Tiktok Script

Organization

social-media-skills

tiktok-script

Use to write a TikTok script — a native, sound-aware short-video script optimized for TikTok's discovery engine (the FYP), built around a brutal 1-second hook, watch-time, and rewatches. Run when the user says "TikTok script," "TikTok video," "script for TikTok," "make a TikTok," "storytime," "TikTok hook," or wants short-form video for TikTok specifically. Reads brand-profile and voice first; rides a trending sound/format where it genuinely fits (live trend research goes to trend-jacking); structures for completion + rewatch; optimizes for TikTok search; outputs a production doc (shot - on-screen text - spoken - sound - timing) plus a Veo prompt pack for faceless/b-roll shots (native filming often beats AI on TikTok). For Instagram Reels use reels-script; for YouTube Shorts use youtube-shorts; for the platform-agnostic scripting craft use short-form-video-script; hands caption to caption-writer and scheduling to scheduling-and-queue.

Overview

Publisher	social-media-skills
Repository	`skills`
Skill name	`tiktok-script`
Stars	215
Forks	44
Bundled files	6
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.
6 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 Script 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-script
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-script .claude/skills/tiktok-script

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

Use it in TypingMind

Enable Tiktok Script 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 Script 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 Script 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 Script

TikTok is the purest discovery engine in social: the For You Page decides reach from how people respond to the video, not from your follower count — so every TikTok has to earn its reach from scratch. That makes the rules specific, and different from Reels:

The hook is brutal — ~1 second. Stop the scroll instantly on three channels (verbal + on-screen text + visual) or the video is invisible.
Watch-time and rewatches are everything. Design for completion and a loop, not just a hook.
Make TikToks, not ads. Native, authentic, slightly-raw content beats polished/ad-like content. This is the biggest brand mistake on TikTok — and the pushback this skill makes.
Sound and trends are part of discovery — ride them where they fit, never forced.
TikTok is also a search engine — keywords (spoken + on-screen + caption) get you found.

(Full mechanics in references/tiktok-mechanics.md.)

Step 0 — Read the foundation first

Load brand-profile.md and voice.md. Voice carries into the spoken script and the caption. Carry guardrails and compliance rules.

Step 1 — Lock the concept, goal, and format

One idea — a TikTok does one thing.
Goal — reach, saves, follows, or comments (shapes the close/CTA).
Format — talking head, storytime, POV, tutorial, listicle, green-screen, Stitch/Duet, or faceless voiceover. Match it to the message and who's making it. See references/formats-and-sound.md.

Step 2 — Decide the sound

Ride a trending sound only where it genuinely fits; otherwise use original audio (most brand/founder content) or a commercial-safe music bed. A forced trend hurts. For live trend research and timing, hand off to trend-jacking. See references/formats-and-sound.md.

Step 3 — Write the 1-second hook

Use hook-writer. Fire the hook on all three channels at once in the first ~1–3 seconds — no intro, no logo, no "hey guys." It must be true (no clickbait the video won't pay off). See references/hooks-and-retention.md.

Step 4 — Structure for watch-time and the loop

Front-load value, keep an open loop, cut all dead air, and design a loop or rewatch trigger so the ending feeds the start (rewatches are one of the strongest FYP signals). Re-hook mid-video for longer scripts. See references/hooks-and-retention.md.

Step 5 — Write the production doc

Output a shootable doc — a row per beat with shot · on-screen text · spoken · sound · timing — so it can be filmed or generated as-is, not a vague paragraph.

Step 6 — TikTok SEO + caption + hashtags

Place target keywords in the spoken script, on-screen text, and caption (TikTok reads all three). Use keyword + niche hashtags, not generic high-volume ones. Hand the caption to caption-writer.

Step 7 — Production: film-first, or the Veo pack

Default to native filming for faces/voices (it out-trusts AI on TikTok). For faceless niches, b-roll, or unfilmable concepts, use the bundled Veo prompt pack (references/veo-prompt-pack.md; API layer in tools/integrations/veo.md) — generated "native/handheld," not glossy. AI-disclosure is auto on TikTok via WoopSocial.

Step 8 — Hand off

Caption → caption-writer.
Schedule → scheduling-and-queue (upload the video to WoopSocial Media, then schedule).

Quality bar — self-check

Does the hook land in ~1 second on all three channels, with no intro tax?
Is it built for watch-time (fast, no dead air) with a loop/rewatch trigger?
Is the sound chosen intentionally and does it actually fit?
Is it native, not ad-like?
Are TikTok-search keywords in spoken + on-screen + caption?
Is the output a shootable production doc?
On-voice; truthful hook; AI-disclosure where generated?

Edge cases & pushback

"Make it a polished ad with our tagline" → push back: ad-style underperforms on TikTok; deliver a native version that still hits the goal.
"Put the trending dance sound on our B2B explainer" → don't force a mismatched trend; pick a sound/format that fits, or original audio.
"Generate it with AI instead of filming" → fine for faceless/b-roll, but flag that filming often wins on TikTok; recommend honestly.
Thin concept → shape the one idea; don't pad to fill time.
Repurposing a Reel → re-fit for TikTok (native tone, sound, search keywords), don't cross-post the watermarked identical file — see cross-platform-repurposing.
Regulated/sensitive → carry guardrails; only verifiable claims; required disclaimers.

Related skills

brand-profile, voice-builder — voice + guardrails.
short-form-video-script — the master scripting craft this specializes for TikTok.
hook-writer — the 1-second hook.
trend-jacking — live trend/sound research and timing.
reels-script — Instagram Reels; youtube-shorts — Shorts; cross-platform-repurposing — adapt across them.
caption-writer — the caption; scheduling-and-queue — schedule the post.
tools/integrations/veo.md — the Veo API/connection layer.

References

references/tiktok-mechanics.md — the FYP discovery engine, signals, native rule, TikTok SEO, length.
references/hooks-and-retention.md — the 1-second hook, watch-time tactics, loop/rewatch design.
references/formats-and-sound.md — TikTok formats + sound/trend strategy and the fit test.
references/veo-prompt-pack.md — AI-video pack for faceless/b-roll, with the native-beats-AI caveat.
references/examples.md — worked production docs, with loops + SEO, vs a polished-ad version.

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 Script AI skill do?

Why use Tiktok Script on TypingMind?

Because you install it once and use it with any model. Tiktok Script 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 Script in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/tiktok-script. 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 Script?

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 Script?

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

Is the Tiktok Script 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

Distributed Triage

pytorch

OrganizationPopular

Sub-triages issues in the oncall:distributed queue by assigning distributed module labels, routing to sub-oncalls, and marking triaged. Use when an issue has been routed to oncall:distributed and…

Hyperframes

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video…

Audio Jingle

Audio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or…

Proof Video

Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

TikTok Script

Step 0 — Read the foundation first

Step 1 — Lock the concept, goal, and format

Step 2 — Decide the sound

Step 3 — Write the 1-second hook

Step 4 — Structure for watch-time and the loop

Step 5 — Write the production doc

Step 6 — TikTok SEO + caption + hashtags

Step 7 — Production: film-first, or the Veo pack

Step 8 — Hand off

Quality bar — self-check

Edge cases & pushback

Related skills

References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now