edit-timeline-studio

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AI Video Editing with Timeline Studio

使用 Timeline Studio 进行 AI 视频编辑

Turn the user's exact editorial request and media into reversible Timeline Studio edits. Keep the editable timeline as the source of truth; never replace it with an opaque one-shot render.

将用户明确的剪辑要求和媒体转换为可逆的 Timeline Studio 编辑。始终以可编辑时间线作为事实来源；绝不能用不透明的一次性渲染结果替换它。

Choose the execution path

选择执行路径

When the user is working in an already open Timeline Studio project, prefer its native browser WebMCP tools if the host exposes them. Read references/webmcp-integration.md: inspect the live state, preview the complete supported edit, review its semantic diff, then apply the returned

previewId

. This route shares the visible editor and differs from the local project-file workflow below. It does not add a remote MCP server or grant permission to upload media.

On first local use after installation, read references/host-environment.md. If Node.js is unavailable, start with the zero-dependency Shell or PowerShell bootstrap; otherwise run
```
node scripts/setup-host.mjs --check
```
. Agent-driven Chinese and mixed Chinese/English voiceover uses Timeline Studio's owned browser-local Hojo TTS Light 80M two-voice bundle and does not require a separate Python voiceover capability. If language runtimes or dependencies are missing, show the exact installation plan and obtain explicit user approval before install mode; never treat Skill installation as permission to modify the host or download models.
Treat local project-file processing as the default for deterministic editing: inspect media locally, modify the portable
```
.timeline
```
through the command layer or local archive services, and render and verify decoded output when the task changes rendered media. Do not open a browser merely because the editor has a UI.
Treat
```
https://video-editor.ai-creator.top/
```
as the canonical hosted editor only when the user explicitly asks to use the website, provides no local repository or project path, or requires a hosted-only capability.
When this repository is available, prefer its Agent command layer and local media tools. Start the local server and browser only for a verified UI-only operation that the local project pipeline cannot express and the user has not required a local-only workflow. Read the actual server URL from process output; never assume port 5173.
Prefer the bundled Timeline Studio MCP tools when the host exposes them. Read references/mcp-integration.md, inspect the project, and always call
```
timeline_project_diff
```
before
```
timeline_project_apply
```
with the same revision and operations. The MCP server is a transport over the repository command runner, not a separate editing implementation.
When MCP is unavailable, inspect
```
package.json
```
for an Agent command script. Do not use
```
npm run ... --if-present
```
as capability detection because it can succeed silently. If the command runner exists, read references/command-contract.md, inspect the project, build a versioned plan, run the structural validator, and use
```
project.diff
```
as the authoritative semantic dry run before
```
project.run
```
.
If a required operation is missing from the local contract, state the exact gap. For repository-development work, implement the smallest shared local operation and renderer support before falling back to UI. Otherwise ask before switching to the browser workflow.
Do not claim deterministic or idempotent execution when only UI automation was available. State the limitation and preserve an editable project archive when the UI supports it.

当用户正在一个已打开的 Timeline Studio 项目中工作时，如果宿主提供原生浏览器 WebMCP 工具，应优先使用。阅读 references/webmcp-integration.md：检查实时状态、预览完整的受支持编辑、审阅语义差异，然后应用返回的

previewId

。此路径与可见编辑器共享状态，不同于下文的本地项目文件工作流。它不会增加远程 MCP 服务器，也不会授予上传媒体的权限。

安装后首次本地使用时，阅读 references/host-environment.md。如果 Node.js 不可用，先使用零依赖 Shell 或 PowerShell 引导程序；否则运行
```
node scripts/setup-host.mjs --check
```
。由 Agent 驱动的中文及中英文混合配音使用 Timeline Studio 自有的浏览器本地 Hojo TTS Light 80M 双声音色包，不需要单独的 Python 配音能力。如果缺少语言运行时或依赖项，应给出准确的安装计划，并在进入安装模式前获得用户明确批准；绝不能将 Skill 安装视为修改宿主或下载模型的许可。
对确定性编辑，默认采用本地项目文件处理：在本地检查媒体，通过命令层或本地归档服务修改可移植的
```
.timeline
```
，并在任务改变渲染媒体时渲染并验证解码后的输出。不要仅仅因为编辑器有 UI 就打开浏览器。
仅当用户明确要求使用网站、未提供本地仓库或项目路径，或者需要仅托管环境才能完成的功能时，才将
```
https://video-editor.ai-creator.top/
```
视为标准托管编辑器。
当此仓库可用时，优先使用其 Agent 命令层和本地媒体工具。仅当已经验证某项操作只能通过 UI 完成、本地项目管线无法表达，且用户未要求仅使用本地工作流时，才启动本地服务器和浏览器。从进程输出中读取实际服务器 URL；绝不能假定端口为 5173。
如果宿主提供捆绑的 Timeline Studio MCP 工具，应优先使用。阅读 references/mcp-integration.md、检查项目，并且始终先以相同的 revision 和 operations 调用
```
timeline_project_diff
```
，再调用
```
timeline_project_apply
```
。MCP 服务器只是仓库 command runner 之上的传输层，而不是另一套独立的编辑实现。
MCP 不可用时，检查
```
package.json
```
中的 Agent 命令脚本。不要使用
```
npm run ... --if-present
```
检测能力，因为它可能在命令不存在时仍静默成功。如果 command runner 存在，阅读 references/command-contract.md、检查项目、构建版本化计划、运行结构验证器，并在
```
project.run
```
之前使用
```
project.diff
```
作为权威的语义 dry run。
如果本地 contract 缺少所需操作，应准确说明缺口。对于仓库开发工作，应先实现最小化的共享本地操作及渲染器支持，再回退到 UI。其他情况下，应先征得用户同意，再切换到浏览器工作流。
只有 UI 自动化可用时，不要声称执行具有确定性或幂等性。应说明这一限制，并在 UI 支持时保留可编辑的项目归档。

