agentleFS
kostja94kostja94/marketing-skills/skills/competitor-research/SKILL.md

competitor-research

Skill1.1k starsChanged 26 days agoMITView on GitHub

When the user wants to find competitors for a product or website, assess substitutes, or analyze competition for content, search visibility, backlinks or positioning. Also use when the user mentions "competitor analysis," "competitor research," "competitor keywords," "competitor backlinks," "link gap," "content gap," "competitor content," "competitive analysis," or "competitor comparison." For content roadmap, use content-strategy.

29 other projects use a version of this.

Trending

More talk lately.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 1 mentionApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 2 mentionsNov 2026: 1 mention
Dec 2025Jun 2026Nov 2026
Mentions a month of the kostja94/marketing-skills repository that our weekly crawl found: only 4 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Most recently taken up by

Used with

Projects with it also use icp-research, level and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • growthack88Skill

    icp-research

    Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Produces TAM analysis, firmographic segments, champion and economic buyer personas, use case mapping, customer proof points, and voice-of-customer synthesis with normalized attributes. Requires website URL as primary input. Upstream: recommended company-context. Downstream: feeds positioning, product-messaging, landing-page-copy, content-strategy, and outreach-emails.

    Also in 5 projects that use this

  • dachi-jp3Skill

    level

    表示レベル(auto / low / medium / high)を切り替える。

    Also in 3 projects that use this

  • VercelSkill

    messaging

    Use when turning settled positioning into the lines other people will reuse: the message hierarchy, value propositions per audience, objection handling, and the proof behind each claim.

    Also in 4 projects that use this

  • ai-agents-for-agencies-coachesSkill

    brand-kit

    Establish and enforce per-client brand fidelity using the DESIGN.md standard (google-labs-code/design.md). Use whenever starting work for a client, creating any ad/landing-page/creative, or when brand colors/fonts/spacing are needed. Auto-extracts a client's visual identity into a validated DESIGN.md, keeps a central registry, and feeds the tokens into image-studio (statics), fb-ad-video-studio (video), and landing pages. Triggers: "set up brand for <client>", "make a DESIGN.md", "match the client's brand", "what are their brand colors", "new client onboarding", any creative work that must be on-brand.

    Also in 4 projects that use this

  • nocodeworkSkill

    company-context

    Interview the user to build or update a reusable company context file for AI tools — what the company does, its offer, clients, personas, positioning, voice, and the questions clients ask most. Use when the user says "build our company context", "create company context", "set up business context for AI", "update our company context", or wants AI to answer clients and write content in the company's voice without re-explaining the business each time. Produces company-context.md.

    Also in 3 projects that use this

  • VercelSkill

    positioning

    Use when working out what a product is, who it's for, and what it competes with: the market alternatives, the ideal customer, the differentiators worth claiming, and the positioning statement that follows.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start with the reference product or URL, market and user task.

    line 18
  2. Distinctive:

    Start with known products, manual alternatives and adjacent steps in the user workflow.

    line 22
  3. Distinctive:

    Search "[brand] alternatives".

    line 29
  4. Distinctive:

    Keep the discovery surface distinct from the competitive relationship.

    line 33
  5. Distinctive:

    When analyzing or auditing a single article, use this lightweight workflow to obtain competitor articles:

    line 76
  6. Distinctive:

    Fetch content: Use mcp_web_fetch or WebSearch to fetch 2–3 top-ranking pages

    line 79

“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Competitor Research

Guides competitor research for SEO, content, backlinks, and positioning. Use when planning content, auditing articles, building links, or evaluating market position.

When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

For marketing engagements, lead with the content and distribution view. Use product comparisons to identify meaningful differences and claims the client can support. For a positioning or replacement question, lead with the product view. Use research workflow to select the evidence, follow discoveries and assemble the final report. The SEO and backlink methods below are optional modules selected by scope.

Discover competitors and classify relationships

Start with the reference product or URL, market and user task. Inspect the product page to establish the input, outcome and intended user. Set the comparison unit (company, product, capability or feature). For an unknown site or ambiguous brand, verify identity before adding candidates.

Choose a product view for user choice, replacement and switching costs; choose a marketing/content view for who attracts the same audience or answers the same question. For a baseline study, maintain one register and derive both views.

  1. Start with known products, manual alternatives and adjacent steps in the user workflow. Inspect navigation, templates, integrations, comparison, alternatives, migration and support pages. Identify unexpected pages and examine the action a user can take there.
  2. For a promising finding, record the actual URL and what it demonstrates. Search the specific feature, user problem or output in the target market, then inspect at least one new candidate when attainable. Trace the chain from original page through query to new evidence. Stop at the agreed boundary or when new sources repeat existing tasks and relationships.
  3. For each material candidate record the comparison unit and task, relationship (direct, indirect, manual substitute, upstream, downstream or platform), coverage (whole or partial, with scope), surface (product, search, community or other evidenced channel), source URL, date and confidence. Leave uncertain relationships pending. Vendor mentions establish leads; check the other product or independent task evidence before claiming substitutability. An import list establishes supported sources, not parity or market share.
  4. Deliver the register, strongest discovery trail and open checks. Offer comparison pages for substantiated evaluation needs, alternatives pages for supported replacement tasks and migration pages for executable transfer paths. Hand keyword-research the source URL, observed action, inferred need and concrete seed when a finding warrants query validation.

