Marketing Copy

Community

mia-ppp

marketing-copy

Produce marketing artifacts from approved positioning and messaging. Use for copywriting, copy editing, homepage and landing copy, Seven Sweeps, proofreading and content refresh. Modes are draft, edit and refresh; independent quality and messaging reviews remain separate.

Overview

Publisher	mia-ppp
Repository	`PMM-Skills`
Skill name	`marketing-copy`
Stars	76
Forks	2
Bundled files	9
License	MIT
Links	Skill source Repository

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.
9 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by mia-ppp on GitHub. Read the source before you install it.

Installation

Install the Marketing Copy 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/mia-ppp/PMM-Skills/tree/main/skills/marketing-copy
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/mia-ppp/PMM-Skills.git /tmp/PMM-Skills
mkdir -p .claude/skills
cp -r /tmp/PMM-Skills/skills/marketing-copy .claude/skills/marketing-copy

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

Use it in TypingMind

Enable Marketing Copy 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 Marketing Copy 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 Marketing Copy 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.

Marketing Copy

Approved context and evidence

Read ../_shared/evidence-gaps.md and ../_shared/ssot-consumption.md. Load only relevant approved manifest context and record sources in Inputs and assumptions. Read ../_shared/segment-selection.md when an audience decision is needed; inherit accepted segments and ICP. Separate sources, interpretation, and proposals. Missing evidence remains Assumed or Gap. Do not edit SSOT. Route proposed canon changes to ssot-context-loop for human review and approval.

Modes

Draft: Read draft methodology. Clarify audience, page role, intended action, source message, proof and constraints. Develop structure, benefits, specific headlines and CTAs before final copy.
Edit: Read Seven Sweeps. Preserve intent and voice; sweep clarity, voice/tone, so-what benefits, proof, specificity, emotion and risk. Explain consequential edits and return an edited artifact, not just advice.
Refresh: First identify what became stale: product truth, buyer needs, proof, traffic intent, links or dates. Compare refresh versus rewrite by scope of changed meaning. Preserve effective structure and voice when strategy remains valid; request approval for upstream changes before a strategic rewrite. Apply the drafting or editing reference to affected sections.

Workflow and required output

Record Inputs and assumptions, mode, audience, originating brief, approved message, proof sources and unsupported claims. Use plain English, concrete benefits and credible commitments. Do not invent metrics, endorsements, roadmap, scarcity or guarantees. Produce ready-to-review copy, meaningful alternatives where requested, explained edits/change rationale, proof-check results, owner handoffs and ranked Evidence gaps. Keep proof gaps out of customer-facing claims as required by the evidence contract. For listings, read description templates: vary channel expression while preserving approved strategic meaning. Read ../_shared/creative-brief.md when commissioning visuals or a demo narrative and ../_shared/behavioral-principles.md only when a behavioral hypothesis helps the brief.

Ownership

positioning-strategy owns competitive meaning; messaging-framework owns reusable message architecture. This skill expresses those decisions in artifacts. Email sequences, cold outbound, social and ad batches route to their specialized execution owners. Editing does not certify its own output: output-quality-check checks originating requirements, messaging-consistency-audit checks approved meaning, and launch-readiness-check checks launch-wide readiness.

Related skills

positioning-strategy, messaging-framework, email-sequence, cold-email, social-content, ad-creative, output-quality-check, messaging-consistency-audit, launch-readiness-check.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

evals/evals.json20 KB
references/common-problems.md1 KB
references/content-refresh.md2 KB
references/copy-frameworks.md8 KB
references/draft.md8 KB
references/edit.md15 KB
references/listing-descriptions.md9 KB
references/natural-transitions.md6 KB
references/plain-english-alternatives.md8 KB

Frequently asked questions

What does the Marketing Copy AI skill do?

Why use Marketing Copy on TypingMind?

Because you install it once and use it with any model. Marketing Copy 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 Marketing Copy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mia-ppp/PMM-Skills/tree/main/skills/marketing-copy. 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 Marketing Copy?

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 Marketing Copy?

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

Is the Marketing Copy AI skill free?

Yes. It is published on GitHub by mia-ppp 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

Agent Transcript

openclaw

OrganizationPopular

Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.

Openclaw Refactor Docs

openclaw

OrganizationPopular

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

Gemini

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Writing Skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Marketing Copy

Approved context and evidence

Modes

Workflow and required output

Ownership

Related skills

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now