Workflow

工作流

For a marker-only request, read references/timeline-markers.md and follow its inspect → plan → validate → diff → apply → inspect workflow through annotation handoff. Markers, chapter cues, ranges, and notes are project annotations; adding them requires no narration, model download, browser session, or video render. The media-production steps below apply only when the user also requests a media edit.

对于仅添加标记的请求，阅读 references/timeline-markers.md，并通过注释交付流程遵循检查 → 计划 → 验证 → 差异 → 应用 → 检查的工作方式。标记、章节提示、范围和备注属于项目注释；添加它们不需要旁白、模型下载、浏览器会话或视频渲染。只有当用户同时要求媒体编辑时，才执行以下媒体制作步骤。

1. Inspect before editing

1. 编辑前检查

Preserve the user's prompt verbatim as the creative brief.
Resolve every referenced asset to an explicit path or URL. Never sweep a directory without approval.
Inspect duration, dimensions, audio presence, and media type.
Read the current project summary before changing an existing project.
Before planning long videos, chapters, musical beat cues, review notes, or edit ranges, read references/timeline-markers.md. Inspect existing annotations and use evidence-backed markers to preserve editorial anchors and decisions where useful. Preserve user annotations and distinguish Agent observations from supplied feedback.
Ask only when an unresolved choice materially changes the edit, such as the desired output duration or aspect ratio.
For an automatic-editing request, read references/auto-edit-workflow.md. Inspect first, classify the content, goal, and delivery with an explicit confidence level, then ask only the minimum category-specific questions that can change the cut. Never ask for facts discoverable from the media.
For a request to reproduce, imitate, recreate, or reverse-engineer a reference video, read references/replication-workflow.md. Classify it as
```
editing-style replication
```
,
```
AI-generation replication
```
, or a hybrid; reconstruct filters, repetitions, source splits, speed curves, transitions, shots, and timing before building; and explicitly resolve whether the authorized original audio track must be retained. Do not start editing until the replication analysis-completeness gate passes. Use current web search to compare AI video platforms only when generation is required, and use lawful web-sourced footage only when the user has not supplied adequate material.
Before loading or downloading a model for media analysis, read references/local-model-routing.md. Inventory the repository's existing local and pinned mirrored capabilities, choose the minimum model chain needed for the evidence gap, run inference locally without driving the visible editor UI, and record exact model/runtime/fallback provenance. Never load every available model by default or create a duplicate cache.
When the user needs web-sourced footage or asks where downloadable material can be found, read references/web-footage-sourcing.md. Give current, task-specific platform suggestions from live search and rank them by source legitimacy, explicit download support, usage rights, visual fit, quality, and provenance. Keep the skill provider-neutral; never hard-code one platform or brand as the permanent route.
For every completed automatic edit, read references/professional-editing-workflow.md. Analyze images directly; analyze video with representative frames, speech/OCR, semantics, and global plus subject-region optical flow. Stabilize before tracking or enhancement. Ask about image-to-video or image-to-image models only after inspection proves that generation is materially useful.
When a video plan could benefit from temporal emphasis, shot-matched color shaping, foreground/background separation, a product or person hero treatment, an editable subject outline, or identity replacement, read references/curves-and-subject-effects.md. Consider these capabilities during shot design instead of waiting for the user to name a control. Analyze in source time before retiming, use speed curves only for motivated timing changes, use Color Wheels to preserve skin and product identity while shaping the look, derive cutouts and outlines from verified masks, require explicit authorization for face swap, and validate preview/export parity and temporal stability before delivery.
When remote generation is materially required, read references/remote-video-generation.md. Search current official documentation, compare only providers that fit the shot blueprint, obtain approval before any paid or privacy-sensitive job, normalize the asynchronous task and provenance, download expiring output bytes, and add verified results to My assets without automatic timeline placement.
For product, brand,
```
marketing-commerce
```
, website-promotion, or other promotional edits, read references/promotion-narrative-workflow.md. Proactively construct an ambitious evidence-backed umbrella narrative rather than a feature list or kinetic-typography montage. Unless the user explicitly requests a teaser, build a complete problem-to-transformation-to-proof-to-CTA arc and actively find several visually distinct cases—normally at least three—each with its own setup, product action, visible result, and connection to the final payoff. Never invent customers, outcomes, metrics, or product behavior to make the story feel larger.
For highlight edits and reference replications where emphasis or dramatic impact matters, read references/highlight-tension-workflow.md. Treat saliency as candidate evidence, assign setup/rise/pre-impact/peak/aftershock roles, design a non-flat tension envelope, protect the decisive hero frame, and reject completion when accurate cutting still lacks a dominant payoff.
For a website walkthrough or promotional recording, use a supported browser-control skill to inspect and rehearse the authorized journey before capture. Read that browser skill completely before browser actions, then follow references/website-promo-workflow.md. Build and complete a page/flow coverage manifest before drawing product conclusions. When required pages are gated, ask the user to sign in themselves in the selected browser; never request credentials or describe inaccessible behavior as verified. Confirm any consequential external action separately, protect signed-in and personal data, and never claim a real screen recording was captured when only screenshots or static assets were available.
Treat
```
tutorial-demo
```
,
```
vlog-event
```
,
```
marketing-commerce
```
, and
```
narrative-documentary
```
as narrated-by-default categories. Preserve and reuse authorized source speech when it already carries the required story; otherwise author the minimum complete narration needed for context, progression, visible result, consequence, and closure, then synthesize it before timing picture. Do not ask whether narration should exist unless the user explicitly requests a source-only, music-only, or silent treatment; ask only for choices that materially affect language, casting, claims, or delivery.
For narrated edits, read references/voiceover-workflow.md. Prefer Timeline Studio's owned, pinned browser-local voices for every supported language. Route Chinese and mixed Chinese/English narration through the owned Hojo TTS Light 80M browser bundle and cast one of its two stable built-in reference profiles—晴岚 /
```
zh_f_qinglan
```
or 若溪 /
```
zh_f_ruoxi
```
—for each narrator or character; never install or use Hojo 40M or MeloTTS for this route. Use a remote service, operating-system voice, or unowned runtime only when the requested language or voice is unavailable locally and the user explicitly approves that fallback. Unless the user requests another delivery, choose the warmest natural storyteller-like match from the eligible local profiles and direct a close, conversational performance with meaningful phrasing; never default to a flat, metallic, or mechanical system-voice effect. Generate narration as separate short breath-group segments, not as one monolithic performance to split afterward. Treat a comma as a sufficient default synthesis boundary, prefer several short phrase clips over one long sentence clip, and use the shared desktop/H5
```
0.4s
```
gap between adjacent voice clips. Lock the complete segmented audio spine before finalizing scene durations, motion, transitions, captions, or picture cuts; adapt and trim visuals to the measured speech and pauses, never the other way around. Treat runtime only as an outcome measurement and do not target, chase, or align to a preset number of seconds.

