜和生成 Prompt,一直推进到素材生成、任务追踪与交付。适用于 Storytime Animation、Animated Explainer 与 Cinematic Drama,三个 Mode 均已完成实际作品验证。尚未建立专属 Mode 的类型不得冒充已支持流程。
Director is an agent skill from s1dashu/director. 导演并制作多类型视频,从创意、研究、剧本、视觉开发、人物与声音设计、分镜和生成 Prompt,一直推进到素材生成、任务追踪与交付。适用于 Storytime Animation、Animated Explainer 与 Cinematic Drama,三个 Mode 均已完成实际作品验证。尚未建立专属 Mode 的类型不得冒充已支持流程。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 85 other files, including reference files (for example `README.md`, `agents/openai.yaml` and `modes/animated-explainer/narration-script-guide.md`).
It sits in Media & Creative, covering Motion graphics. The repository describes itself as: Direct complete videos with multi-mode workflows for research, scripts, visual development, shot design, media generation, and delivery. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 0972f54. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Director loads about 2.2k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 519 words of instructions outside code blocks.
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.
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.
The full file from s1dashu/director at commit 0972f54, republished under its MIT licence (© s1dashu). 519 words, ~2,249 tokens.
.claude/skills/director/SKILL.md (or your agent's skills folder). This skill also uses 81 other files; get the full folder from GitHub.director 是视频创作与制作的顶层导演 skill,不以动画、旁白或任何单一题材定义自身。它负责先判断作品类型和创作目标,再把任务路由到经过验证的 Mode、style、共享资产与执行工具。
把每支视频拆成三层选择:
三者不互相替代。先选择 Mode,再从该 Mode 的 styles/ 中选择 style 并确认共享资产,最后选择执行 CLI。
用户已指定 Mode 时直接使用。未指定时,根据视频的核心驱动力推荐;无法判断时再询问作品主要由个人经历、知识解释、现实证据,还是人物行动与戏剧冲突驱动。不要因为当前已实现的 Mode 以旁白驱动为主,就把所有视频默认解释成动画解说。
storytime-animation):由第一人称讲述者与个人经历驱动,用动画重现自己、身边人或明确改编的故事。已完成首支五片段作品的生成与质量验证。animated-explainer):使用旁白和动画,在一支短片中讲清楚一个概念、理论、人物思想、历史事件或知识主题。这就是重构前已经完成多期实作验证的原有工作流。cinematic-drama,剧情影像):把已确认的世界观、人物设定、剧本和指定情节制作成由人物行动、对白与戏剧冲突驱动的 AI 电影、AI 漫剧、短剧或微电影。已完成端到端作品验证。
选定 Mode 后,在任何采集、研究、写作、分镜或素材规划之前完整读取对应 workflow.md 及其指定的专属文档。不把 Animated Explainer 的旁白结构、字数、分镜、封面或纯动画切片流程默认套用到其他 Mode。当前只有上方列出的三个 Mode 属于已进入实现的制作能力,三者均已完成实际作品验证。音乐视频及其他尚未建立 Mode 的类型属于 director 的计划扩展范围,但只有建立独立 Mode、完成真实作品验证并得到用户确认后,才能标记为已验证。
用户要求尚未建立专属 Mode 的视频类型时,明确说明当前缺少该类型的专属工作流;可以与用户共同定义目标、输入、叙事结构、素材策略、质量门槛和验证作品,但不得静默套用 Animated Explainer 或 Storytime Animation。新增 Mode 应放入 modes/<mode>/,把类型专属流程、style 和 Prompt 方法留在该 Mode 内;只有真正跨类型复用的能力才提升到 references/。
声音是各 Mode 的创作选择,不是 director 的身份边界。未来 Mode 可以由对白、同期声、音乐、纯画面或多种声音结构驱动;只有当前 Mode 明确要求统一旁白或声音身份时,才进入音色锚点流程。
每个 style 默认只属于一个 Mode,并与该 Mode 的内容目标、素材结构和 Prompt 方法一起验证。不向用户展示其他 Mode 的 style,也不在未验证时默认跨 Mode 混用。只有一个 style 已经通过多个 Mode 的实际作品验证并得到用户确认后,才将它提升为明确的跨 Mode 共享 style。
Storytime Animation
Animated Explainer
Cinematic Drama
用户未指定 style 时,只展示当前 Mode 的内置或候选选项并等待选择,不设置静默默认值;自定义文字 style 与该 Mode 的内置 style 具有同等优先级。style 只定义跨作品稳定的媒介、材质、线条、造型、色彩和运动语言,不是固定 Prompt、场景或镜头模板。候选 style 必须明确验证状态,样片经用户确认后才可标记为已验证。
