Takes a raw list of keywords and groups them into topic clusters presented as a table, then suggests one specific blog topic per cluster so you're not left guessing what to write about each group. Meant to run right after keyword research and before assigning topics to writers or an editorial calendar. Works especially well fed directly with the long-tail keyword output from a seed-keyword prompt.
A structured conversion audit for an underperforming landing page, built from a screenshot description, the conversion goal, current conversion rate, and target audience.
- Evaluates the above-the-fold section, headline, and value proposition, scored 1-10
- Reviews CTA placement, copy, and trust signal inventory
- Identifies specific friction points along the conversion path
- Suggests concrete A/B tests to run
- Delivers a priority-ordered fix list
- Works best with an actual screenshot attached, since it leans on above-the-fold visual signals
Builds an FAQ section that reads as genuinely local rather than a generic template with the city name swapped in, using a business description, city/region, common customer concerns, and known local competitors as inputs.
It researches and organizes questions into general local, area-specific service, local pricing/availability, and regional regulation/compliance categories, plus competitor differentiators, and outputs FAQ schema markup ready to implement. Run in deep-research mode so local regulations get verified rather than guessed.
Expands a single service page into genuinely distinct versions for multiple target cities, using the original service page content, a list of target cities, and any local market insights you have. For each city it produces a localized title tag, a unique opening paragraph, a local market context section, city-specific pain points, where to place local proof or testimonials, neighborhood mentions, and local schema markup recommendations. Keep each city variant substantially unique, since thin swapped-city-name pages risk being treated as duplicate content.
Branches a single seed keyword out into a list of long-tail queries a real customer might type, ranked by commercial intent rather than just volume.
- Inputs: seed keyword, how many long-tail keywords to generate, and a description of the product or service
- Returns the full list of long-tail variations
- Follows up by picking the three with the strongest commercial intent and explaining why
- Meant to run once per seed keyword from a broader seed list
- Feed the winning keywords straight into the keyword clustering prompt next
For a blog post that already has its primary keyword in place, this suggests a set number of LSI, or Latent Semantic Indexing, related terms to deepen topical coverage.
A follow-up pass maps each suggested LSI keyword to the specific section or paragraph where it fits naturally, so you're not just left with a word list. The prompt itself warns against forcing every term in, since over-applying LSI keywords leads to stuffing.
Paste in your current meta title, current meta description, target
keyword, and the top-ranking competitor titles and descriptions pulled
from the live SERP.
The prompt returns three rewritten title tag options and three meta
description options, each with character counts, plus a CTR optimization
rationale, a differentiation strategy against what's already ranking, and
A/B testing recommendations.
Feed in this month's SEO metrics, the previous period's numbers, campaign
activities, and budget, and the prompt turns raw traffic and ranking data
into an executive-ready recap built around revenue impact, market share,
and efficiency gains rather than technical detail. Output includes a
performance headline, ROI highlight, top three strategic wins, a five-metric
dashboard, competitive position update, next month's focus, and an
investment recommendation for stakeholders who only see SEO once a month.
Drops in a single content section and rewrites it so it answers the
underlying query more directly, reading cleanly to both search engines'
NLP models and human readers.
Useful for passages that ramble, bury the answer, or read vague — no
setup is needed beyond the text itself, which makes it a fast mid-edit
fix rather than a full content rewrite workflow.