tiktok-video-publishing

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

tiktok-video-publishing

A format-execution skill — configure the TikTok VIDEO publish for reach + discovery + compliant disclosure and write the search-optimized caption. The agent configures the publish + writes the caption; the video FILE is an input; WoopSocial publishes via
postType=VIDEO
and auto-discloses AI on TikTok.

这是一个 format-execution skill——用于配置 TikTok VIDEO 发布，以提升触达 + 发现度并实现合规 disclosure，同时撰写经过搜索优化的 caption。Agent 配置发布 + 撰写 caption；video FILE 是输入；WoopSocial 通过
postType=VIDEO
发布，并自动在 TikTok 上披露 AI 内容。

The POV: the publish config is the most controllable reach layer

核心视角：发布配置是最可控的触达层

The script gets filmed once, but the publish config is set at upload and is the most controllable reach/ SEO layer. Four levers: the caption is search (TikTok is a search engine; only the first ~100–150 chars show — lead with the primary keyword, not a teaser); duet/stitch ON is free distribution (others remixing your video grows its engagement cluster); the cover frame wins the profile grid + search; and disclosure (the

isBrandedContent

isYourBrand

flags) keeps you compliant. The video file is an input — this skill makes it land correctly and get found.

Script 只需拍摄一次，但发布配置是在上传时设置的，也是最可控的触达/SEO 层。有四个杠杆：caption 就是搜索（TikTok 是搜索引擎；只有最前面的约 100–150 个字符会显示——要以 primary keyword 开头，而不是用 teaser 吊胃口）；开启 duet/stitch 等于免费分发（他人 remix 你的视频会扩大其 engagement cluster）；cover frame 能赢得个人主页网格 + 搜索；以及 disclosure（
isBrandedContent
/
isYourBrand
flags）确保内容合规。video file 是输入——此 skill 会让它正确落地并被找到。

Read these first

先读取以下内容

brand-profile — voice/niche (and the search phrasing the audience uses).
goals-and-kpis — the goal (reach / saves / shop conversions).
the script/video (often from tiktok-script) — the topic to optimize the caption around.

brand-profile——品牌语气/垂直领域（以及受众使用的搜索表达方式）。
goals-and-kpis——目标（触达 / 收藏 / 店铺转化）。
script/video（通常来自 tiktok-script）——用于围绕其优化 caption 的主题。

The framework: REACH

框架：REACH

(Depth:

references/the-reach-framework.md

R — Rank the caption: lead-load the primary keyword (first ~100 chars) → value-prop → secondary keywords + niche hashtags; long-tail; mirror in on-screen text.
E — Engage-open settings:
```
allowComment
```
/
```
allowDuet
```
/
```
allowStitch
```
ON for reach (restrict only for genuine brand-safety).
A — Attract with the cover: a legible title-card
```
cover
```
image (the video's cover/thumbnail) that wins the profile grid + search.
C — Confirm disclosure:
```
isBrandedContent
```
/
```
isYourBrand
```
truthfully, #ad up front; AI auto-disclosed on TikTok but prohibited AI uses stay prohibited; branded content can't be private.
H — Handle mode + specs + validate:
```
privacyLevel
```
from platform-inputs;
```
DIRECT_POST
```
vs
```
MEDIA_UPLOAD
```
(trending sound); 1080×1920 9:16, ≤1GB, cap from
```
maxVideoPostDurationSec
```
; validate; no update → delete+recreate.

（详细内容：

references/the-reach-framework.md

。）

R — 对 caption 排序： 在前部加载 primary keyword（前约 100 个字符）→ value-prop → secondary keywords + niche hashtags；采用 long-tail 关键词；同步反映在屏幕文字中。
E — 开启互动设置： 为提升触达，将
```
allowComment
```
/
```
allowDuet
```
/
```
allowStitch
```
设为 ON（仅在确有 brand-safety 风险时限制）。
A — 用 cover 吸引： 使用清晰易读的 title-card
```
cover
```
image（视频的 cover/thumbnail），赢得个人主页网格 + 搜索。
C — 确认 disclosure： 如实设置
```
isBrandedContent
```
/
```
isYourBrand
```
，并将 #ad 放在前面；TikTok 会自动披露 AI 内容，但被禁止的 AI 用法仍属禁止范围；branded content 不能设为 private。
H — 处理模式 + 规格 + 验证： 从 platform-inputs 获取
```
privacyLevel
```
；选择
```
DIRECT_POST
```
或
```
MEDIA_UPLOAD
```
（trending sound）；1080×1920 9:16，≤1GB，上限由
```
maxVideoPostDurationSec
```
决定；验证；没有 update → delete + recreate。

The reality (verify-quarterly)

实际情况（每季度核验）

Caption-as-search (first ~100 chars, long-tail, Google surfacing, hashtag lift, pinned-comment = native); duet/stitch/comments as reach levers; cover wins profile grid + search; privacy + disclosure (branded vs your-brand, AI labels/prohibited uses, branded-can't-be-private); specs + length + DIRECT_POST vs MEDIA_UPLOAD (trending sound):

references/video-publishing-2026-reality.md

. Caption-SEO formula, reach-settings defaults, the full VIDEO publish-config block + worked examples:

references/publish-config-and-recipes.md

将 caption 用作搜索（前约 100 个字符、long-tail、在 Google 中出现、hashtag 提升效果、pinned-comment = 原生功能）；duet/stitch/comments 可作为触达杠杆；cover 赢得个人主页网格 + 搜索；privacy + disclosure（branded 与 your-brand 的区别、AI 标签/禁止用法、branded 不能设为 private）；规格 + 时长 +

DIRECT_POST

与

MEDIA_UPLOAD

（trending sound）：

references/video-publishing-2026-reality.md

。Caption-SEO 公式、reach-settings 默认值、完整的 VIDEO 发布配置块 + 实例：

references/publish-config-and-recipes.md

。

Honest scope (never violate)

诚实的能力边界（绝不违反）

The agent configures the publish + writes the caption. The video FILE is filmed by a human or made by the video skills (
```
veo-3
```
/
```
luma
```
/
```
kling
```
+ edited) — WoopSocial doesn't film/edit/generate video.
WoopSocial publishes via
postType=VIDEO
(raw-bytes upload) and auto-discloses AI on TikTok. No update → edit = delete + recreate (only while
```
NOT_STARTED
```
).
Native/human: pinned comment + replies (no comment surface) and licensed trending sound (use
```
MEDIA_UPLOAD
```
). Disclosure truthful; prohibited AI uses stay prohibited; branded content can't be private. Never promise the FYP/virality; never fabricate metrics (native analytics only). (Scope, distinctions + connections:
```
references/scope-and-connections.md
```
.)

**Agent 负责配置发布 + 撰写 caption。**video FILE 由真人拍摄，或由视频 skills（
veo-3
/
luma
/
kling
+ 编辑）制作——WoopSocial 不负责拍摄、编辑或生成视频。
WoopSocial 通过
postType=VIDEO
发布（raw-bytes upload），并会**在 TikTok 上自动披露 AI 内容。**没有 update → 编辑 = 删除 + 重新创建（仅在
```
NOT_STARTED
```
状态下可行）。
原生/人工：pinned comment + replies（无 comment surface）和获得许可的 trending sound（使用
```
MEDIA_UPLOAD
```
）。**Disclosure 必须如实；被禁止的 AI 用法仍属禁止范围；branded content 不能设为 private。**绝不承诺进入 FYP 或实现爆款；绝不捏造 metrics（仅使用原生 analytics）。（范围、区别 + 关联：
```
references/scope-and-connections.md
```
。）

Distinct from its siblings (route correctly)

