gooseworks-ai/goose-skills / skills/marketing/improve-search-visibility
improve-search-visibility
VerifiedSEO and AI-answer visibility. Use for a site SEO or technical audit with ranked fixes, competitor keyword and topic gaps, a topic cluster, SEO metrics for domains, a programmatic SEO page-set plan, or checking where ChatGPT and Google name the brand. Delivers the requested audit, comparison, map or blueprint with dated evidence and clear data limits. Also covers app store listings and local search. Drafts changes; never edits live. Full pages go to make-content; paid search goes to run-paid-campaigns.
references/rival-content-map.md
View on GitHub# Rival content map (free)
Use for the requested competitor, audit or pSEO branch. It answers **what kinds of pages do the rivals have that we don't?** ("They have 12 comparison pages and 40 integration pages; you have none.") Everything here is free: sitemaps and the host's own fetch (marketing-guide §3, "Public data"; the `marketing-data-access` skill (`../../marketing-data-access/SKILL.md`) lists sitemaps as a free source).
## Who to map
Use the requested rivals. Otherwise choose a focused set from the tracked roster (`competitor_read`) and observed search competitors, explaining the selection. The requested comparison count wins.
## 1. Read each sitemap
`/sitemap.xml`, else `/sitemap_index.xml` (follow its child sitemaps), else the `Sitemap:` line in `/robots.txt`, else the blog feed (`/feed`, `/blog/feed`). If these are absent or incomplete, inspect public blog/resource/navigation indexes or available crawl exports for the requested scope. Record discovery methods and limits; do not imply the sitemap is a complete content inventory. Hosts that cannot fetch mark the unavailable checks and say why.
## 2. Sort every URL by page type
Use the URL first, the page title when the URL is unclear. Adapt patterns to the site (a `/compare/` folder is the same type as `/vs/`).
| Page type | Typical URL patterns |
|---|---|
| Comparison ("X vs Y") | `/vs/`, `/compare/`, `-vs-` |
| Alternatives | `/alternatives/`, `/alternative-to-` |
| Integration | `/integrations/`, `/apps/`, `/marketplace/` |
| Use case or role | `/use-cases/`, `/for-`, `/solutions/`, `/roles/` |
| Industry | `/industries/`, `/for-<industry>` |
| Template or example | `/templates/`, `/examples/` |
| Glossary or "what is" | `/glossary/`, `/what-is/` |
| Free tool or calculator | `/tools/`, `/calculator` |
| Case study | `/customers/`, `/case-studies/`, `/stories/` |
| Pricing | `/pricing` |
| Docs and help | `/docs/`, `/help/` |
| Blog (editorial) | `/blog/`, `/posts/`, `/articles/` |
| Location | `/locations/`, `/<city>/` |
| Other | anything else |
## 3. Spot the templated sets
A type with dozens of near-identical URLs that vary on one thing (a rival's name, a tool, an industry, a city) is a templated set. For each: page count, what varies, whether it looks clean or auto-generated. Sample 3–5 pages per set (one obvious, one long-tail, one in between) and score each 1–5 on:
| Dimension | What to look for |
|---|---|
| Depth | real sections and detail, not a paragraph swapped per page |
| Unique value per page | facts that only this page has (a real comparison, real integration steps) |
| Data | tables, prices, screenshots, specifics |
| Freshness | a visible date, current prices |
| Internal links | links to related pages and back to a hub |
Average ≥ 4: well built, hard to beat without a real difference. 3–4: beatable with better pages. < 3: thin — easy to beat, and a quality risk if it's ours. Our own templated sets use the same score (and the foundation check's risk rule).
## 4. The page-type gap table (goes in the report's story)
| Page type | You | Rival A | Rival B | Rival C | Gap? |
|---|---|---|---|---|---|
| Comparison | 0 | 12 | 8 | 3 | **yes** |
| Integration | 2 | 40 | 28 | 15 | partly |
| Case study | 0 | 22 | 15 | 8 | **yes** |
A candidate gap means we lack useful coverage for an intent relevant to our buyers while a checked rival invests in it. Two rivals provide stronger evidence, not a prerequisite. A type everyone has is not automatically ours to copy: weigh it against what buyers ask (don't follow the herd). Counts come from sitemaps on the date read; in the story say it plainly ("from each site's public list of pages, read 19 Oct — it can miss pages"), never the word "sitemap" outside the developer section.
## 5. Where it lands
For an AI-answer check, a relevant gap becomes a needed roadmap row and a first-page brief. For a topic/ranking-gap request, continue to the topic-level matrix in `seo-jobs.md`; page-family counts alone do not fulfill it. For a pSEO request, continue to the complete page-family blueprint, data model and pilot in `seo-jobs.md` rather than stopping at one sample page.
Use `seo-data.md` for ranking, demand and traffic evidence. A set's existence or template score never proves it ranks or drives traffic. Topic architecture and a useful pSEO blueprint can be drafted without numerical volume/difficulty, with demand confidence stated.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |