37 Social Caption Global logo

37 Social Caption Global

Community
minhnv0807
37-social-caption-global

Use when the user needs ORGANIC social captions for Instagram, LinkedIn, TikTok, Facebook, or X — hook, mobile-readable body, two A/B variants, platform-correct hashtags, written to brand voice and funnel stage. Trigger on 'write a caption', 'Instagram caption', 'LinkedIn post copy', 'TikTok caption', 'caption for this photo', 'we have the image but no words'. Also use when the user drops a picture and asks what to write with it. Not for — paid ad copy with character limits and policy, see `05-ad-copy-global`; the spoken lines in a video, see `04-script-video-global`; the brief that precedes writing, see `36-content-brief-global`; long-form authority posts, see `26-thought-leadership-content-global`.

Overview

Publisherminhnv0807
Repositoryai-business-skills
Skill name37-social-caption-global
Stars
612
Forks
228
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by minhnv0807 on GitHub. Read the source before you install it.

Installation

Install the 37 Social Caption Global 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/minhnv0807/ai-business-skills/tree/master/skills/en/37-social-caption-global
  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/minhnv0807/ai-business-skills.git /tmp/ai-business-skills
mkdir -p .claude/skills
cp -r /tmp/ai-business-skills/skills/en/37-social-caption-global .claude/skills/37-social-caption-global
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 37 Social Caption Global 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 37 Social Caption Global 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 37 Social Caption Global 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.

Social Caption (Global)

Organic captions for owned social posts on Instagram, LinkedIn, TikTok, Facebook, and X. A good caption has a hook strong enough to stop the thumb, a body that earns the scroll, and a CTA clear enough that the reader knows what to do. Written for someone reading on a phone, moving fast.

Not this skill: paid ad copy — different constraints (ad policy review, character limits in placements, primary text truncation, iteration against CPA). Use 05-ad-copy-global.

Information gathering

Read the Brand Voice Document (35-brand-voice-global) and the content brief (36-content-brief-global) first. If the brief already sets angle, hook direction, and CTA, use them — do not re-ask. If both are missing, ask up to 4 questions:

  1. What is the product, service, or topic — and is there a real number, testimonial, or case study available?
  2. Which funnel stage? TOFU (awareness) / MOFU (consideration) / BOFU (conversion)
  3. Which channel? Instagram / LinkedIn / TikTok / Facebook / X
  4. What is the intended CTA and target length? (comment / click / DM / book / buy — short under 100 words / medium 100-200 / long over 200)

Principles

  1. The first line is the hook. Never open with the brand name or a greeting. The reader decides in about a second.
  2. One caption = one message. Do not stack benefits into a single post.
  3. A specific number beats a vague adjective. "Cut onboarding from 11 days to 3" beats "dramatically faster".
  4. Write for mobile. Paragraphs of 1-3 sentences with white space between them. No walls of text.
  5. BOFU needs a clear CTA and a real reason to act now. Manufactured urgency is a brand risk; a genuine deadline, batch, or capacity limit is not.
  6. Read it aloud before you ship it. If it sounds like a status report, the tone is wrong.
  7. Check it against brand voice. Vocabulary and banned words from 35-brand-voice-global. Default banned list: "game-changer", "revolutionary", "unlock your potential", "don't miss out", "act now", "elevate your", "we're excited to announce", "best-in-class".
  8. Disclose material connections. Paid partnership, gifted product, affiliate link, or employee-authored posts need clear disclosure in the caption itself, not only in a platform tag — FTC endorsement rules apply to organic content.

Workflow

1. Read the brief and the brand voice

From 36-content-brief-global: angle, source insight, key message, CTA. From 35-brand-voice-global: tone, vocabulary, sentence rules. Without a brief, gather the 4 answers above first.

2. Write the hook to funnel stage

The hook must stand alone with no context.

StageHook directionTypical form
TOFUPain / curiosity / contrarianA question that names the frustration, or a statement that inverts the category's default belief
MOFUSocial proof / concrete resultA number, a short testimonial, a before-and-after
BOFUOffer / genuine urgencyA specific discount or bonus, a real deadline, a real capacity limit

3. Write 2 genuinely different A/B variants

The two variants must differ structurally, not by a few swapped words:

  • Variant A: one hook direction (for example pain) plus one body structure (for example a list).
  • Variant B: a different hook direction (for example curiosity or social proof) plus a different structure (for example a short narrative).

Each variant: Hook (opening line) then Body (2-4 short paragraphs, 1-3 sentences each) then CTA (a specific action).

4. Write the selection note

State plainly: use A when [context or audience], use B when [context or audience], and how to mix (hook A with body B, or the reverse) if that is sensible.