与同类 skill 的区别（正确路由）

tiktok-video-publishing (this) = the VIDEO publish-config + search caption (duet/stitch/cover apply; autoAddMusic ignored) · tiktok-script = writes the VIDEO SCRIPT (the content) · tiktok-photo-mode = the PHOTO carousel (autoAddMusic applies; duet/stitch/cover don't) · reels-script/youtube-shorts = other video formats · caption-writer/hook-writer = generic copy.

tiktok-video-publishing（当前 skill） = VIDEO 发布配置 + 搜索 caption（适用 duet/stitch/cover；忽略 autoAddMusic）· tiktok-script = 撰写 VIDEO SCRIPT（内容本身）· tiktok-photo-mode = PHOTO 轮播（适用 autoAddMusic；不适用 duet/stitch/cover）· reels-script/youtube-shorts = 其他视频格式 · caption-writer/hook-writer = 通用文案。

Where this connects

关联关系

Reads first: brand-profile, goals-and-kpis, the script/video (tiktok-script). Content inputs (external to WoopSocial): tiktok-script, the video cluster (veo-3/luma/kling) + editing, image-prompt/ideogram/nano-banana (cover frame), hook-writer/caption-writer. Publish: scheduling-and-queue → WoopSocial (

postType=VIDEO

), platform-specs-and-validation (validate + field rules), content-calendar. Engage/reuse/measure: community-management (pinned comment + replies), content-recycling (→ Reels/Shorts), analytics-and-reporting, experimentation-and-ab-testing (A/B caption/cover). Filming/editing, trending sound, and comments stay external/native.

首先读取：brand-profile、goals-and-kpis、script/video（tiktok-script）。内容输入（WoopSocial 外部）：tiktok-script、video skill 集群（veo-3/luma/kling）+ editing、image-prompt/ideogram/nano-banana（cover frame）、hook-writer/caption-writer。发布：scheduling-and-queue → WoopSocial（

postType=VIDEO

）、platform-specs-and-validation（验证 + 字段规则）、content-calendar。互动/复用/衡量：community-management（pinned comment + replies）、content-recycling（→ Reels/Shorts）、analytics-and-reporting、experimentation-and-ab-testing（A/B caption/cover）。拍摄/编辑、trending sound 和 comments 保持外部/原生。

Definition of done

完成标准

A search-optimized caption (primary keyword lead-loaded, value-prop, secondary keywords + niche hashtags, mirrored in on-screen text); reach settings open (comment/duet/stitch ON unless brand-safety); a legible title-card cover frame; truthful disclosure flags with #ad up front (and AI auto-disclosed, prohibited AI uses excluded, branded never private); the full WoopSocial VIDEO config (postType VIDEO, privacyLevel from platform-inputs, postMode chosen, specs right) validated before publish; the video file produced externally, WoopSocial publishing postType VIDEO with AI auto-disclosure, edits via delete+recreate, trending sound/pinned comment/replies left native, nothing fabricated and no promised FYP; correctly distinguished from tiktok-script and tiktok-photo-mode.

经过搜索优化的 caption（在前部加载 primary keyword、value-prop、secondary keywords + niche hashtags，并同步反映在屏幕文字中）；reach 设置保持开放（除非涉及 brand-safety，否则 comment/duet/stitch 设为 ON）；清晰易读的 title-card cover frame；如实设置 disclosure flags，并将 #ad 放在前面（AI 自动披露，排除被禁止的 AI 用法，branded content 绝不设为 private）；发布前验证完整的 WoopSocial VIDEO 配置（postType VIDEO、privacyLevel from platform-inputs、选定 postMode、规格正确）；video file 在外部生成，由 WoopSocial 以 postType VIDEO 发布并自动披露 AI，编辑采用 delete+recreate，trending sound/pinned comment/replies 保持原生，不捏造任何内容，也不承诺进入 FYP；正确区分 tiktok-script 和 tiktok-photo-mode。