将用户的提示词逐字保留为创作简报。
将每个被引用的素材解析为明确的路径或 URL。未经批准，不得扫描目录。
检查时长、尺寸、音频存在情况和媒体类型。
修改现有项目之前，读取当前项目摘要。
在规划长视频、章节、音乐节拍提示、审阅备注或编辑范围之前，阅读 references/timeline-markers.md。检查现有注释，并使用有证据支持的标记，在有助于保留的情况下维持剪辑锚点和既有决策。保留用户注释，并区分 Agent 观察结果与用户提供的反馈。
只有当某个尚未确定的选择会实质性改变编辑结果时才提问，例如目标输出时长或宽高比。
对于自动编辑请求，阅读 references/auto-edit-workflow.md。先检查，再对内容、目标和交付形式进行分类并给出明确置信度，然后只提出最少量的、会改变剪辑方案的分类专属问题。绝不要询问可以从媒体中发现的事实。
对于复刻、模仿、重建或逆向解析参考视频的请求，阅读 references/replication-workflow.md。将其分类为
```
editing-style replication
```
、
```
AI-generation replication
```
或混合类型；在构建之前重建滤镜、重复镜头、源素材拆分、速度曲线、转场、镜头和时序；并明确确定是否必须保留已获授权的原始音轨。在复刻分析完整性门槛通过之前，不要开始编辑。只有在确实需要生成时才使用实时网页搜索比较 AI 视频平台；只有在用户未提供足够素材时，才使用合法的网络来源素材。
加载或下载用于媒体分析的模型之前，阅读 references/local-model-routing.md。盘点仓库已有的本地能力和固定版本的镜像能力，选择填补证据缺口所需的最少模型链，在不驱动可见编辑器 UI 的情况下进行本地推理，并记录准确的模型、运行时及 fallback 来源。绝不能默认加载所有可用模型或创建重复缓存。
当用户需要网络来源素材或询问可下载素材的获取位置时，阅读 references/web-footage-sourcing.md。通过实时搜索提供当前且针对具体任务的平台建议，并按照来源合法性、明确的下载支持、使用权、视觉匹配度、质量和来源可追溯性进行排序。保持 Skill 的平台中立性；绝不能将某个平台或品牌硬编码为永久路径。
对于每个已完成的自动编辑，阅读 references/professional-editing-workflow.md。直接分析图像；使用代表性帧、语音/OCR、语义以及全局和主体区域光流分析视频。进行跟踪或增强之前先稳定画面。只有在检查证明生成具有实质价值后，才询问是否使用图生视频或图生图模型。
当视频方案可能受益于时序强调、与镜头匹配的颜色塑造、前景/背景分离、产品或人物主角处理、可编辑主体轮廓或身份替换时，阅读 references/curves-and-subject-effects.md。应在镜头设计期间考虑这些能力，而不是等待用户点名某个控制项。重新调整时间之前在源时间中进行分析；仅为有动机的时序变化使用速度曲线；使用 Color Wheels 在塑造视觉风格的同时保留皮肤和产品身份；基于经过验证的 mask 生成 cutout 和 outline；face swap 必须获得明确授权；交付前验证预览/导出一致性和时间稳定性。
当实质上需要远程生成时，阅读 references/remote-video-generation.md。搜索当前的官方文档，仅比较符合镜头蓝图的提供商，在任何付费或涉及隐私的任务之前获得批准，规范化异步任务及其来源信息，下载会过期的输出数据，并将验证后的结果添加到 My assets，而不自动放入时间线。
对于产品、品牌、
```
marketing-commerce
```
、网站推广或其他宣传类编辑，阅读 references/promotion-narrative-workflow.md。主动构建大胆且有证据支持的总体叙事，而不是功能列表或动态字体蒙太奇。除非用户明确要求预告片，否则应构建完整的“问题—转变—证明—CTA”叙事弧，并主动寻找多个视觉差异明显的案例——通常至少三个——每个案例都应包含自己的铺垫、产品动作、可见结果，以及与最终回报的联系。绝不能虚构客户、结果、指标或产品行为来夸大故事。
对于重点片段编辑和强调冲击力或戏剧效果的参考复刻，阅读 references/highlight-tension-workflow.md。将显著性视为候选证据，分配铺垫、上升、冲击前、峰值和余震角色，设计非平坦的张力包络，保护决定性的 hero frame；如果准确剪辑仍然缺少主导性回报，则拒绝判定完成。
对于网站演示或宣传录制，使用受支持的浏览器控制 skill 检查并排练已获授权的浏览流程。在执行浏览器操作前完整阅读该浏览器 skill，然后遵循 references/website-promo-workflow.md。得出产品结论之前，先构建并完成页面/流程覆盖清单。当所需页面受访问限制时，请用户在选定浏览器中自行登录；绝不能索要凭据，也不能将无法访问的行为描述为已验证。单独确认任何重要的外部操作，保护已登录会话和个人数据；当只有截图或静态素材时，绝不能声称已捕获真实屏幕录制。
将
```
tutorial-demo
```
、
```
vlog-event
```
、
```
marketing-commerce
```
和
```
narrative-documentary
```
视为默认带旁白的类别。如果已获授权的源语音已经承载所需故事，应保留并复用；否则，应创作满足上下文、推进、可见结果、后果和收束所需的最小完整旁白，并在确定画面时间之前完成合成。除非用户明确要求仅源声、仅音乐或静音处理，否则不要询问是否需要旁白；只询问那些会实质影响语言、角色声音选择、事实主张或呈现方式的问题。
对于带旁白的编辑，阅读 references/voiceover-workflow.md。对于每种受支持的语言，优先使用 Timeline Studio 自有且固定版本的浏览器本地声音。中文及中英文混合旁白应通过自有 Hojo TTS Light 80M 浏览器音色包处理，并为每位旁白或角色选用两个稳定内置参考档案之一——晴岚 /
```
zh_f_qinglan
```
或若溪 /
```
zh_f_ruoxi
```
；此路径绝不能安装或使用 Hojo 40M 或 MeloTTS。只有当本地无法提供所需语言或声音，并且用户明确批准 fallback 时，才使用远程服务、操作系统声音或非自有运行时。除非用户要求其他交付方式，否则应从符合条件的本地档案中选择最温暖、最自然的讲述者风格匹配，并以贴近自然的对话式演绎呈现有意义的语段；绝不能默认使用平淡、金属感或机械化的系统声音效果。将旁白生成为独立的短呼吸组片段，而不是先生成一个整体表演再进行拆分。将逗号视为足够的默认合成边界，优先使用多个短句片段而不是一个长句片段，并在相邻配音片段之间使用统一的 desktop/H5
```
0.4s
```
间隔。在最终确定场景时长、运动、转场、字幕或画面剪切之前，锁定完整的分段音频主线；根据实测语音和停顿调整视觉时长，绝不能反过来让语音迁就画面。运行时长仅作为结果衡量指标，不得追求、追逐或对齐预设秒数。

