Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →silverstein/minutes-seo-wave
Plan, build, and review one evidence-backed SEO content wave for the Minutes site, including SERP research, page inventory, design-system compliance, internal linking, generated LLM text, and a shipped-wave retro.
Passed 16 of 19 test cases with the skill, and 5 of 19 without it.
and 18 more in the full report
13 fixed6 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to inspect the sitemap configuration in our repository to ensure our new SEO landing pages are properly registered. What exact shell command reads the top 240 lines of the sitemap file?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies running sed -n '1,240p' site/app/sitemap.ts to inspect the sitemap file. | Missed | Passed |
The instructions your model reads when the skill loads.
Produce one coherent SEO content wave, not a pile of disconnected pages. Keep the method reusable across comparison pages, use-case or resource pages, and docs hubs.
Competitive research and keyword specifics are time-sensitive. Research them fresh for each wave. Internal competitive plans may exist in gitignored documentation; never invent, reconstruct, or embed those private specifics in this skill or in repository documentation.
Collect:
If theme or keywords are missing, inspect the repository and ask only for the choice that materially changes the wave. Do not invent search volume, keyword difficulty, competitor capabilities, pricing, compliance status, or product claims.
Map the current routes before proposing slugs or outlines:
rg --files site/app | rg '/page\.tsx$'
rg --files site/public | rg '\.md$'
sed -n '1,240p' site/app/sitemap.ts
Inspect relevant hubs, shared page components, adjacent pages, metadata, structured data, and markdown twins. Record pages that already satisfy the target intent, pages that should be refreshed instead of duplicated, and genuine content gaps.
Research each target query with current search results. Identify:
test cases passed, vs 5 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.