find-broll

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Find B-roll

查找 B-roll

Source cutaways that illustrate what the speaker means, not merely the nearest noun. Prefer a small number of accurate, authoritative assets over broad stock search or decorative coverage.
Set
SKILL_DIR
to the absolute directory containing this file. Use the adjacent
analyze-video-editing
skill when the source needs transcription or editorial analysis. Use the adjacent
video-editing
skill for compositing, audio preservation, rendering, review artifacts, and final validation.
查找能够表达说话者含义的切镜,而不只是匹配最近的名词。相比广泛搜索图库或堆砌装饰性画面,应优先使用少量准确、权威的素材。
将
SKILL_DIR
设置为包含此文件的绝对目录。当来源需要转录或编辑分析时,使用相邻的
analyze-video-editing
skill。当来源需要合成、保留音频、渲染、生成审阅产物和最终验证时,使用相邻的
video-editing
skill。

Establish the contract

确定协作契约

Inspect the real source before planning. Accept a transcript, a word-timestamp transcript, or local video/audio. If only media is supplied, transcribe once with word timestamps and preserve the raw output.
Capture only preferences that materially change sourcing:
  • delivery aspect ratio and duration;
  • desired coverage density and whether the hook is denser than the body;
  • allowed source types and any explicit bans;
  • whether clip audio is stripped or intentionally mixed;
  • source-credit preference;
  • existing brand tokens or Remotion project for concept graphics;
  • any user-owned library, channels, or must-include assets.
User overrides apply immediately for the rest of the run. Do not infer licensing permission, brand ownership, or consent from availability.
在制定方案前检查实际来源。可接受转录稿、带逐词时间戳的转录稿,或本地视频/音频。如果只提供了媒体文件,则进行一次带逐词时间戳的转录,并保留原始输出。
只记录会实质影响素材查找的偏好:
  • 交付宽高比和时长;
  • 期望的素材覆盖密度,以及开头钩子是否比正文更密集;
  • 允许的来源类型及任何明确禁用项;
  • 是否移除片段音频,或有意混合片段音频;
  • 来源署名偏好;
  • 用于概念图形的现有品牌视觉元素或 Remotion 项目;
  • 用户自有素材库、频道或必须纳入的素材。
用户在运行过程中给出的覆盖指令会立即适用于后续步骤。不得根据素材可获取这一点推断许可、品牌所有权或同意。

Plan before downloading

下载前规划

Read the whole transcript and state its thesis. Then create an annotated beat plan with:
  1. stable beat ID;
  2. exact narration and anchor word;
  3. one-sentence interpretation of what the line means;
  4. route:
    receipt
    ,
    entity
    ,
    product
    ,
    concept
    ,
    archival
    , or
    cultural
    ;
  5. proposed source type and why it is authoritative;
  6. intended duration and output placement;
  7. status:
    planned
    ,
    sourced
    ,
    approved
    ,
    placed
    , or
    dropped
    .
Walk the full palette before dropping a meaningful beat, but never pad. A correct empty space is better than a wrong cutaway. Read references/sourcing-and-routing.md when choosing routes or search strategies.
Treat plan approval as authorization for read-only research and downloading public candidates. Ask separately before paid acquisition, publishing, signing in with new credentials, or sending anything externally.
通读整份转录稿并说明其核心论点。然后创建一份带注释的 beat 方案,包含:
  1. 稳定的 beat ID;
  2. 准确的旁白文本和锚定词;
  3. 用一句话解释这句话的含义;
  4. 路线:
    receipt
    、
    entity
    、
    product
    、
    concept
    、
    archival
    或
    cultural
    ;
  5. 建议的来源类型,以及其为何具有权威性;
  6. 预期时长和输出位置;
  7. 状态:
    planned
    、
    sourced
    、
    approved
    、
    placed
    或
    dropped
    。
在舍弃任何有意义的 beat 前,应遍历完整的素材候选范围,但绝不要为了凑数而添加素材。正确的留白优于错误的切镜。选择路线或搜索策略时,读取 references/sourcing-and-routing.md。
将方案获批视为进行只读研究和下载公开候选素材的授权。付费采购、发布、使用新凭据登录或对外发送任何内容之前,必须另行征得许可。