2. Plan at the supported fidelity

2. 在受支持的保真度下规划

For an automatic edit, preserve the prompt and normalize inferred, confirmed, defaulted, and unresolved decisions into an editable brief. Build a source-time decision record with keep/remove/shorten/reorder decisions, reasons, confidence, caption expectations, audio-continuity constraints, and protected content before changing the timeline.
For explanatory product, tutorial, or website beats, choose an explicit attention treatment for the single named target: magnify small or dense evidence, underline exact text or numbers, or frame the exact boundary of a control, card, or result. Use at most one supporting treatment with a camera move, and apply the underline or frame only after the camera has stopped.
For subject-led shots, choose the smallest justified treatment: use cutout to change context or layer depth, outline to focus attention without removing context, and face swap only when identity replacement is explicitly requested and authorized. Apply a speed curve to a meaningful action phase or editorial beat, not as continuous decoration. Preserve the analyzed source-time mapping when retiming.
With the command runner, express edits as declarative operations with stable IDs, seconds, revisions, operation IDs, and preconditions. Run
```
scripts/validate_edit_plan.mjs <plan.json>
```
for transport-shape errors, then run
```
npm run agent -- project.diff <plan.json>
```
to reject unsupported operations and invalid project-specific edits before applying anything.
With browser UI only, write a short ordered checklist of visible user intents and expected UI outcomes. Prefer named controls and clip labels; use coordinates only as a last-resort fallback grounded in a current screenshot.
Keep main Visuals contiguous. Treat captions, stickers, source audio, voiceover, music, and overlays as timed clips.
Apply a one-way caption-to-speech rule: if the project configures or enables any caption, every visible caption must correspond to audible speech. Link transcription captions to the existing spoken source clip, and generate a voiceover for every new narration, explanatory, promotional, or text-led caption. Existing source speech satisfies this rule and must not receive a duplicate voiceover. When captions are absent, narration is still the default for
```
tutorial-demo
```
,
```
vlog-event
```
,
```
marketing-commerce
```
, and
```
narrative-documentary
```
; it remains optional for other categories unless the brief requires it. If a configured caption has no authorized speech route, omit it or stop with the editable project preserved.
For narrated edits, synthesize each short breath group into its own physical archived audio file from the outset and bind each caption to exactly one matching
```
audioClipId
```
; do not generate one monolithic narration file and split it after synthesis. Split at sentence-ending punctuation and, by default, at commas, semicolons, colons, em dashes, or another clear spoken pause. Keep a boundary joined only when splitting would create a meaningless fragment or break a proper name, number, URL, or intended bilingual phrase. For free-script generation, keep the first clip at the explicit playhead, append every later clip after the current voiceover-track end, and never reuse an unchanged playhead or
```
0s
```
; caption-scoped generation stays anchored to its caption. Place adjacent narration clips with the shared desktop/H5 default
```
0.4s
```
gap, then derive caption timing and picture timing from the accepted audio sequence.
Preserve media identity and source-time mapping when moving or trimming clips.