共享 references 只维护跨 Mode 能复用的能力:
当 Mode 需要人物参考时,只为必须稳定识别的人物生成参考图,不为一次性群演生成。人物参考承担身份、相貌、比例、服装与材质职责。Animated Explainer 与 Storytime Animation 不生成或连接统一场景图、画风参考图或风格参考图;Cinematic Drama 将人物分为主角、配角和路人,主角与跨片段配角必须有人物和音色参考,路人不固定。三视图按角色重要性与制作速度选择:主角默认建议制作,重要配角按需制作,次要配角可使用单张参考。style 始终使用纯文字规则锁定,不使用抽象的统一画风参考图替代 style。
内置音色的唯一正式媒体源为顶级目录 voices/,权威清单为内置音色库。宿主项目可以额外登记私有人物与音色,但不得扫描历史作品冒充正式资产库。repository-assets/ 只保存 README 封面、效果示例和 style 预览等仓库展示素材,不属于 skill 执行资产,也不得被工作流当作生成输入。
Mode 和执行工具相互独立:Mode 决定制作什么,工具文档决定如何在用户选定的平台上生成、管理和下载媒体。任意 Mode 都可在平台能力足够时选择任意已适配 CLI。
当前工具文档:
工具专属命令、模型别名、输入模式、参数映射、任务跟踪和下载规则只在对应 tools/ 文档中维护,不在 Mode、style 或共享 references 中复制。
以下流程当前适用于 Animated Explainer 和 Storytime Animation。各 Mode 的采集、研究、结构、写作、视觉职责和质量门槛以对应 Mode 文件为准。
旁白.md。video/ 目录,不得只报告节点或任务 ID。下载后向用户返回可访问的本地文件路径;宿主支持媒体渲染时,在最终回复中直接展示可播放视频。默认只确认成功终态、可追溯 ID、资源完整性和下载成功,不主动抽帧或听写;用户明确要求或返回异常时才做针对性内容检查。任务失败或平台未返回资源 URL 时,明确说明不存在可下载文件,不伪造交付。全部片段生成后,提示用户在剪辑工具中手动拼接并轻量修剪局部废帧、片尾画面或声音毛刺。只有用户明确要求时,才由 Agent 执行自动拼接。需要封面时读取当前 Mode 的封面指南。目前只有 Animated Explainer 封面指南 已建立专属流程;不将它默认套用到其他 Mode。
| 任务 | 必须完整读取 |
|---|---|
| 选择 Mode,或开始采集、研究、写作、分镜与制作 | 当前选定的 Mode 文件 |
| 编写、改写或拆分 Animated Explainer 旁白 | Animated Explainer 流程和旁白讲稿写作指南 |
| 采集、改编或编写第一人称故事 | Storytime Animation 流程 |
| 制作 AI 电影、AI 漫剧、短剧或微电影 | Cinematic Drama 流程、视觉与声音参考资产指南和当前 style |
| 编写、改写或排查 Cinematic Drama 视频 Prompt | Cinematic Drama 流程、专属视频 Prompt 指南、当前 style、共享视频生成 Prompt 指南和目标模型官方指南 |
| 规划或生成人物参考 | 人物参考图指南、当前 Mode 和所选 style;Storytime 另读人物形象库,Cinematic Drama 另读视觉与声音参考资产指南 |
| 编写、改写或排查视频生成 Prompt | 当前 Mode、共享视频生成 Prompt 指南和目标模型官方指南 |
| 选择、建立、转换或更换音色 | 内置音色库和音色参考与音频转换指南 |
| 生成、比较、修改或质检 Animated Explainer 封面 | Animated Explainer 封面指南 |
| 安装、选择或执行媒体 CLI | 选定的 Tool 文件 |
Seedance 官方指南较长,定向排查时优先搜索:基础公式、多模态参考、编辑视频、延长视频、定义主体、使用分镜时序、动作描述要求、运镜写法、特殊字符规范、音色参考不准、人物 ID 漂移、风格漂移、视频延长 vs 分段拼接、视频结尾有噪音和中文发音不准。
进入生成前,先通过当前 Mode 的专属质量门槛和共享视频 Prompt 检查。以下任一情况存在时,不得进入后续批量生成或最终交付:
失败时保留 Mode、style、工具、模型、参数、素材映射、任务 ID、终态和 stderr 或等价日志。修正真实原因后重新执行,不静默换 Mode、style、模型或平台。
默认使用用户当前使用的语言回复;用户明确指定其他输出语言时,遵循用户指定的语言。
创作草稿默认先在对话中使用普通 Markdown 段落展示,不放入 text、plaintext 或其他代码块。讲稿经用户确认后保存为独立 旁白.md;每个视频 Prompt 片段也分别保存为独立 Markdown 文件。这些文件与人物、素材等生产文档平铺在当前作品的同一文档目录,并向用户返回文件路径。
信息冲突时:内容与叙事方法以当前 Mode 为准;视觉语言以用户选择的 style 和已确认人物参考为准;模型提示能力以最新官方指南为准;平台命令、模型名、输入能力与参数以当前 CLI 和实时 schema 为准。
© s1dashu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 81 other files (references) in the repository root of s1dashu/director.
Open the folder on GitHubat commit 0972f54
Director 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Director this skills1dashu/director | 789 | — | ~2.2k | Automated safety check: Pass | MIT | |
| HyperFrames Animationheygen-com/hyperframes | 59k | 3 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Slack GIF Creatoranthropics/skills | 180k | 29 repos | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills | 8.4k | 6 repos | ~3.2k | Automated safety check: Notes | Apache-2.0 | |