Search from a known brand and from a user task

  • Search "[brand] alternatives". Capture the publisher, the reference product, named replacements and the job each claims to replace. Check both vendor comparison pages and third-party lists. Follow promising names to their official product or feature pages.
  • Search the competitor brand and relevant branded variants in the target market. Inspect placements explicitly labeled as ads. Record query, locale, date, advertiser, visible destination and promoted benefit. An ad impression supports competition for that search opportunity; the advertiser's selected keyword, match type and spend remain unknown. If ads cannot be inspected, mark coverage pending. If an ad promises a different workflow, investigate that relationship separately.
  • Search "best [specific feature or job]" and "best [tool] for [audience or constraint]". Extract products and the reasons for inclusion, then check the claimed capability at the source. Use the new feature or use case as the next query to discover specialist providers beyond familiar brands.

Keep the discovery surface distinct from the competitive relationship. Deduplicate products across ads, lists and alternative pages while retaining each independent source and what it establishes.

Discover products through their distribution channels

Map the task to the device or host where the user performs it. For each relevant environment, inspect the native marketplace or in-product add-on catalog: mobile app stores, browser extensions, collaboration or CRM marketplaces, integration directories and connector/template galleries. Start with categories, collections, related apps, publisher portfolios and host recommendations as well as native search. Follow the tools and endpoints named by a connector into their own listings. For private or login-only catalogs use available authorized access or request a listing/export when needed; mark unchecked surfaces explicitly.

Record the store and locale, host, listing URL or stable ID, publisher, workflow step, inputs and outputs. Distinguish first-party features, standalone apps, extensions of known products, third-party connectors and recipes. Group multiple distribution listings under the same product while preserving channel-specific capabilities. A listing supports availability and stated scope; user reviews provide leads for use cases to verify. Record whether discovery used the native catalog or only a publicly indexed listing.

Research Types

TypePurposeOutput
Keyword/topicTopics competitors rank for; gapsKeyword opportunities; content ideas
ContentStructure, length, gaps vs top rankersLength target; H2 structure; content gaps
BacklinkLink profile; sites linking to competitorsLink gap; outreach targets
PricingCompetitor pricing, positioningPricing context; differentiation
SEO metricsOrganic traffic, rankings vs competitorsBenchmark; opportunity areas

Competitor Keyword / Topic Analysis

MethodPractice
Reverse engineeringAnalyze competitor titles, H1, URL; identify topics they rank for
SERP overlapKeywords with overlapping top-ranking pages → same cluster; #4–10 = opportunity
site: operatorsite:competitor.com to see indexed pages
ToolAhrefs, Semrush—competitor keyword overlap, gap analysis

Output: Keyword opportunities; topics competitors cover that you don't.

Competitor Content Analysis

ElementCheck
Word countTop 10 average; length target for your content
H2 structureTopics covered; structure to adopt
Content gapsWhat top rankers cover that you miss
Keyword placementPrimary keyword in title, H1, first 100 words
FormatLists, tables, FAQ; match or improve

Use when: Auditing or creating articles; see article-page-generator for Research Phase integration.

Competitor Article Fetch Workflow (for Article Analysis)

When analyzing or auditing a single article, use this lightweight workflow to obtain competitor articles:

  1. Obtain URLs: From the user, relevant Contextus competitor or content modules, or web search for "[target keyword]" to find top-ranking pages
  2. Fetch content: Use mcp_web_fetch or WebSearch to fetch 2–3 top-ranking pages
  3. Analyze: Word count, H2 structure, keyword placement, content gaps, CTA, schema
  4. Output: Competitor URLs, brief structure comparison, content gaps, length target, keyword opportunities

Output format: Competitor URLs; word count and H2 structure per URL; content gaps vs your article; recommended length target; keyword opportunities (terms top rankers use that your article misses).

Competitor Backlink Analysis

ActionPurpose
Compare profilesYour backlinks vs competitors
Link gapSites linking to competitors but not you
OpportunityOutreach to those sites; content they might link to

Tools: Ahrefs, Semrush—Link Intersect, competitor backlink reports. See backlink-analysis.

Competitor Pricing

UsePractice
PositioningWhere you sit vs competitors
DifferentiationValue prop when price differs
Alternatives pagesWho to include; how to position

See pricing-strategy, alternatives-page-generator.

Data Sources

SourceUse
SimilarWebTraffic, engagement, traffic sources by domain
AhrefsCompetitor domains, backlinks, DR
SEMrushOrganic competitors, traffic share
GAReferral traffic, acquisition by source
PostHogCompetitor feature usage (if tracked)

Report Workflow

  1. Parse — Read Excel/CSV, infer domain, visits, traffic sources, etc. from headers
  2. Enrich — Web search, visit competitor sites; read root {project}.md if present
  3. Build — Structure data for report
  4. Generate — Output report in chosen format

Output Format

  • Competitors identified
  • Research type (keyword, content, backlink, pricing)
  • Findings (gaps, opportunities, benchmarks)
  • Recommendations (content to create, links to pursue, positioning)

Report Structure Reference

SectionContent
Executive SummaryKey findings (top 3), top 3 recommendations
Competitor OverviewCompetitor, category, market position, key strength
Product ComparisonFeature/capability vs Us vs Competitors
SWOT AnalysisOur strengths/weaknesses/opportunities/threats; competitor deep dives
Marketing & MessagingValue prop, target audience, key channels
Gaps & OpportunitiesGap, opportunity, priority
Prioritized RecommendationsRecommendation, impact, effort, owner

Related Skills

  • keyword-research: Competitor reverse; keyword discovery
  • article-page-generator: Competitor article analysis in Research Phase
  • content-strategy: Competitor analysis for topic mapping
  • content-optimization: Competitor length and structure as reference
  • backlink-analysis: Competitor backlink comparison; link gap
  • seo-monitoring: Competitive comparison; organic vs competitors
  • alternatives-page-generator: Competitor selection; comparison framing
  • migration-page-generator: Competitor migration paths
  • pricing-strategy: Competitor pricing context
  • affiliate-marketing: Find affiliates promoting competitors
  • directories: Competitor info for directory submissions

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.