对于自动编辑，保留提示词，并将推断出的、已确认的、默认采用的及尚未解决的决定规范化为可编辑简报。在修改时间线之前，构建源时间决策记录，其中包含保留、删除、缩短和重排决定及其原因、置信度、字幕预期、音频连续性约束和受保护内容。
对于解释性产品、教程或网站片段，为唯一明确的目标选择一种明确的注意力处理方式：放大较小或密集的证据，标注准确的文字或数字，或框出控件、卡片或结果的准确边界。最多使用一种辅助处理配合镜头运动，并且只能在镜头停止后添加标注或边框。
对于主体主导的镜头，选择有充分依据的最小处理方式：使用 cutout 更换背景或建立分层景深，使用 outline 在保留环境的同时集中注意力，仅在明确要求且获得授权时使用 face swap。将速度曲线应用于有意义的动作阶段或剪辑节拍，而不是将其作为持续装饰。重新调整时间时，保留已分析的源时间映射。
使用 command runner 时，将编辑表达为带有稳定 ID、秒数、revision、operation ID 和前置条件的声明式操作。先运行
```
scripts/validate_edit_plan.mjs <plan.json>
```
检测传输结构错误，再运行
```
npm run agent -- project.diff <plan.json>
```
，在应用任何修改之前拒绝不受支持的操作和无效的项目专属编辑。
仅使用浏览器 UI 时，编写一份简短的有序清单，列出可见的用户意图和预期的 UI 结果。优先使用具名控件和片段标签；只有在没有其他选择时，才使用基于当前截图的坐标作为 fallback。
保持主 Visuals 轨道连续。将字幕、贴纸、源音频、配音、音乐和叠加层视为定时片段。
采用单向字幕对应语音规则：如果项目配置或启用了任何字幕，每个可见字幕都必须对应可听语音。将转录字幕关联到已有的源语音片段，并为每段新增的旁白、解释、宣传或文字主导字幕生成配音。已有源语音满足此规则，不应再生成重复配音。未配置字幕时，
```
tutorial-demo
```
、
```
vlog-event
```
、
```
marketing-commerce
```
和
```
narrative-documentary
```
仍默认包含旁白；其他类别除非简报要求，否则旁白为可选项。如果已配置字幕但没有获授权的语音路径，则省略字幕，或在保留可编辑项目的前提下停止。
对于带旁白的编辑，从一开始就为每个短呼吸组生成独立的实体归档音频文件，并将每条字幕精确绑定到一个匹配的
```
audioClipId
```
；不要生成一个完整的旁白文件后再进行拆分。在句末标点处拆分，默认也在逗号、分号、冒号、破折号或其他清晰停顿处拆分。只有当拆分会形成无意义碎片，或破坏专有名词、数字、URL 或计划中的双语短语时，才保留边界。对于自由脚本生成，首个片段必须位于明确的播放头位置，后续片段必须追加在当前配音轨道末尾之后，绝不能重复使用未变化的播放头或
```
0s
```
；字幕范围的生成则锚定到对应字幕。将相邻旁白片段放置在统一的 desktop/H5 默认
```
0.4s
```
间隔处，然后根据已接受的音频序列推导字幕时间和画面时间。
移动或裁剪片段时，保留媒体身份和源时间映射。

3. Apply safely

3. 安全应用

Save a project version or export a
```
.timeline
```
archive before a destructive batch.
Apply one transaction per user-visible intent. Fail the whole transaction when a precondition fails.
Never silently substitute missing media, voices, models, fonts, or effects.
Keep every result undoable and editable in the normal UI.
Do not start a paid or remote generation job without a clear user request.
Do not put
```
output.render
```
in a command plan or claim that
```
project.run
```
renders video. Use the separate versioned
```
project.render
```
request for its documented portable subset, and use the browser editor for AI generation or unsupported composition features.
For a completed video-editing request, resolve an explicit absolute output directory and create both a portable
```
.timeline
```
project and the rendered result video there. Planning, diagnosis, annotation-only work, and an explicit editor-only handoff are exemptions. Annotation-only delivery needs a newly written, inspected
```
.timeline
```
archive; do not render an unchanged video merely to deliver markers.

