Collabs And Cross Promotion logo

Collabs And Cross Promotion

Organization
social-media-skills
collabs-and-cross-promotion

Creator collabs and cross-promotion — organic creator-to-creator partnerships that swap audiences. Use when someone wants to set up a collab, audience swap, cross-promotion, shoutout swap, joint giveaway, guest spot, joint video/series, a YouTube/IG collab post, or co-promo with another creator. Picks a complementary, similar-size, values-aligned partner, agrees the plan before creating, and co-creates shared-value content (not a bare shoutout) on a coordinated schedule. Uses the UNITE framework. Reads brand-profile + goals-and-kpis first. WoopSocial publishes each partner's OWN posts to their OWN accounts; it does NOT create native IG Collab co-authored posts, run giveaways, duet/stitch, or manage the agreement. A pure mutual collab isn't a sponsorship, but payment/free product makes it one -> disclose -> ugc-and-influencer; partnerships must be genuine; metrics never fabricated. Distinct from ugc-and-influencer (brand->creator) and creator-monetization (the creator's income).

Overview

Publishersocial-media-skills
Repositoryskills
Skill namecollabs-and-cross-promotion
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 Collabs And Cross Promotion 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/collabs-and-cross-promotion
  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/collabs-and-cross-promotion .claude/skills/collabs-and-cross-promotion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Collabs And Cross Promotion 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 Collabs And Cross Promotion 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 Collabs And Cross Promotion 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.

collabs-and-cross-promotion

A strategy/relationship skill — pick the partner, plan the cross-promo, write both sides. The agent advises + drafts + plans; WoopSocial publishes each partner's own posts on the coordinated schedule; the co-created content + the relationship are native/human.

The POV: mutuality, complementary partners, plan before you create

A collab's defining trait is mutuality — both creators contribute and both promote. That's what separates it from a sponsorship (a paid mention) and from brand→creator UGC. The growth comes from a complementary-not-competing, similar-size (0.5–2×), values-aligned partner — and from agreeing the cross-promo plan before anyone creates. Be honest about the shift: bare shoutouts barely move the needle now — shared value beats shared exposure, so co-create something real. WoopSocial's job is the coordinated publish of each side's own posts; the co-created content and the relationship are not things a scheduler can make.

Read these first

  1. brand-profile — niche / audience / values (for fit).
  2. goals-and-kpis — the growth goal + the success metric (subs/followers per source).

The framework: UNITE

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

  • U — Understand the fit: complementary not competing; 0.5–2× size; values-aligned + authentic (audiences spot fakes).
  • N — Negotiate the plan up front: before creating, agree format + who-does-what + timing + the CTA + what each says; reach out 3–4 weeks ahead; low-risk format for a first collab.
  • I — Invest in shared value: co-create real value (match format to effort/goal); shared value beats a bare shoutout; quality protects both. (Co-created content is native/with the partner.)
  • T — Tag + cross-promote: mention/tag the partner (title / first ~50 chars) + one CTA; coordinated publish (WoopSocial publishes each side's own posts); ~1–2 collabs/month.
  • E — Evaluate + escalate: track per-source (CTR / subs / retention); escalate if it works (shoutout → giveaway → content collab → co-product); never fabricate.

The reality (verify-quarterly)

Mutuality as the defining trait (vs sponsorship / brand-UGC); partner fit (complementary, 0.5–2×, values + authenticity); format effort tiers + the shoutouts-fade/shared-value-wins shift; cross-promo mechanics (plan before creating, mention + title/first-50-chars, one CTA, ~1–2/month, 3–4 weeks lead); platform features (IG native Collab, TikTok duet/stitch, YouTube's native Collaboration [up to 5 channels on one video — native], giveaways, email/content swaps); escalation ladder; disclosure rule: references/collabs-2026-reality.md. Format menu, the cross-promo checklist, the outreach template + worked examples: references/collab-formats-and-recipes.md.

Honest scope (never violate)

  • The agent picks the partner, chooses the format, drafts the outreach, plans the cross-promo, and writes each partner's posts.
  • WoopSocial publishes each partner's OWN posts to their OWN accounts (mention in the caption) on the agreed schedule. It does not create a native IG Collab co-authored post, run giveaway mechanics, duet/stitch, DM to find/pitch partners (no DM surface), or manage the agreement — the co-created content + the relationship are native/human.
  • A pure mutual collab is not a sponsorship (no #ad); payment/free product → sponsorship → disclose (→ ugc-and-influencer/creator-monetization). Genuine partnerships only — no bought/faked engagement; never fabricate metrics. (Scope, distinctions + connections: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

collabs-and-cross-promotion (this) = creator-to-creator MUTUAL partnership (unpaid; both promote) · ugc-and-influencer = brand→creator (paid/licensed, disclosed) · creator-monetization = the creator's own income · social-selling-and-dm = the DM outreach mechanics (can pitch a partner) · campaign-and-launch-planning = the campaign wrapper a collab may sit inside.

Where this connects

Reads first: brand-profile, goals-and-kpis. Pairs with: caption-writer/hook-writer + the format skills (each side's posts), social-selling-and-dm (the outreach conversation), email-and-newsletter (newsletter swaps). Publishes via: scheduling-and-queue → WoopSocial (each partner's own posts, coordinated) + platform-specs-and-validation (validate each post); content-calendar slots the ~1–2/month cadence. Measures with: analytics-and-reporting (per-source CTR/subs/retention). Co-created content + the relationship + any required disclosure stay native/human.

Definition of done

A complementary, not-competing, 0.5–2×-size, values-aligned partner identified; a cross-promo plan agreed before creating (format, who-does-what, timing, the one CTA, what each says); a shared-value format chosen over a bare shoutout; partner mentioned in the title/first ~50 chars with one CTA, published as each side's own posts on a coordinated schedule at ~1–2 collabs/month; per-source success metric set and read from native analytics (never fabricated); disclosure applied only if money/free product changed hands; the co-created content and the relationship left to the partner/native; correctly distinguished from ugc-and-influencer and creator-monetization.

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 Collabs And Cross Promotion AI skill do?

Creator collabs and cross-promotion — organic creator-to-creator partnerships that swap audiences. Use when someone wants to set up a collab, audience swap, cross-promotion, shoutout swap, joint giveaway, guest spot, joint video/series, a YouTube/IG collab post, or co-promo with another creator. Picks a complementary, similar-size, values-aligned partner, agrees the plan before creating, and co-creates shared-value content (not a bare shoutout) on a coordinated schedule. Uses the UNITE framework. Reads brand-profile + goals-and-kpis first. WoopSocial publishes each partner's OWN posts to th...

Why use Collabs And Cross Promotion on TypingMind?

Because you install it once and use it with any model. Collabs And Cross Promotion 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 Collabs And Cross Promotion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/collabs-and-cross-promotion. 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 Collabs And Cross Promotion?

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 Collabs And Cross Promotion?

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

Is the Collabs And Cross Promotion 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 👇