AgentStack
SKILL verified MIT Self-run

Brand Research

skill-orkas-ai-orkas-awesome-agentskills-brand-research · by Orkas-AI

Research a brand from public sources and produce a sourced Brand DNA brief. Use this skill whenever the user asks to understand a company, product, positioning, competitors, brand voice, social proof, or GTM/content context from public evidence.

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-orkas-ai-orkas-awesome-agentskills-brand-research

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Brand Research? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Brand Research

Use this skill to research a company, product, or brand from its website and public sources, then produce a sourced Brand DNA brief. The work is evidence collection plus synthesis; do not invent missing facts.

When To Use

  • The user provides a company URL, product URL, brand name, or company/product context and asks for brand research.
  • The user wants Brand DNA, positioning, target customers, competitors, brand voice, social proof, pricing, online presence, or content gaps.
  • The user needs source-backed context before GTM, SEO, GEO/AEO, content strategy, sales messaging, or competitor analysis.

Do not use for:

  • Writing landing pages, ads, articles, or full content plans.
  • Running a full SEO audit, website audit, or social media performance analysis.
  • Investment, legal, financial, or diligence conclusions.
  • Updating or publishing to the user's website.
  • Making claims without source evidence.

How To Call

  1. Confirm the input.
  • Identify the company URL, company/product name, and optional one-line context.
  • If the URL or company identity is ambiguous, ask the user to confirm.
  • If the homepage is unreachable after retrying, report the access problem instead of inventing a profile.
  1. Research the company website first.
  • Prioritize the homepage, about page, pricing page, product/features pages, customer/case-study pages, docs/help/integrations pages, and blog index when relevant.
  • Extract what the product does, who it serves, features, pricing model, target audience signals, integrations, social proof, and repeated messaging.
  • Keep source URLs for important claims.
  1. Search public sources second.
  • Use third-party sources to clarify category, team, funding, competitors, reviews, alternatives, and user language.
  • Do not let low-quality directories override the company's own website.
  • Mark sparse, outdated, paywalled, or weak evidence.
  1. Identify competitors.
  • Compile 3-5 direct or adjacent competitors when evidence is available.
  • For each, note name, URL, overlap, and apparent edge.
  • If competitors are unclear, say so and explain the missing evidence.
  1. Synthesize the Brand DNA.
  • Use references/brand-dna-template.md.
  • Separate sourced facts from interpretation.
  • Use "Not found" or "Not disclosed" when facts cannot be verified.
  • Be opinionated in content gaps, but label them as analysis rather than fact.
  1. Deliver safely.
  • By default, return the Brand DNA in the conversation.
  • Save brand_dna.md only when the user asks for a file or confirms saving.
  • Include top findings, evidence caveats, and suggested next uses.

Default Output

# Brand DNA - [Company Name]

## Overview

## What It Does

## Target Customer

## Competitors

## Differentiators

## Brand Voice

## Social Proof

## Content Gaps

## Source Notes

External Dependencies

  • Web access is required for public website and source research.
  • Some websites may block automated access, require JavaScript rendering, or hide content behind login walls.
  • Paid sources such as Crunchbase, PitchBook, Ahrefs, Semrush, G2, or Capterra may be unavailable unless the user provides access.
  • No API key is required by default.

Limits And Known Issues

  • The result is only as reliable as accessible sources.
  • Funding, team, pricing, and review information can be outdated, hidden, or paywalled.
  • Competitor identification may be low confidence in new or ambiguous categories.
  • The skill does not replace legal, financial, investment, or compliance diligence.
  • The skill does not publish, edit, or modify the user's website.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.