在执行破坏性批量修改之前，保存项目版本或导出
```
.timeline
```
归档。
每个用户可见意图使用一个事务。当任一前置条件失败时，整个事务都应失败。
绝不能静默替换缺失的媒体、声音、模型、字体或特效。
确保每个结果都能在常规 UI 中撤销并继续编辑。
没有明确用户请求时，绝不能启动付费或远程生成任务。
不要在命令计划中放入
```
output.render
```
，也不要声称
```
project.run
```
会渲染视频。应单独使用版本化的
```
project.render
```
请求处理其文档规定的可移植子集；对于 AI 生成或不受支持的合成功能，应使用浏览器编辑器。
对于已完成的视频编辑请求，应解析明确的绝对输出目录，并在其中创建可移植的
```
.timeline
```
项目和渲染结果视频。规划、诊断、纯注释工作和明确的仅编辑器交付属于例外。纯注释交付需要新写入并经过检查的
```
.timeline
```
归档；不要仅为交付标记而渲染未修改的视频。

4. Verify the result

4. 验证结果

Re-read the timeline summary and compare it with the requested ordering, track placement, and enabled states. For narrated edits, confirm the final project duration follows the locked audio spine rather than an earlier runtime estimate.
Preview the opening, every cut or transition, caption boundaries, overlays, and the final frame.
Play the timeline continuously across every visual, caption, and audio boundary. The timeline clock must advance monotonically; reject any boundary that stalls, jumps backward, repeats a clip tail, or activates both adjacent half-open clips at once.
Check audible behavior, not just visible tracks. Distinguish embedded video audio from explicitly separated source-audio clips and verify mute/link state.
When placing stereo or multichannel audio with FFmpeg, apply every intended offset to every channel explicitly. For
```
adelay
```
, use
```
adelay=<milliseconds>:all=1
```
or provide one delay value per channel; a single value with the default
```
all=false
```
delays only the first channel and can pile every later clip into the other channel at time zero. Before delivery, compare left/right activity in the opening window and around every scheduled speech boundary. Reject channel-only early speech, multiple narration clips stacked at the opening, or undocumented interchannel onset skew.
Verify every visible caption resolves to one audible speech clip for its complete active interval. Reject orphan captions, silent linked clips, captions extending beyond speech, duplicate source-speech plus voiceover, or text-only caption delivery.
Verify adjacent Agent-generated narration clips are separate physical assets, use short phrase-level breath groups with commas treated as valid default split points, and retain the shared desktop/H5
```
0.4s
```
of intentional timeline space. Inspect the isolated speech bus at the opening and reject repeated free-script generations that share
```
0s
```
, reuse an unchanged playhead, or overlap before their scheduled starts. Also reject overlong multi-clause synthesis, a monolithic narration that was merely cut into ranges, meaningless micro-fragments, accidental overlaps, clipped breath/release tails, or picture timing that forced the accepted speech out of its natural cadence.
Listen to the complete narration at normal playback speed. Reject cold or mechanical timbre, flat pitch and energy, synthetic word-by-word delivery, rigidly equal pauses, rushed cadence, clipped pauses, unnatural pronunciation, segment-level speed changes, unexplained loudness jumps, or narration that was globally accelerated merely to hit a target duration. Require a warm, human, storyteller-like result with restrained pitch variation, phrase-level emphasis, and natural breath space unless the user explicitly requests another character. For phrase-scoped narration, measure every final stem after all processing; by default target
```
-18 LUFS
```
integrated and no higher than
```
-2 dBTP
```
, require the loudest-to-quietest segment spread to stay within
```
1 LU
```
, and keep segment LRA within
```
5 LU
```
unless an intentional exception is documented. Never accept a narration mix from full-program loudness alone, and do not rely on one-pass normalization of short clips as proof of consistency.
For final export, verify container, dimensions, duration, decoded frames, visible overlays/captions, and a real audio track.
Treat every artifact produced before a product or workflow fix as stale for delivery. A code or Skill edit is not a regenerated result: rerun the affected flow from a fresh project, export a new
```
.timeline
```
and result video under distinct paths, record their modification times and SHA-256 hashes, and compare them with the prior artifacts. Never present, relink, rename, or copy an old render as evidence of the fix.
For repeated free-script voice generation, run a minimum three-segment regression through the real UI. Reopen the exported
```
.timeline
```
and require exactly one segment at the initial playhead, every later start to equal the preceding end plus the planned gap within timeline precision, and no overlaps. Then inspect or decode the final rendered audio at the same boundaries; project structure alone is insufficient proof that the mix is correct.
When a review build must be unmistakably distinguishable from an earlier render, add a brief explicit verification slate or build marker and disclose it. Remove it from the clean final only after the new artifact has passed freshness, timeline, decode, and hash checks.
Reopen and verify the
```
.timeline
```
in Timeline Studio, not only with structural inspection: the main Visuals track must be visible, the first frame must render in Preview, archived media must resolve, and captions/audio/track state must match. Fully decode and verify the rendered video, then return both absolute paths.

