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/M6-head-to-head.md
View on GitHub# M6 — Head-to-Head Page Comparison
URL-mode matrix comparing a target page against 1-N competitor pages disputing the same query or intent.
## Inputs
- `target_urls[]`: 1+ target URLs.
- `competitor_urls[]`: 1-N competitor URLs aligned with each target URL.
- `attach_serp_extract_run: <slug>` (optional) — feeds SERP features per query.
- `intent_focus`: optional string for grouping pairs.
## Provider/extractor surfaces
- Deterministic HTML extraction (reuse `technical-seo` extractor subset): title, meta description, H1-H4 tree, word count (useful body, excluding nav/footer/sidebar), schema types, image alt coverage, internal link count, external link count, last-modified observed.
- `serp-extract` evidence: SERP features owned per URL for the matching query.
## Compute rules
Emit one row per `target_url × competitor_url` pair. Each row records both URLs and their observable values; the report renders the matrix.
```yaml
page_matrix:
- pair_id: ""
intent_focus: ""
target_url: ""
competitor_url: ""
target:
title: ""
title_length: 0
meta_description: ""
meta_description_length: 0
h1: ""
h_tree_counts:
h1: 0
h2: 0
h3: 0
h4: 0
word_count_useful: 0
schema_types: []
image_alt_pct: 0
internal_links: 0
external_links: 0
last_modified: null
serp_features_owned: []
competitor:
<same shape as target>
diffs:
word_count_delta: 0
h2_delta: 0
schema_types_only_competitor: []
schema_types_only_target: []
serp_features_only_competitor: []
serp_features_only_target: []
```
## Edge cases
- Page fetch blocked or 4xx/5xx: skip the row, add a limitation with the URL and status.
- Multiple H1 on a page: keep both, surface as `h_tree_counts.h1: 2` and note in synthesis.
- Word count outliers (>10000 words): keep but tag with `word_count_outlier: true`.
- Schema detection: rely on JSON-LD parsing; microdata/RDFa not required for v1.
## Anti-patterns
- Re-running the full `technical-seo` audit; only the comparable subset.
- Counting nav/footer/sidebar text in word count.
- Inferring "better content" from word count alone.
- Mixing pairs from different intents into the same matrix without `intent_focus`.
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 |