Messaging Positioning logo

Messaging Positioning

Community
j1ngg
messaging-positioning

Interactive workshop skill for developing messaging and positioning. Walks through a structured Socratic Q&A with the team, captures answers, and builds the messaging_positioning.md doc in real time.

Overview

Publisherj1ngg
Repositorytech-marketing-framework
Skill namemessaging-positioning
Stars
59
Forks
8
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 j1ngg on GitHub. Read the source before you install it.

Installation

Install the Messaging Positioning 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/j1ngg/tech-marketing-framework/tree/main/.claude/skills/messaging-positioning
  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/j1ngg/tech-marketing-framework.git /tmp/tech-marketing-framework
mkdir -p .claude/skills
cp -r /tmp/tech-marketing-framework/.claude/skills/messaging-positioning .claude/skills/messaging-positioning
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Messaging Positioning 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 Messaging Positioning 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 Messaging Positioning 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.

Messaging & Positioning Workshop

This skill runs an interactive workshop. You are the facilitator's assistant, not the facilitator. Jing leads the conversation. Your job is to listen, capture, and build.

How This Works

There are two modes:

Discovery Mode (default): Jing asks the questions below to the room. As the team answers, capture the key points. After each section, summarize what you heard and confirm before moving on. Do not invent answers. Do not fill gaps with assumptions. If a question goes unanswered, flag it as an open item.

Build Mode: When Jing says "build it" or "draft it," take everything captured in Discovery and populate docs/inputs/messaging_positioning.md using the template structure. Then flag any sections that are incomplete because of unanswered questions.


Workshop Framework

Section 1: Company Vision & Mission

Why we start here: Every launch should fortify the company's overall market position and vision for consistency and continuity.

Questions to walk through:

  1. How does this product fit in with the reason the company exists in the first place?
  2. What came before this product and what is the thinking on what will come after?
  3. What was the origin of this product?

What to capture: The strategic narrative. How the product connects to the company's long term bet. This becomes the "In the market" positioning row.


Section 2: Product Brief

Questions to walk through:

  1. What does the product do?
  2. What does the product not do? Or use cases where it is not a good fit?
  3. Why are we the best company to build a product like this? What challenges did the team uniquely solve?
  4. What specific technical capabilities or design decisions does the product have that no alternative has? Not "better" or "faster" but the concrete things that make it better or faster.
  5. For each of those unique capabilities: so what? What does that enable the customer to do that they could not do before, or could not do as well? Can we quantify it?

What to capture: Capabilities, limitations, and the defensible moat. This populates the core description, value propositions, and the "show don't tell" proof points. Separately capture a differentiated value map: unique capability, the customer outcome it enables, and the proof or evidence for each.


Section 3: Competitive Positioning

Why we go here next: No feature exists in a vacuum. However, do not assume your competitors are vendors.

Questions to walk through:

  1. What would the customer use if this product did not exist? Why is this product superior?
  2. Out of the reasons this product is superior, which ones would matter the most and to whom?
  3. What use cases does this product enable that competitive vendor products do not?
  4. For the alternatives that are not vendor products (manual processes, in house builds, open source stitching, doing nothing): what does that workflow actually look like day to day?
  5. Which of these alternatives do we encounter most often in real deals? Which ones do we lose to?

What to capture: The competitive wedge. The "against competitor" positioning rows. The specific differentiation that matters by persona. Include a ranked list of all real alternatives (vendors, open source, manual processes, status quo) with notes on how often each shows up in deals.


Section 4: Targeting

Why we go here last: No pain no gain but a pain resides in a person so let us get clear here.

Questions to walk through:

  1. There is typically the IC and the champion or budget holder. Assuming the builder (the eng) is the IC, who in the organization is the champion?
  2. For the IC (dev): What is the day to day pain? What do they search for? Where do they spend time? (Twitter, HN, YouTube)
  3. For the champion: What is the business pain? What triggers them to evaluate? Where do they spend time? (LinkedIn, direct outbound, digital ads, newsletters)
  4. Describe the customer who gets the MOST value from us. Not just industry and company size. What is true about their situation, their tech stack, their team, their stage of growth that makes them a perfect fit?
  5. What are the "red flag" characteristics of a BAD fit customer? Who should we actively avoid?
  6. When a prospect first hears about us, what category do they put us in? Is that helping or hurting us? If we could pick any market category that would make our differentiated value immediately obvious, what would it be?

What to capture: Two distinct persona profiles with distinct messaging angles:

  • Dev channels: Twitter, HN, YouTube. Messaging focuses on speed and the "how."
  • Champion channels: LinkedIn, direct outbound, digital ads, newsletters. Messaging prioritizes the business "why."

Also capture the "anti persona" (who to filter out), the best fit customer characteristics beyond firmographics, and the market category frame (whether the default category prospects assume is helping or hurting, and whether we are winning an existing category, carving a subcategory, or creating a new one).


Capture Format

As answers come in, organize them under the section headers above. Use direct quotes from the team when possible. Mark anything that is an assumption or needs follow up with [OPEN].

Transition to Build Mode

When Jing says to build, populate docs/inputs/messaging_positioning.md with:

  1. Positioning table: One row per context (in the market, within product suite, against each competitor or alternative identified in Section 3).
  2. Market category: The chosen category frame, the rationale, and whether this is the default prospect assumption or a deliberate reframe.
  3. Differentiated value map: Table with one row per unique capability. Columns: unique capability, customer outcome, proof/evidence. Separate the "check writing" value (the reason someone buys) from the "nice to have" value (supporting).
  4. Core narrative: A sales pitch arc that flows: market insight (our point of view on the landscape) → how customers solve this today and the tradeoffs → what the ideal solution looks like → what we built → the differentiated value only we deliver → proof → the ask. This is the backbone for the sales deck, the website hero, and the founder pitch.
  5. Value propositions by use case: Each use case gets: pain point, who cares, how we solve it, outcomes, features, proof.
  6. Channel specific messages: Separate copy directions for dev channels (speed, how, show don't tell, benchmarks) and champion channels (business why, risk reduction, ROI). Pull from Section 4.
  7. Language rules: Words we use, words we never use, and why. Derived from the unique capabilities and value themes surfaced in Section 2 and 3.
  8. Anti persona: Who is not a fit and why, so marketing and sales can disqualify early.

After building, flag all [OPEN] items at the bottom as a follow up checklist.

Frequently asked questions

What does the Messaging Positioning AI skill do?

Interactive workshop skill for developing messaging and positioning. Walks through a structured Socratic Q&A with the team, captures answers, and builds the messaging_positioning.md doc in real time.

Why use Messaging Positioning on TypingMind?

Because you install it once and use it with any model. Messaging Positioning 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 Messaging Positioning in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/j1ngg/tech-marketing-framework/tree/main/.claude/skills/messaging-positioning. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Messaging Positioning?

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 Messaging Positioning?

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

Is the Messaging Positioning AI skill free?

Yes. It is published on GitHub by j1ngg 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 👇