重新读取时间线摘要，并将其与请求的顺序、轨道位置和启用状态进行比较。对于带旁白的编辑，确认最终项目时长遵循已锁定的音频主线，而不是较早的运行时长估计。
预览开头、每个剪切或转场、字幕边界、叠加层和最后一帧。
跨每个视觉、字幕和音频边界连续播放时间线。时间线时钟必须单调前进；拒绝任何停滞、倒退、重复片段尾部或同时激活两个相邻半开区间片段的边界。
检查可听行为，而不只是可见轨道。区分嵌入视频音频与明确分离的源音频片段，并验证静音/链接状态。
使用 FFmpeg 放置立体声或多声道音频时，必须将每个预期偏移显式应用到每个声道。对于
```
adelay
```
，使用
```
adelay=<milliseconds>:all=1
```
或为每个声道提供一个延迟值；使用默认值
```
all=false
```
只会延迟第一个声道，并可能将每个后续片段堆叠到另一声道的零时间位置。交付之前，比较开头窗口及每个计划语音边界处的左右声道活动。拒绝仅某声道提前出现的语音、开头叠加多个旁白片段或未记录的声道间起始偏移。
验证每个可见字幕在其完整生效区间内都对应一个可听的语音片段。拒绝孤立字幕、无声的关联片段、超出语音范围的字幕、源语音与配音重复，或纯文字字幕交付。
验证相邻的 Agent 生成旁白片段是独立实体素材，采用短句级呼吸组，将逗号视为有效的默认拆分点，并保留统一的 desktop/H5
```
0.4s
```
预期时间线间隔。检查开头处的独立语音总线，并拒绝重复的自由脚本生成共享
```
0s
```
、重复使用未变化的播放头或在计划开始时间之前重叠。同时拒绝过长多从句合成、仅被切分成范围的完整旁白、无意义的微小碎片、意外重叠、被截断的呼吸或收音尾部，以及迫使已接受语音偏离自然节奏的画面计时。
以正常播放速度完整收听旁白。拒绝冷硬或机械音色、平坦的音高和能量、逐词式的合成演绎、僵硬的等长停顿、仓促节奏、被截断的停顿、不自然发音、片段级速度变化、无法解释的响度跳变，或仅为达到目标时长而对整个旁白进行全局加速。除非用户明确要求其他声音角色，否则应要求温暖、贴近真人的讲述者效果，并具有克制的音高变化、句级强调和自然呼吸空间。对于句级旁白，在所有处理完成后测量每个最终 stem；默认目标为
```
-18 LUFS
```
整合响度且不高于
```
-2 dBTP
```
，要求最响与最轻片段之间的差距保持在
```
1 LU
```
内，并要求片段 LRA 保持在
```
5 LU
```
内，除非已记录有意例外。绝不能仅依据整个节目的响度接受旁白混音，也不能把短片段的一次性归一化当作一致性证明。
最终导出时，验证容器格式、尺寸、时长、解码帧、可见叠加层/字幕以及真实存在的音轨。
将产品或工作流修复之前生成的每个产物视为不适合交付的过期产物。代码或 Skill 修改不等于重新生成的结果：应从全新项目重新运行受影响的流程，在不同路径下导出新的
```
.timeline
```
和结果视频，记录其修改时间和 SHA-256 哈希，并与之前的产物进行比较。绝不能呈现、重新链接、重命名或复制旧渲染结果来证明修复已生效。
对于重复的自由脚本配音生成，通过真实 UI 运行至少三个片段的回归测试。重新打开导出的
```
.timeline
```
，要求初始播放头处恰好存在一个片段，每个后续片段的开始时间都等于前一片段结束时间加计划间隔，且误差在时间线精度范围内，同时不得重叠。然后在相同边界处检查或解码最终渲染音频；仅验证项目结构不足以证明混音正确。
当审阅版构建必须与之前的渲染结果明确区分时，添加简短、明确的验证 slate 或构建标记并进行说明。只有在新产物通过新鲜度、时间线、解码和哈希检查之后，才能将其从干净的最终版本中移除。
在 Timeline Studio 中重新打开并验证
```
.timeline
```
，不能只做结构检查：主 Visuals 轨道必须可见，Preview 中必须渲染第一帧，归档媒体必须能够解析，字幕、音频和轨道状态必须匹配。完整解码并验证渲染后的视频，然后返回两个绝对路径。

Interpret underspecified requests conservatively

保守解读不明确的要求

For “try it,” “open it,” or “let me edit” requests without an editorial brief, start the editor, import only the explicitly named assets, verify automatic placement, and hand off the live editable workspace.
Do not invent trims, captions, aspect-ratio changes, AI generation, or exports.
Treat an explicit request to “automatically edit,” “clean up,” “condense,” “make highlights,” or equivalent wording as permission to make reversible editorial decisions within the confirmed brief. State consequential defaults, protect category-specific content, and report the decisions; do not treat that request as a mere handoff.
Treat persistent onboarding completion, model downloads, remote generation, and destructive reset as separate user decisions.

对于“试试”“打开它”或“让我编辑”等没有剪辑简报的请求，应启动编辑器，只导入明确指定的素材，验证自动放置结果，并交付实时可编辑工作区。
绝不能自行添加裁剪、字幕、宽高比变更、AI 生成或导出。
将“自动编辑”“清理”“精简”“制作高光片段”或类似表述视为在已确认简报范围内作出可逆剪辑决定的许可。说明重要的默认设置，保护分类专属内容，并报告所作决定；不要将该请求视为单纯交付。
将完成新手引导、下载模型、远程生成和破坏性重置视为彼此独立且需要用户分别决定的事项。

Learn from every real run

从每次真实运行中学习

For editor evaluation, regression work, or any run that exposes friction, read references/e2e-evaluation.md. For automatic-editing evaluation, also read references/auto-edit-scenarios.md and use its fixed category cards, clarification checks, hard gates, and adjacent stress variants. Capture the attempted action, observed result, evidence, fallback, and verification. Classify the finding as product, browser-control, environment, or skill guidance. Update the smallest relevant skill instruction or reference, validate the skill, reinstall the local copy, and rerun the affected scenario plus adjacent smoke tests. Never weaken an assertion merely to make a test pass.

