Tiktok Video Publishing

Organization

social-media-skills

tiktok-video-publishing

The TikTok VIDEO publish-config skill. Use when someone wants to "publish/schedule a TikTok video," "configure a TikTok upload," set the caption/cover/privacy/duet-stitch/disclosure, or post a TikTok video via WoopSocial (postType VIDEO). Configures the publish for reach, discovery, and compliant disclosure AND writes the search-optimized caption: the caption is search (lead-load the primary keyword), duet/ stitch ON is free distribution, the cover frame wins the profile grid + search, and the disclosure flags (isBrandedContent/isYourBrand) are set truthfully. Uses the REACH framework. Reads brand-profile + goals-and-kpis + the script/video first. The VIDEO FILE is filmed by a human or made by the video skills (not WoopSocial); WoopSocial publishes via raw-bytes upload and auto-discloses AI on TikTok; trending sound / pinned comment / replies are native or human; no update endpoint (edit = delete+recreate); metrics never fabricated. Distinct from tiktok-script (the VIDEO SCRIPT) and tiktok-photo-mode (PHOTO).

Overview

Publisher	social-media-skills
Repository	`skills`
Skill name	`tiktok-video-publishing`
Stars	215
Forks	44
Bundled files	5
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by social-media-skills on GitHub. Read the source before you install it.

Installation

Install the Tiktok Video Publishing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/social-media-skills/skills/tree/main/skills/tiktok-video-publishing
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/tiktok-video-publishing .claude/skills/tiktok-video-publishing

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tiktok Video Publishing in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tiktok Video Publishing on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tiktok Video Publishing is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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.

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

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.

Read these first

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.

The framework: 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.

The reality (verify-quarterly)

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.

Honest scope (never violate)

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.)

Distinct from its siblings (route correctly)

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.

Where this connects

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.

Definition of done

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.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Tiktok Video Publishing AI skill do?

Why use Tiktok Video Publishing on TypingMind?

Because you install it once and use it with any model. Tiktok Video Publishing is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tiktok Video Publishing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/tiktok-video-publishing. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Tiktok Video Publishing?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tiktok Video Publishing?

As many as you like. As long as a model supports skills, you can use Tiktok Video Publishing with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tiktok Video Publishing AI skill free?

Yes. It is published on GitHub by social-media-skills under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Audiocraft Audio Generation

NousResearch

OrganizationPopular

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

Brag Slim

Launch video from a project or URL, upstream-maintained.

Brag

Project launch video via Hyperframes, upstream-maintained.

Comfyui

Generate images, video, and audio via diffusion workflows.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

tiktok-video-publishing

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

Read these first

The framework: REACH

The reality (verify-quarterly)

Honest scope (never violate)

Distinct from its siblings (route correctly)

Where this connects

Definition of done

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now