Tiktok Photo Mode

Organization

social-media-skills

tiktok-photo-mode

The TikTok Photo Mode format-execution skill. Use when someone wants a "TikTok photo carousel," "photo mode," "TikTok slideshow," "swipeable TikTok post," or to publish a multi-image TikTok post via WoopSocial (postType PHOTO). Builds a TikTok-native carousel that wins on completion rate — hook slide 1, progressive reveal with cliffhangers, reward + one CTA — AND sets the exact WoopSocial PHOTO publish config (privacy, comments, music, truthful disclosure flags). Uses the SWIPE framework. Reads brand-profile + goals-and-kpis first. The agent writes the slide plan + overlay copy + caption + config; the IMAGES are made by a human/image skill, not WoopSocial; WoopSocial publishes the native PHOTO post; metrics never fabricated and photo mode is never promised as a reach hack. Distinct from tiktok-script (VIDEO) and carousel-writer (cross-platform copy).

Overview

Publisher	social-media-skills
Repository	`skills`
Skill name	`tiktok-photo-mode`
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 Photo Mode 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-photo-mode
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-photo-mode .claude/skills/tiktok-photo-mode

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

Use it in TypingMind

Enable Tiktok Photo Mode 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 Photo Mode 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 Photo Mode 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-photo-mode

A format-execution skill — produce a TikTok-native Photo Mode carousel (craft for completion) and the exact WoopSocial PHOTO publish config. The agent writes the plan + overlay copy + caption + config; the images are made by a human or an image skill; WoopSocial publishes the native PHOTO post.

The POV: win completion, don't chase a reach hack

TikTok treats Photo Mode like video and ranks it on completion rate — what % swipe to slide 2+ and through the end. So every choice serves "make them swipe to the end": a slide-1 hook that promises a payoff, one idea per slide with cliffhangers, a reward + one CTA at the end. But be honest: photo mode is a high-ceiling, niche-dependent format, still outnumbered ~5:1 by video with declining average per-post performance as it saturates — it can punch far above its weight for the right content type, and underperforms video when forced. Never promise virality. Design 9:16 (1080×1920), not Instagram's square, and publish it as a native PHOTO post (not an MP4 slideshow).

Read these first

brand-profile — niche + voice (does a swipeable format fit?).
goals-and-kpis — the goal (saves / comments / follows / reach).

The framework: SWIPE

(Depth: references/the-swipe-framework.md.)

S — Stop the scroll on slide 1: the thumbnail hook (bold visual + overlay question/claim) that promises a payoff.
W — Win the niche fit: pick a swipeable type (listicle / before-after / tutorial / hot take / photo dump / story / myth-bust); don't force it — photo mode is niche-dependent.
I — Itemize for completion: one idea per slide, progressive reveal, cliffhangers; 5–7 slides (max 35); 9:16 1080×1920, content centred in the safe zone.
P — Pay off + prompt: reward on the final slide + one CTA; question in the caption; don't beg for likes.
E — Equip the publish config: postType=PHOTO, privacyLevel (from platform-inputs), allowComment, autoAddMusic (applies to PHOTO), truthful isYourBrand/isBrandedContent, DIRECT_POST vs MEDIA_UPLOAD; 1–2 hashtags + overlay keywords (TikTok SEO); validate before publish.

The reality (verify-quarterly)

The honest performance tension (high-ceiling vs video-dominance + declining averages); completion rate as the primary signal; 9:16 1080×1920 + safe zone; 5–7 slides; hook / progressive reveal / cliffhanger / reward; sound (autoAddMusic) + text overlays as TikTok SEO; 1–2 hashtags; native-vs-MP4; winning content types + engagement tactics: references/photo-mode-2026-reality.md. Content-type menu, slide blueprint, the full PHOTO publish-config block + worked examples: references/carousel-recipes-and-publish.md.

Honest scope (never violate)

The agent writes the slide plan + overlay copy + caption + publish config. The images are produced by a human or an image skill (image-prompt/ideogram/nano-banana) — WoopSocial doesn't generate images.
WoopSocial publishes the native PHOTO post (postType=PHOTO, raw-bytes upload) and auto-discloses AI on TikTok. No update endpoint → edit = delete + recreate (only while NOT_STARTED).
Disclosure flags set truthfully (isBrandedContent when paid/gifted; isYourBrand for own-brand promo) — never falsely "organic." Never promise virality / a "5×"; never fabricate metrics (native analytics only). (Scope, distinctions + connections: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

tiktok-photo-mode (this) = the TikTok-native PHOTO carousel (completion craft + the WoopSocial PHOTO publish config) · tiktok-script = the TikTok VIDEO script (duet/stitch/cover live there) · carousel-writer = cross-platform carousel copy craft · reels-script/youtube-shorts = video · caption-writer/hook-writer = the caption + overlay lines this skill arranges.

Where this connects

Reads first: brand-profile, goals-and-kpis. Copy: hook-writer, caption-writer. Images (external to WoopSocial): image-prompt/ideogram/nano-banana, carousel-writer (adapt down to 9:16). Publish: scheduling-and-queue → WoopSocial (native PHOTO), platform-specs-and-validation (validate + postType/field rules), content-calendar. Reuse/measure: content-recycling (→ IG/ Pinterest), analytics-and-reporting (completion/saves), experimentation-and-ab-testing (A/B the first slide). Images stay external.

Definition of done

A swipeable content type matched to the niche and goal; a slide-1 hook that promises a payoff; a 5–7 slide progressive reveal with cliffhangers, one idea per slide, designed 9:16 1080×1920 with content in the safe zone; a final-slide reward + one CTA and a caption question (not a like-beg); 1–2 hashtags + overlay keywords for TikTok SEO; the complete WoopSocial PHOTO publish config (postType PHOTO, privacyLevel, allowComment, autoAddMusic, truthful isYourBrand/isBrandedContent, postMode) validated before publish; images produced externally, WoopSocial publishing the native PHOTO post with AI auto-disclosure, edits via delete+recreate, nothing fabricated and no promised virality; correctly distinguished from tiktok-script and carousel-writer.

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 Photo Mode AI skill do?

Why use Tiktok Photo Mode on TypingMind?

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

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

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 Photo Mode?

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

Is the Tiktok Photo Mode 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

Brag Slim

NousResearch

OrganizationPopular

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.

Heartmula

HeartMuLa: Suno-like song generation from lyrics + tags.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

tiktok-photo-mode

The POV: win completion, don't chase a reach hack

Read these first

The framework: SWIPE

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