对于编辑器评估、回归工作或任何暴露摩擦问题的运行，阅读 references/e2e-evaluation.md。对于自动编辑评估，还应阅读 references/auto-edit-scenarios.md，并使用其中固定的分类卡片、澄清检查、硬性门槛和相邻压力变体。记录尝试执行的动作、观察结果、证据、fallback 和验证情况。将问题分类为产品、浏览器控制、环境或 Skill 指导问题。更新最小范围内的相关 Skill 指令或参考文档，验证 Skill，重新安装本地副本，然后重新运行受影响的场景及相邻冒烟测试。绝不能为了使测试通过而削弱断言。

Capability boundaries

能力边界

Read references/host-environment.md for host dependency checks and approved installation, and references/voiceover-workflow.md before Agent-driven narration or pre-voiceover generation.

Read references/current-capabilities.md when deciding whether a request can be executed now. Read references/webmcp-integration.md when editing a project already open in a browser that exposes Timeline Studio tools. Read references/mcp-integration.md when connecting or invoking the bundled MCP server, and references/command-contract.md when implementing or invoking the underlying Agent command layer. Read references/local-model-routing.md before model-assisted analysis or enhancement. Read references/remote-video-generation.md before selecting or calling a remote video generator, digital-human service, or programmable composition service. Read references/web-footage-sourcing.md for provider-neutral, current web and short-video footage suggestions. Read references/browser-workflow.md for UI execution, references/auto-edit-workflow.md for category-aware automatic editing, references/promotion-narrative-workflow.md for evidence-backed product and promotional storytelling with closed-loop cases, references/replication-workflow.md for editing-style and AI-generation remakes, references/highlight-tension-workflow.md for peak hierarchy and tension shaping, references/curves-and-subject-effects.md for speed curves, Color Wheels, cutout, outline, and authorized face-swap shot design, references/professional-editing-workflow.md for shared media analysis, generation negotiation, stabilization, enhancement, and artifact delivery, references/auto-edit-scenarios.md for its repeatable category matrix, and references/e2e-evaluation.md for repeated experience-driven testing.

For public explanations, route one question to one page: use docs/agent-video-editing.md for what Timeline Studio is; the platform guide for Codex, Claude Code, GitHub Copilot, or Gemini CLI for discovery and invocation; docs/examples.md for reproducible cases; docs/command-reference.md for exact runner syntax; and docs/comparison.md for FFmpeg, CapCut, and Remotion comparisons. Do not load all public pages unless the user asks for a broad overview.

If a requested operation is unsupported, keep the valid partial timeline unchanged and state the exact missing command or runtime capability.

阅读 references/host-environment.md 以了解宿主依赖检查和获批准的安装操作；在执行 Agent 驱动的旁白或预配音生成之前，阅读 references/voiceover-workflow.md。

判断请求当前能否执行时，阅读 references/current-capabilities.md。编辑宿主浏览器中已打开且提供 Timeline Studio 工具的项目时，阅读 references/webmcp-integration.md。连接或调用捆绑的 MCP 服务器时，阅读 references/mcp-integration.md；实现或调用底层 Agent 命令层时，阅读 references/command-contract.md。进行模型辅助分析或增强之前，阅读 references/local-model-routing.md。选择或调用远程视频生成器、数字人服务或可编程合成服务之前，阅读 references/remote-video-generation.md。阅读 references/web-footage-sourcing.md，获取平台中立、当前的网络和短视频素材建议。阅读 references/browser-workflow.md 了解 UI 执行，阅读 references/auto-edit-workflow.md 了解分类感知的自动编辑，阅读 references/promotion-narrative-workflow.md 了解有证据支持的产品与推广叙事及闭环案例，阅读 references/replication-workflow.md 了解 editing-style 和 AI-generation 重制，阅读 references/highlight-tension-workflow.md 了解峰值层级和张力塑造，阅读 references/curves-and-subject-effects.md 了解速度曲线、Color Wheels、cutout、outline 和获授权的 face swap 镜头设计，阅读 references/professional-editing-workflow.md 了解共享媒体分析、生成协商、稳定、增强和产物交付，阅读 references/auto-edit-scenarios.md 了解可重复的分类矩阵，阅读 references/e2e-evaluation.md 了解基于实际体验的重复测试。

对于公开说明，应将每个问题路由到对应页面：使用 docs/agent-video-editing.md 介绍 Timeline Studio；使用 Codex、Claude Code、GitHub Copilot 或 Gemini CLI 的平台指南了解发现与调用方式；使用 docs/examples.md 查看可复现案例；使用 docs/command-reference.md 查看准确的 runner 语法；使用 docs/comparison.md 比较 FFmpeg、CapCut 和 Remotion。除非用户要求广泛概览，否则不要加载所有公开页面。

如果请求的操作不受支持，应保持有效的部分时间线不变，并准确说明缺少的命令或运行时能力。