Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bozhouDev/video-skills-toolkit --skill video-scriptgit clone --depth 1 https://github.com/bozhouDev/video-skills-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/video-script)<a href="https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/video-script"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/video-script.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00197 | $0.04225 |
| Opus 5 | $0.00098 | $0.02112 |
| Sonnet 5 | $0.00039 | $0.00845 |
| Haiku 4.5 | $0.00020 | $0.00422 |
Grade A, and why
video-script scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Script · Director Layer(短视频留存增强)
把已锁定的完整声音和字幕时间轴转成全片一致、可确认、可还原的导演处理稿。先回答“观众经历什么、画面世界如何演进”,再回答“每一段真实口播时间里发生什么”。
本 Skill 是逐字稿与实现管线之间的导演层。它不默认把所有内容做成 MG,也不把“运动优先”误解为“所有东西一直动”。真人、真实录屏、截图、B-roll、图形动画和留白都可以成为正确答案;关键是它们是否共同服务同一条叙事与注意力路径。
对短视频,本 Skill 可作为“爆款潜力导演”:它负责让镜头继续履行上游稿件的停滑、留存和传播意图,但不承诺流量结果,也不用画面替上游修稿。
职责门禁
- 正式视频导演稿必须同时具备:已确认逐字稿、已锁定完整音频、主字幕文件和校准后的带时间码字幕数据。只有选题、素材、大纲、逐字稿或
8–15s声音试听时,先完成上游,不得进入正式分镜。 - 用户同时要求“写逐字稿+做分镜”时,先完成当前工作区可用的上游逐字稿创作/审稿流程,再完成声音试听、完整配音、字幕生成和校准,最后把同一版本交给本 Skill。不要一边写正文、一边生成声音、一边预设画面。
- 不改写原稿的事实、观点、顺序、句子或连接词。发现口语、逻辑、事实或段间衔接阻塞制作时,引用具体相邻句,标为“上游逐字稿阻塞”,转回当前可用的逐字稿修订流程;若未安装专用 Skill,则明确告知用户需先修稿。用户明确要求按草稿原样继续时才做导演处理。
- 不输出 HTML、JSX、Remotion 组件、HyperFrames DOM 或 ChatCut MG 实体。实现属于下游 Skill。
执行职责
- 导演规划者完成导演诊断、素材职责、导演稿和制作规格;角色和能力要求以当前运行时与工作区指令为准,不在 Skill 中写死模型版本。
- 本阶段不得启动任何镜头执行者,也不得提前写场景代码。只有导演稿、制作规格、素材计划和 motion contract 锁定后,才交给已选管线的单一执行者;本工具包的 HyperFrames 执行者是
hyperframes-scene-animator。
单一导演来源
锁定后的 导演契约 + beat graph 是下游的叙事与视觉单一事实源。
- 下游可以补坐标、组件、帧、选择器、缓动和渲染细节。
- 下游不得擅自更换核心视觉命题、贯穿物、证据顺序、运动语法或转场关系。
- 实现不可行时,记录冲突与保守替代方案,返回导演阶段确认;不要静默重新导演。
默认保持管线无关
- 用户未指定工具时,不选择默认实现工具,也不写
pipeline。 - 使用真人、录屏、截图、B-roll、仿真 UI、流程关系、图形动画、空间和镜头等通用语言,不在导演契约中混入平台属性、坐标、帧号或组件名。
- 用户明确指定 Remotion、ChatCut、HyperFrames、剪映或其他管线时,保留同一份导演契约,只追加最少必要的应用说明。
- 能用真实证据直接说明的内容,不用抽象隐喻替代;抽象逻辑才优先寻找可演进的视觉隐喻。
按需读取
- 每次正式生成导演稿时读取
references/director-treatment.md。 - 导演方向锁定后读取
references/beat-graph.md。 - 完成导演稿前读取
references/anti-ppt-gate.md;写制作规格时在实现前再检查一次。低清 proof 后的语义运动、转场中点、AI 味硬拒绝项和联系表连续性由下游执行者检查;HyperFrames 管线使用hyperframes-scene-animator。 - 正式交付时读取
references/output-template.md。 - 目标是短视频、平台分发型视频,或用户明确要求完播、留存、爆款/传播潜力时,读取
references/short-video-retention-directing.md;只提取稿件已有意图,不调用上游选题或片头改写流程。 - 中长视频、复杂剪辑判断或节奏诊断时读取
references/editing-methodology.md。 - 命中既有平台风险或用户要求复盘经验时读取
references/lessons-learned.md,只应用相关规则。 - 分镜已确认且用户要求继续制作时读取
references/production-spec.md。制作规格必须使用已经锁定的最终声音和带时间码字幕,并在代码动画管线中同步产出work/motion-contract.json。 - 用户明确要求 HyperFrames 制作时:若尚无固定舞台工程,先读取
talking-head-hyperframes生成模板与素材交接;交接状态为READY_FOR_EXECUTION后,一律读取hyperframes-scene-animator实现所有镜头。模板 Skill 不制作场景。 - 使用 Studio 暖白 Remotion 模板、沿用 J-space 视觉或用户锁定同类背景时,在给方向卡前用
view_image查看 Studio 暖白蓝金网格高清参考图,并按references/director-treatment.md把背景当作导演约束,而不是实现阶段再补的装饰。 - 需要实际生成图片时读取
imagegen;导演阶段默认只写资产职责和规格。
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 42 B
- assets/references/studio-warm-grid-jspace-s06-1920x1080.png 953 KB
- evals/evals.json 11 KB
- evals/trigger-evals.json 2.4 KB
- references/anti-ppt-gate.md 5.5 KB
- references/beat-graph.md 8.0 KB
- references/director-treatment.md 9.6 KB
- references/editing-methodology.md 9.4 KB
- references/hyperframes-motion-contract.template.json 4.5 KB
- references/lessons-learned.md 15 KB
- references/output-template.md 8.1 KB
- references/production-spec.md 13 KB
- references/remotion-motion-contract.template.json 4.5 KB
- references/short-video-retention-directing.md 4.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 184 lines · 197 tokens per session scan A 5e4b7d812ce7
video-script is a skill published in the GitHub repository bozhouDev/video-skills-toolkit (137 stars, last pushed 1mo ago), licensed MIT. It adds 197 tokens to every session and 4,225 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
video-hyperframes
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
video-hyperframes
A web-based sequence of video frames designed for Hyperframes or Remotion, with each frame presenting one visual idea.
remocn
Build Remotion videos with remocn — copy-paste animation components and timeline-driven UI primitives from a shadcn registry. Use when composing a video or scene in a Remotion project, adding a single animation, transition, background, or UI-block sim, or reaching for a video-ready UI primitive (button, dialog…
minimax-cli
Nested swiss-knife reference for the MiniMax mmx CLI and the canonical MiniMax CLI procedure shipped with the TUI: install mmx-cli, discover the correct TUI-managed MiniMax preset/key slot without leaking secrets, match mainland vs international regions, and route image/video/music/TTS generation or one-shot shell…
videoagent-audio-studio
Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.