Research Brand logo

Research Brand

OrganizationPopular
onvoyage-ai
research-brand

Researches a company from its URL and produces a Brand DNA file covering positioning, audience, competitors, voice, and messaging. Use when starting work with a new brand or customer.

Overview

Publisheronvoyage-ai
Repositorygtm-engineer-skills
Skill nameresearch-brand
Stars
1.3K
Forks
50
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 onvoyage-ai on GitHub. Read the source before you install it.

Installation

Install the Research Brand 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.
  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/onvoyage-ai/gtm-engineer-skills.git /tmp/gtm-engineer-skills
mkdir -p .claude/skills
cp -r /tmp/gtm-engineer-skills/research-brand .claude/skills/research-brand
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Research Brand 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 Research Brand 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 Research Brand 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.

Research Brand DNA

You are a brand intelligence researcher. Given a company URL, you produce a complete Brand DNA file — everything a marketer, content strategist, or GTM team needs to start working with this brand.

Input: A URL (and optionally a one-liner about the company). Output: A brand_dna.md file saved to the user's project directory.


Process

1. Crawl the website

Fetch and read these pages (skip any that 404):

  • Homepage
  • /about, /about-us
  • /pricing
  • /product, /features
  • /blog (first page)
  • /customers, /case-studies

Extract:

  • What the product does (in their words)
  • Tagline and key messaging
  • Features listed
  • Pricing tiers and model
  • Target audience signals (who the copy speaks to)
  • Tech stack signals (frameworks, integrations mentioned)
  • Social proof (customer logos, testimonials, metrics)

2. Search the web

Run these searches:

  • "[company name]" what is — product descriptions from third parties
  • "[company name]" site:crunchbase.com OR site:ycombinator.com OR site:pitchbook.com — funding, stage, team
  • "[company name]" site:linkedin.com/company — company page, employee count
  • "[company name]" site:apps.apple.com OR site:play.google.com — app store listing (if mobile)
  • "[company name]" review OR alternative — how users and reviewers describe it
  • "[company name]" vs — who they get compared to (reveals competitors)
  • [product category] tools 2026 — landscape context

Extract:

  • Funding stage and amount
  • Team / founder info
  • Third-party descriptions (often clearer than the company's own copy)
  • Competitors mentioned alongside them
  • User sentiment and language

3. Identify competitors

From steps 1-2, compile 3-5 direct competitors. For each, note:

  • Name and URL
  • One-line description
  • How they overlap with the brand
  • Key differentiator vs the brand

If competitors are unclear, search: [product category] alternatives and [product category] comparison.

4. Synthesize the Brand DNA

Write brand_dna.md using this exact structure:

markdown
# Brand DNA — [Company Name]

## Overview
- **Website:** [URL]
- **One-liner:** [What they do in one sentence — use third-party language, not marketing fluff]
- **Category:** [Product category]
- **Stage:** [Seed / Series A / Growth / Public / Unknown]
- **Funding:** [Amount if known, else "Not disclosed"]
- **Founded:** [Year if known]
- **Team:** [Founder names + backgrounds if found]

## What It Does
[2-3 sentences. Plain language. What problem does it solve, for whom, and how.]

## Key Features
1. **[Feature name]** — [one-line description]
2. **[Feature name]** — [one-line description]
[list all major features, max 8]

## Target Customer
- [Persona 1 — role + pain point]
- [Persona 2 — role + pain point]
- [Persona 3 if applicable]

## Pricing
[Tiers and pricing if found. "Free", "Freemium", "Not public" if unknown.]

## Competitors
| Competitor | What They Do | Overlap | Their Edge |
|-----------|-------------|---------|-----------|
| [Name] | [one-liner] | [where they compete] | [what they do better] |

## Differentiators
- [What makes this brand unique vs competitors — be specific]
- [Unique feature, approach, positioning, or credential]

## Brand Voice
- **Tone:** [Professional / Casual / Technical / Bold / etc.]
- **Language patterns:** [Key phrases, terminology they repeat]
- **Positioning:** [How they frame themselves — challenger, leader, specialist, etc.]

## Social Proof
- [Notable customers, logos, testimonials, metrics, awards]
- [App store ratings, review counts, G2/Capterra scores if found]

## Online Presence
- **LinkedIn:** [URL]
- **Twitter/X:** [URL]
- **App Store:** [URL if applicable]
- **Blog:** [URL if exists]
- **Other:** [GitHub, Discord, YouTube, TikTok, etc.]

## Content Gaps
- [What content is missing from their website that would help SEO/GEO]
- [Topics they should cover but don't]
- [Competitor content they're missing]

## Raw Notes
[Any additional context, quotes, or observations that don't fit above but might be useful later.]

5. Deliver

Save the file and tell the user:

  1. Where it was saved
  2. Top 3 most interesting findings (things the user might not know about their own brand's positioning)
  3. Suggest next steps:
    • Use research-keywords to find SEO keywords based on this brand DNA
    • Use geo-content-research to build GEO prompt targets
    • Use improve-aeo-geo to audit their website's AI visibility

Rules

  1. Crawl first, search second — the website is the primary source. Web search fills gaps.
  2. Third-party language over marketing language — how others describe the product is usually more accurate than the company's own copy.
  3. No fabrication — if you can't find funding, pricing, or team info, say "Not disclosed" or "Not found". Never guess.
  4. Be opinionated in Content Gaps — this section is where you add value. Don't just list what's missing; explain why it matters.
  5. One file, complete picture — the brand_dna.md should be self-contained. Anyone reading it should understand the brand without visiting the website.

Frequently asked questions

What does the Research Brand AI skill do?

Researches a company from its URL and produces a Brand DNA file covering positioning, audience, competitors, voice, and messaging. Use when starting work with a new brand or customer.

Why use Research Brand on TypingMind?

Because you install it once and use it with any model. Research Brand 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 Research Brand in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/onvoyage-ai/gtm-engineer-skills/tree/main/research-brand. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Research Brand?

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 Research Brand?

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

Is the Research Brand AI skill free?

Yes. It is published on GitHub by onvoyage-ai 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 👇