| Faceless Explainer Videoheygen-com/hyperframes | 59k | 3 repos | ~7.7k | Automated safety check: Notes | Apache-2.0 | |
| Video ShotcraftVincentwei1021/video-shotcraft | 11k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 |
heygen-com/hyperframes
Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.
anthropics/skills
Provides Slack size and frame limits, Python animation helpers and validators for building animated GIFs sized for emoji and messages.
google-labs-code/stitch-skills
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
heygen-com/hyperframes
Turns an article, notes or a topic brief into an explainer video whose visuals are invented per scene, built frame by frame in HyperFrames with no footage.
Vincentwei1021/video-shotcraft
Makes cinematic product videos with Remotion from shot recipe cards, a ready template, real page screenshots, camera moves and sound design, or builds a single animated shot.
heygen-com/hyperframes
Imports Figma assets, brand tokens, components and motion into a HyperFrames video composition, using the Figma REST API with a connector or native export for shaders.
Categories
导演并制作多类型视频,从创意、研究、剧本、视觉开发、人物与声音设计、分镜和生成 Prompt,一直推进到素材生成、任务追踪与交付。适用于 Storytime Animation、Animated Explainer 与 Cinematic Drama,三个 Mode 均已完成实际作品验证。尚未建立专属 Mode 的类型不得冒充已支持流程。. Director is an agent skill from s1dashu/director.
Director fits situations like: tasks that involve Motion graphics.
Run `npx skills add s1dashu/director --skill director -a claude-code`. Or copy the skill folder (the s1dashu/director repository) into .claude/skills/director in your project. Claude Code loads it when a task matches its description.
Run `npx skills add s1dashu/director --skill director -a codex`. Or copy the skill folder (the s1dashu/director repository) into .agents/skills/director in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add s1dashu/director --skill director -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/director, .gemini/skills/director, .github/skills/director and .opencode/skills/director in your project.
SKILL.md names no scripts, command-line tools or credentials: Director is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
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.
Director is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 10k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Director: HyperFrames Animation (heygen-com/hyperframes, 59k stars), Slack GIF Creator (anthropics/skills, 180k stars), Stitch to Remotion Walkthrough Videos (google-labs-code/stitch-skills, 8.4k stars) and Faceless Explainer Video (heygen-com/hyperframes, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
s1dashu (a GitHub user) maintains it in s1dashu/director, which has 789 GitHub stars. The repository was last updated on August 10, 2026.
Source: s1dashu/director on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.