5. Apply hashtags and platform adaptation

Hashtags are a discovery and categorization signal now, not a reach lever. Fewer and more targeted outperforms volume on every major platform.

ChannelHashtagsAdaptation
Instagram3-5, targeted to the actual topicThe first line carries the hook — it is what shows before "more". Visual leads; the caption supports it
LinkedIn3, professional and topicalFirst 2-3 lines are visible before "see more". First-person point of view, no hard sell, external links often better in the first comment
TikTok3-5, mixing one trending tag with niche tags1-2 lines, keyword-forward so it surfaces in TikTok search. The real hook lives in the first second of video; the caption supports it
Facebook0-2, or noneLonger captions work. Conversational. Line breaks matter more than hashtags
X1-2 maximumOne idea, no wind-up. If it needs more, it is a thread — write it as one

Truncation points and character limits change; check the platform preview before publishing rather than trusting a remembered number.

Output structure

File name: social-caption-[topic]-[YYYYMMDD].md

markdown
# Social Caption — [Topic]

## Context
| Item | Detail |
|------|--------|
| Funnel stage | TOFU / MOFU / BOFU |
| Channel | |
| Objective | |
| Target length | |
| Source brief | [link to content brief if any] |
| Disclosure required | none / paid partnership / gifted / affiliate |

## Variant A — [hook direction]
**Hook:**
[Opening line — stands alone, creates pain / curiosity / surprise]

**Body:**
[2-4 short paragraphs, 1-3 sentences each, white space between]

**CTA:**
[Specific action]

## Variant B — [different hook direction]
**Hook:**
[Different angle — if A used pain, B uses curiosity or social proof]

**Body:**
[Different structure from A — if A used a list, B uses narrative]

**CTA:**
[May match or differ from A]

## Selection notes
- Use **A** when: [context / audience]
- Use **B** when: [context / audience]
- Mixing A+B: [hook A with body B or the reverse, if sensible]

## Hashtags
[Per platform norm — Instagram 3-5 / LinkedIn 3 / TikTok 3-5 / Facebook 0-2 / X 1-2]

## Brand voice check
- Matches Brand Voice Document: Yes / No
- Banned words: none present
- Read aloud: sounds natural
- Every claim substantiable: Yes

Related skills

  • 35-brand-voice-global: read before writing (tone, vocabulary, banned words); run its section VII checklist before handoff.
  • 36-content-brief-global: supplies angle, source insight, key message, and CTA.
  • 01-content-calendar-global: captions are written against a calendar slot (channel, funnel stage, pillar).
  • 05-ad-copy-global: when the post will run as a paid ad, rewrite to ad-copy standards. Never push an organic caption into an ad unchanged.
  • 42-image-brief-global, 43-carousel-brief-global: the accompanying visual brief, produced after the caption is approved.

Quality checklist

  • First line is a hook — no brand name, no greeting.
  • One caption = one message = one CTA.
  • The two variants differ genuinely (different hook direction and different structure).
  • Selection note states when to use A and when to use B.
  • Specific numbers replace vague adjectives wherever evidence exists.
  • Paragraphs are 1-3 sentences and readable on a phone.
  • BOFU has a clear CTA and, where urgency is used, a real reason for it.
  • No banned words (checked against 35-brand-voice-global).
  • Hashtag count and style match the channel's current norm.
  • Material connection disclosed in-caption where one exists.
  • Read aloud — it sounds like a person talking.

Frequently asked questions

What does the 37 Social Caption Global AI skill do?

Use when the user needs ORGANIC social captions for Instagram, LinkedIn, TikTok, Facebook, or X — hook, mobile-readable body, two A/B variants, platform-correct hashtags, written to brand voice and funnel stage. Trigger on 'write a caption', 'Instagram caption', 'LinkedIn post copy', 'TikTok caption', 'caption for this photo', 'we have the image but no words'. Also use when the user drops a picture and asks what to write with it. Not for — paid ad copy with character limits and policy, see `05-ad-copy-global`; the spoken lines in a video, see `04-script-video-global`; the brief that precede...

Why use 37 Social Caption Global on TypingMind?

Because you install it once and use it with any model. 37 Social Caption Global 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 37 Social Caption Global in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/minhnv0807/ai-business-skills/tree/master/skills/en/37-social-caption-global. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use 37 Social Caption Global?

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 37 Social Caption Global?

As many as you like. As long as a model supports skills, you can use 37 Social Caption Global with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 37 Social Caption Global AI skill free?

Yes. It is published on GitHub by minhnv0807 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 👇