Source by authority

按权威性查找来源

Cluster the approved beats by source so each page, channel, or film is fetched once. Search metadata first; download only likely winners.
  • Receipts: use the authentic post, headline, study, pricing page, review, or metric.
  • People and entities: use the official or primary source and match the moment to the claim, not just the name.
  • Products and interfaces: prefer the user's own current recording, then the official current demonstration.
  • Concepts: create a restrained brand-consistent graphic, or use authoritative real footage when one exists.
  • Archival material: prefer canonical archives with explicit provenance and usage terms.
  • Cultural or reaction clips: use the user's curated library; do not blind-pick memes.
Inspect real search and metadata payloads before writing parsers or choosing formats. Record the canonical URL, creator, title, publication date, capture/download time, rights or usage note, and exact source interval. Reject watermarks, synthetic stock presented as real, burned-in captions that conflict with the edit, stale product interfaces, and sources whose provenance cannot be explained.
The agent may select one best candidate for an objective route when the evidence is unambiguous. Present choices for subjective or taste-sensitive routes, and preserve the user's final selection in the manifest.
按来源对已批准的 beat 聚类,使每个页面、频道或影片只获取一次。优先搜索元数据;只下载最有可能入选的素材。
  • **佐证素材(Receipts):**使用真实的帖子、标题、研究、定价页、评测或指标。
  • **人物与实体:**使用官方或一手来源,并让画面与具体主张相匹配,而不只是匹配名称。
  • **产品与界面:**优先使用用户自己的最新录屏,其次使用官方当前演示。
  • **概念:**制作克制且符合品牌风格的图形;若存在权威的真实影像,也可使用。
  • **档案素材:**优先使用来源和使用权条款明确的标准档案库。
  • **文化或反应片段:**使用用户策划的素材库;不要随意挑选梗图。
在编写解析器或选择格式前,检查真实的搜索结果和元数据负载。记录规范 URL、创作者、标题、发布日期、捕获或下载时间、权利或使用说明,以及确切的来源区间。拒绝带有水印、被伪装成真实素材的合成图库、与剪辑冲突的烧录字幕、过期产品界面,以及无法说明来源溯源的素材。
对于证据明确的客观路线,Agent 可以选择一个最佳候选。对于主观或审美敏感的路线,应提供选项,并在 manifest 中保留用户的最终选择。

Place on meaning

按语义放置

Anchor a cutaway to the spoken word or phrase it illustrates, usually 0.2–0.5 seconds after the word begins. Never reveal the answer before the narration says it. Bias slightly late when timestamps are uncertain.
Keep source time and output time distinct. Strip external clip audio unless the edit explicitly calls for it. Use full-frame cover crop only when it preserves the subject; use a designed background for partial-frame or portrait material. Static receipts may remain still or use truly sub-pixel motion—never integer-stepped FFmpeg
zoompan
.
Write every approved choice to a project-local manifest before rendering. Read references/manifest-and-timing.md for the fields and timing checks.
将切镜锚定到其所表达的口播词语或短语,通常在该词开始后 0.2–0.5 秒处。绝不要在旁白说出答案之前提前揭示答案。时间戳不确定时,应略微偏晚。
明确区分来源时间和输出时间。除非剪辑明确要求,否则移除外部片段的音频。仅当全画幅 cover 裁切不会破坏主体时才使用;对于局部画面或竖屏素材,使用经过设计的背景。静态佐证素材可以保持静止,也可以采用真正的亚像素级运动——绝不要使用按整数步进执行的 FFmpeg
zoompan
。
渲染前,将每个获批选择写入项目本地的 manifest。字段和时序检查请参阅 references/manifest-and-timing.md。

Verify the render

验证渲染结果

Use the adjacent
video-editing
workbench to render a low-resolution candidate first. Generate:
  • a midpoint frame for every placed beat;
  • a strip around every B-roll entrance and exit;
  • a contact sheet covering the full sequence;
  • a technical validation report for the final deliverable.
Inspect the actual images. Confirm the source is the intended one, the cut lands after the anchor, the subject survives the crop, no flash of talking head appears between adjacent cutaways, captions and overlays remain readable, audio continuity is intact, and every
approved
beat appears exactly once.
Deliver the master with the B-roll manifest, source list, approval state, review artifacts, validation report, and checksum. Never redistribute unused source media.
使用相邻的
video-editing
工作台,先渲染低分辨率候选版本。生成:
  • 每个已放置 beat 的中间帧;
  • 每个 B-roll 进入和退出点周围的连续画面带;
  • 覆盖完整序列的 contact sheet(接触印片表);
  • 最终交付物的技术验证报告。
检查实际生成的图像。确认来源符合预期,切镜落在锚定词之后,主体在裁切后仍完整可见,相邻切镜之间没有闪现真人出镜画面,字幕和叠加图层仍然清晰可读,音频连续性未受影响,并且每个
approved
beat 恰好出现一次。
交付母版,并附上 B-roll manifest、来源列表、审批状态、审阅产物、验证报告和校验和。绝不重新分发未使用的源媒体。

Attribution

来源说明

This workflow adapts the MIT-licensed B-Roll Finder methodology by Louise De Sadeleer. The implementation is integrated with this repository's existing analysis, rendering, and validation contracts; third-party media retains its own rights and terms.
此工作流改编自 Louise De Sadeleer 的 MIT 许可项目 B-Roll Finder 方法。其实现已与本仓库现有的分析、渲染和验证契约集成;第三方媒体仍保留各自的权利和使用条款。