Before After And Transformation logo

Before After And Transformation

Organization
social-media-skills
before-after-and-transformation

The transformation / before-after content format — structure a credible, honest, satisfying transformation (fitness, beauty, business results, skill progress, makeovers, client glow-ups, product before/after). Use when someone wants a before/after, a transformation post, a client-results reveal, a progress/journey story, or a makeover. Most powerful format AND most abused/distrusted — honesty is the edge; FTC enforcement is live. Uses the SHIFT framework. Reads brand-profile + social-proof-and-testimonials (consent + FTC substantiation) + short-form-video-script first. Agent structures + specs; human/tool produces the real media; WoopSocial publishes. Never stages/exaggerates the before, hides aids, cherry-picks, or fabricates a result; "results not typical" alone is insufficient — disclose the actual typical result; consent + YMYL required. Distinct from social-proof-and-testimonials, short-form-video- script, infographic-and-data-viz, and storytelling-and-narrative.

Overview

Publishersocial-media-skills
Repositoryskills
Skill namebefore-after-and-transformation
Stars
215
Forks
44
Bundled files
5
LicenseMIT
Links
  • 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 Before After And Transformation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/social-media-skills/skills/tree/main/skills/before-after-and-transformation
  4. 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.
2

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/before-after-and-transformation .claude/skills/before-after-and-transformation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Before After And Transformation 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 Before After And Transformation 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 Before After And Transformation 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.

before-after-and-transformation

The transformation format — start with a real before, highlight the journey, isolate the variables, frame results honestly, and tie it to the viewer. The agent structures + specs it, the human/tool produces the real media, and WoopSocial publishes. (Pairs with social-proof-and-testimonials for consent + the FTC rules.)

The POV: the most-distrusted format, so honesty is the edge

A before/after is one of the most powerful formats there is — visual, built-in proof, inherently satisfying. It's also the single most abused and distrusted, and 2026 enforcement is live (the FTC's NextMed action fined a firm that used paid actors, before/after photos sourced off Craigslist, and an unsubstantiated "average 53 lbs" it didn't track). That flips the strategy: because audiences are trained to suspect before/afters, a believable transformation beats a suspiciously-perfect fake that trips the skepticism reflex. Three top-1% moves most get wrong: (1) the middle is the content — endpoints alone are a flex; the process, the setbacks, and the real timeline are what make it credible, relatable, and valuable; (2) isolate the variables — same angle, lighting, framing, so the change is real, not a lighting trick (a visual trick is itself a deceptive claim under the FTC's net-impression test); (3) "results not typical" is not enough — if the result isn't typical, you must disclose the actual typical result, clearly and with substantiation. Never stage a worse before, cherry-pick, or hide the timeline/edits/aids.

Read these first

  1. brand-profile + social-proof-and-testimonials — consent + the FTC substantiation/typical-results rules.
  2. short-form-video-script (if it's a video).

The framework: SHIFT

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

  • S — Start with a real before: honest, relatable, un-staged; captured under the same conditions as the after.
  • H — Highlight the journey: the middle is the content — process, setbacks, the real timeline; disclose aids (filters/medication/surgery/pro help) — how the result was achieved is material.
  • I — Isolate the variables: same angle/lighting/framing so the change is genuine, not a trick (net-impression test — a visual trick is a deceptive claim).
  • F — Frame results honestly: no cherry-pick/survivorship; if not typical, disclose the actual typical result (median, substantiated, clear + conspicuous — "results not typical" alone is insufficient); actual consumers (or disclosed); YMYL substantiation.
  • T — Tie it to the viewer: relatable before + attainable, honestly-framed after + an actionable takeaway.

