conversion-agency/agentic-seo-skills / skills/competitive-analysis
competitive-analysis
VerifiedWhen the user wants to compare domains or URLs against competitors across SEO footprint, share of voice, keyword/content gap, head-to-head pages, off-page link gap (via backlink-analysis), and brand positioning. Orchestrates evidence from serp-extract, keyword-research, backlink-analysis, and topic-cluster without duplicating their work.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 16.6 KB |
| contract.yaml | config | 685 B |
| evals/fixture.md | markdown | 3.9 KB |
| references/modules/M1-footprint.md | markdown | 2.4 KB |
| references/modules/M2-share-of-voice.md | markdown | 3.4 KB |
| references/modules/M3-keyword-gap.md | markdown | 2.5 KB |
| references/modules/M4-link-gap.md | markdown | 2.0 KB |
| references/modules/M5-content-footprint.md | markdown | 3.4 KB |
| references/modules/M6-head-to-head.md | markdown | 2.3 KB |
| references/modules/M7-brand.md | markdown | 3.8 KB |
references/modules/M5-content-footprint.md
View on GitHub# M5 — Topical Authority & Content Footprint
Content territory mapping across players: how many URLs cover which subtopic, with what depth, format, and freshness.
## Inputs
- Per-player sitemap URL (default `/sitemap.xml`, accepting nested sitemaps).
- `attach_topic_cluster_ref: <seed-slug>` (optional) — anchors the subtopic taxonomy.
- `subtopics[]` (optional fallback) — when no cluster ref, the user-supplied taxonomy.
- `freshness_window_months`: default 24.
## Compute rules
- **Content Footprint Map**: per player, count URLs per top-level path (`/blog/`, `/guia/`, `/case/`, etc.) using sitemap discovery. Record coverage method (`sitemap | crawl | user-supplied`) and missing sections.
- **Topical Coverage Matrix**: for each subtopic in the cluster (or subtopics input), classify per player as `ausente | tangencial | dedicado | hub`. Rules:
- `ausente`: no URL slug or `<h1>` matches the subtopic term.
- `tangencial`: subtopic appears inside a broader URL but is not the main subject.
- `dedicado`: ≥1 URL has the term in slug or H1 and ≥ N useful words (configurable, default 600).
- `hub`: ≥3 URLs covering different angles of the same subtopic, with cross-linking observed.
- **Intent Coverage Spread**: distribute the URLs per subtopic by intent (informacional/comparativa/transacional/navegacional/branded-defensiva). Intent comes from URL+title evidence; mark `unknown` when ambiguous.
- **Format & Module Inventory**: per URL, presence of `FAQ`, `tabela`, `vídeo`, `embed YouTube`, `calculadora` (form + script), `glossário interno`, `citação externa`, `schema Article/Review/HowTo/FAQPage`. Aggregate counts per player.
- **Content Freshness**: per URL, `published_at` and `updated_at` from `article:published_time`, `article:modified_time`, schema `datePublished`/`dateModified`, or visible date. Aggregate median age and share updated within `freshness_window_months`.
## Row shapes (YAML)
```yaml
coverage_matrix:
- subtopic: ""
by_player:
- player: ""
coverage: ausente | tangencial | dedicado | hub
sample_urls: []
evidence_path: project/audits/competitive-<run-slug>/sources/m5/<player>/...
format_inventory:
- player: ""
counts:
faq: 0
tabela: 0
video: 0
embed_youtube: 0
calculadora: 0
glossario_interno: 0
citacao_externa: 0
schema_article: 0
schema_review: 0
schema_howto: 0
schema_faqpage: 0
freshness_table:
- player: ""
urls_total: 0
median_age_days: null
updated_within_window_pct: null
intent_coverage:
- subtopic: ""
by_player:
- player: ""
intents:
informacional: 0
comparativa: 0
transacional: 0
navegacional: 0
branded_defensiva: 0
unknown: 0
```
## Edge cases
- Sitemap blocked or fragmented: declare `coverage_method: incomplete` and surface `missing_sections`.
- URL renders without `published_at`/`updated_at` evidence: freshness fields stay `null`; never derive from URL path.
- Subtopic absent from the cluster: skip; do not invent subtopics from competitor URLs.
- Multilingual sites: filter sitemaps to the project language by `hreflang` or URL pattern before counting.
## Anti-patterns
- Inferring intent from URL slug alone.
- Counting word length and calling it "quality".
- Inventing `updated_at` from URL slugs containing dates.
- Mixing apex domain and subdomain footprints without recording the rule.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |