aaron-he-zhu/aaron-marketing-skills

competitor-analysis

Use when the user asks to "analyze competitors" or "竞品分析"; benchmarks competitor keywords, content, backlinks, AI citations, and traffic share into strengths, weaknesses, and an action plan.

Ver código-fonte
Documento original do Skill

Renderizado do repositório de origem, preservando títulos, exemplos, código, tabelas, links e imagens.

Competitor Analysis

Analyzes competitor SEO and GEO strategies to reveal repeatable wins, weak spots, and market gaps.

Quick Start

Analyze SEO strategy for [competitor URL]
Compare my site [URL] against [competitor 1], [competitor 2], [competitor 3]

Skill Contract

Expected output: a prioritized competitor brief plus the standard handoff summary for memory/research/.

  • Reads: competitor URLs/domains, your own site metrics, business model, target audience, industry context, and any user-provided or tool data.
  • Writes: a user-facing analysis and reusable summary.
  • Promotes: durable competitor facts, keyword priorities, entity candidates, and pending strategy decisions to memory/hot-cache.md, memory/open-loops.md, and memory/research/.
  • Done when: 3-5 competitors are benchmarked across keywords, backlinks, and traffic share in one comparison table; each strength-to-learn and weakness-to-exploit cites evidence; and the deliverable closes with an Immediate / Short-term / Long-term plan.
  • Primary next skill: content-gap-analysis when the competitive landscape is clear.

Handoff Summary

Emit the standard shape from skill-contract.md §Handoff Summary Format.

Data Sources

Optional integrations: ~~SEO tool, ~~analytics, ~~AI monitor. Without tools, ask for competitor URLs, your site metrics, and industry context. See CONNECTORS.md.

Zero-dependency competitor fetch (keyless): python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecrawl.py" scrape <competitor-url> returns the rendered page as LLM-ready markdown (JavaScript-heavy pages included), firecrawl.py map <competitor-domain> --limit 500 inventories their URL surface fast, and firecrawl.py search "<brand or topic>" --tbs qdr:m finds their fresh coverage — all on Firecrawl's keyless free tier (~1,000 credits/mo). The connector pre-flights the target's robots.txt locally and refuses on a Disallow per SECURITY.md §Scraping Boundaries. See scripts/connectors/README.md.

Decision Gates

Stop and ask — when the competitor set cannot be established:

  1. No competitors named and none inferable from CLAUDE.md, prior research, or the user's niche → ask the user to name 2-5 competitors, OR offer to infer them from a target keyword via serp-analysis first.

Continue silently — do not stop for: which 3-5 of a longer list to deep-dive (pick the closest direct competitors and note the rest); missing your-own-site metrics (benchmark competitors against each other and mark your row N/A); missing optional tool data (label Estimated and proceed).

Instructions

When a user requests competitor analysis:

  1. Identify Competitors — separate direct competitors, indirect alternatives, and content competitors if the user has not named them already.
  2. Gather Competitor Data — capture URL, domain age, estimated traffic, domain authority, business model, target audience, and key offerings.
  3. Analyze Keyword Rankings — document total rankings, top 10/top 3 counts, high-value keywords, intent mix, and keyword gaps.
  4. Audit Content Strategy — review content volume, top performers, publishing patterns, themes, and success factors.
  5. Analyze Backlink Profile — review backlink totals, quality mix, top linking domains, link acquisition patterns, and linkable assets.
  6. Technical SEO Assessment — evaluate Core Web Vitals, mobile-friendliness, architecture, internal linking, URL structure, and standout strengths/weaknesses.
  7. GEO / AI Citation Analysis — test which queries cite competitors, what formats get cited, and where competitors still leave openings.
  8. Synthesize Competitive Intelligence — deliver an Executive Summary, comparison table, CITE comparison, strengths to learn from, weaknesses to exploit, keyword opportunities, content recommendations, and an Immediate / Short-term / Long-term plan.

Label every metric Measured (tool/export), User-provided, or Estimated (model inference); never present an estimate as measured; if a required metric is unavailable, mark it N/A — do not invent it.

Quality bar: every strength or weakness ties to a labeled metric and a named competitor — a specific ranking or backlink figure for a named domain, not "strong content presence".

Reference: See Analysis Templates for the compact templates used at each step.

Example

See references/example-report.md for a full sample analyzing HubSpot's marketing keyword dominance.

Advanced Analysis Types

Content Gap Analysis

For a pairwise topic-coverage gap map ("content [competitor] has that I don't, sorted by traffic potential"), hand off to content-gap-analysis — that is its dedicated job.

Video Benchmarking

When a competitor invests in video, benchmark their YouTube outliers (views >=2x their channel average) and the title/thumbnail packaging that drives those wins — those patterns show what topics and framing earn reach. See platforms/youtube.md.

Link Intersection

Find sites linking to [competitor 1] AND [competitor 2] but not me

SERP Feature Analysis

What SERP features do competitors win? (Featured snippets, PAA, etc.)

Historical Tracking

How has [competitor]'s SEO strategy evolved over the past year?

Save Results

Write path: memory/research/competitor-analysis/YYYY-MM-DD-<topic>.md; promote durable competitor facts and entity candidates to memory/hot-cache.md. See Skill Contract §Save Results Template.

Reference Materials

Next Best Skill

Primary: content-gap-analysis. Also: serp-analysis and offsite-signal-analyzer. If the goal is a head-to-head "us vs them" page, hand the vetted competitor set to page-play-builder.

do mesmo repositório

Mais Skills

Todos os Skills
aaron-he-zhu
Comunidade

ad-test-designer

Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试

instalações
1
GitHub Stars
2,7 mil
Atualizado
3 de set.
aaron-he-zhu
Comunidade

attribution-reconciler

Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution models, and reads incrementality from a geo/holdout test. Not for the point-in-time R2 veto or RQS gate — use ad-account-auditor; not for the ROI/ROAS ratio math itself — use roi-calculator; not for organic dark-social share attribution or GA4 direct-traffic decomposition — use dark-social-attributor. 付费广告归因对账/去重/增量

instalações
1
GitHub Stars
2,7 mil
Atualizado
3 de set.
aaron-he-zhu
Comunidade

audience-belief-mapper

Use when the user asks to "map what our buyers believe", "capture the objections we keep hearing", or "find the switching forces that move the beachhead"; produces a belief map of the beachhead — held beliefs and mental models, the recurring objections and their reframes, and the JTBD four forces (push of the problem, pull of the new, anxiety of switching, habit of the present) — each item sourced from interviews or win-loss notes (User-provided) and labeled Measured / User-provided / Estimated, with any unverified quote or comparative claim marked "[needs source]" and routed to the claims candidates, never adjudicated here. Not for demographic or persona profiling — use audience-mapper; not for the positioning canvas — use positioning-truth-tracer. 受众信念/异议地图/切换四力/流失语言

instalações
1
GitHub Stars
2,7 mil
Atualizado
3 de set.
aaron-he-zhu
Comunidade

audience-mapper

Use when the user asks to "analyze my target audience", "build an audience profile for influencer targeting", "research a niche community", or "deep-dive a subculture before partnering with creators"; in audience mode produces demographic/psychographic profiles, a platform-priority matrix, named personas, and an influencer-selection criteria set, and in niche mode produces a community map, culture decode (language/norms/taboos), key-voice tiers, a Brand Fit Score, and a phased entry strategy. Not for finding specific creators to contract — use influencer-discovery; not for scoring a shortlist on Suitability — use fit-scorer. 目标受众画像/人群分析 · 细分社群/亚文化调研

instalações
1
GitHub Stars
2,7 mil
Atualizado
3 de set.