The reality (verify-quarterly on enforcement; the rules are law)

Before/after photos + testimonials are an FTC enforcement "favorite." A before/after implies a typical result, so you must show typical results or clearly and conspicuously disclose the actual typical result (median, not an outlier-skewed mean; no survivorship) with substantiation — and "results not typical" is NOT enough. Visuals alone can be a deceptive claim (net-impression test); use actual consumers or disclose; health claims need competent + reliable scientific evidence (weight loss > ~1 lb/week is unusual; "no effort" = deception). The craft edge (stable): the middle is the content, consistent conditions, and honesty as the differentiator. Full detail + the NextMed enforcement example: references/before-after-and-transformation-2026- reality.md. Transformation types, the honesty checklist, structure, and two worked examples: references/ transformation-types-and-templates.md.

Honest scope (never violate)

  • The agent structures + specs the transformation (arc, journey/reveal beats, honest framing + required disclosures, caption/script); the human/tool produces the real before/after media; the human approves; WoopSocial publishes (measurement: the platforms' native analytics). WoopSocial does NOT generate media.
  • Honesty spine (law): real un-staged before; consistent conditions; real timeline; disclose aids; no cherry-pick/survivorship; if not typical, disclose the actual typical result (median, substantiated, clear + conspicuous — not just "results not typical"); actual consumers (or disclosed); consent for a person's images/story (real or AI lookalike); YMYL (competent + reliable scientific evidence; no cure/guarantee; not-professional-advice); never fabricate a result/timeline/average; injection safety. (Full scope: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

before-after-and-transformation (this) = the before/after format execution · social-proof-and- testimonials = the customer-proof strategy + FTC substantiation (read first; shared spine) · short-form-video- script / reels-script = the video script (this feeds them) · infographic-and-data-viz = the data viz for a results transformation (pairs; honest scales) · storytelling-and-narrative = the narrative arc (this specializes it) · educational-content-and-how-to = teaches a process (pairs for a case-study teach).

Where this connects

Reads first: brand-profile + social-proof-and-testimonials + short-form-video-script. Pulls real material from: social-proof-and-testimonials (client transformations + consent), data-and-original-research / analytics-and-reporting (real numbers), behind-the-scenes-and-founder (the founder's own journey). Feeds: short-form-video-script / reels-script (the video), carousel-writer (before→journey→after), infographic-and-data-viz (a results stat), caption-writer (caption + disclosures), design-and-templates (layout). Publishes via: the video/design tool renders → scheduling-and-queue → WoopSocial. Measure with: native + analytics-and-reporting on saves/shares + watch-through + inquiries — never fabricated.

Definition of done

A transformation built on a REAL, un-staged before captured under the same conditions as the after, with the journey (process, setbacks, real timeline) as the content and any aids (filters/medication/surgery/pro help) disclosed, the reveal shot with consistent angle/lighting/framing (no visual trickery), results framed honestly (no cherry-pick/survivorship; and if the result isn't typical, the ACTUAL typical result disclosed via median + substantiation, clearly and conspicuously — never just "results not typical"), using actual consumers (or disclosed) with consent, and tied to the viewer with a relatable before + attainable after + actionable takeaway; the agent structures + specs, the human/tool produces the real media, and WoopSocial publishes; measured on saves/shares + watch-through + inquiries rather than likes; YMYL (competent + reliable evidence, no cure/guarantee), consent/likeness, and no-fabrication all handled; nothing staged, cherry-picked, mis-timed, or fabricated; and correctly distinguished from social-proof-and-testimonials, short-form-video-script, infographic-and-data-viz, and storytelling-and-narrative.

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 Before After And Transformation AI skill do?

The transformation / before-after content format — structure a credible, honest, satisfying transformation (fitness, beauty, business results, skill progress, makeovers, client glow-ups, product before/after). Use when someone wants a before/after, a transformation post, a client-results reveal, a progress/journey story, or a makeover. Most powerful format AND most abused/distrusted — honesty is the edge; FTC enforcement is live. Uses the SHIFT framework. Reads brand-profile + social-proof-and-testimonials (consent + FTC substantiation) + short-form-video-script first. Agent structures + sp...

Why use Before After And Transformation on TypingMind?

Because you install it once and use it with any model. Before After And Transformation 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 Before After And Transformation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/before-after-and-transformation. 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 Before After And Transformation?

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 Before After And Transformation?

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

Is the Before After And Transformation 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