wordpress-llm-optimization
Skill1 starsChanged 12 days agoMITView on GitHub
Use when the user wants their WordPress content optimized for AI search and assistants: being cited by ChatGPT/Claude/Perplexity/AI Overviews, "LLM SEO", "GEO", "AEO", answer engine optimization, or "make my site show up in AI answers". Triggers on "optimize for AI search", "LLM-friendly", "get cited by AI", "answer engine".
In this repository29 other files it gives its agents.
- ads-studioSkill
- blog-post-and-newsletterSkill
- calendarSkill
- chapter-draftingSkill
- character-mergeSkill
- financeSkill
- getting-startedSkill
- manuscript-importSkill
- manuscript-revisionsSkill
- markersSkill
- marketing-studioSkill
- mentionsSkill
- pen-namesSkill
- quick-task-captureSkill
- sales-studioSkill
- social-handoffSkill
- story-bibleSkill
- stos-setupSkill
- tasksSkill
- timelineSkill
- time-trackingSkill
- wordpress-connectSkill
- wordpress-mediaSkill
- wordpress-pagesSkill
- wordpress-postsSkill
- wordpress-productsSkill
- wordpress-seoSkill
- worldbuilding-mergeSkill
- worldbuildingSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 39
Keep the author's voice — restructure paragraphs, don't sand the prose down to listicle mush.
- Distinctive: line 40
Never invent facts to fill an FAQ.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
WordPress LLM optimization
Restructure posts and pages so AI assistants can retrieve, quote, and cite them. Complements wordpress-seo (classic search); run that skill's audit too when the user wants both.
Tools
Same WordPress tools as wordpress-seo — content-level changes only:
stos_wp_posts_get({ id, penNameId? })
stos_wp_posts_update({ id, fields: { title, content, excerpt }, penNameId? })
stos_wp_pages_get / stos_wp_pages_updateMultiple sites: pass penNameId (from stos_pen_names_list) to target a specific pen name's site; omit for the account default. Ask which site when the user has several pen names.
What LLM-retrievable content looks like
- Answer-first structure — the direct answer to the page's core question appears in the first ~2 sentences, then the elaboration. AI retrieval quotes openings.
- Self-contained sections — each H2/H3 section makes sense quoted alone: restate the subject in the section ("Amazon KDP royalties are…" not "They are…"). No "as mentioned above".
- Extractable Q&A — a short FAQ block near the end with real questions as H3s and 1–3 sentence answers. Add matching FAQPage JSON-LD in a
<script type="application/ld+json">block. - Clear entity naming — full names on first use (book titles, pen names, series, tools); pronouns only after the entity is established in the same section.
- Facts in stable shapes — prices, dates, steps as lists or tables, not buried in prose.
- Freshness signals — a visible "Last updated" line when the user revises evergreen content.
Workflow
- Fetch the post, map its structure (headings, opening, FAQ presence).
- Score against the six points above; report the gaps briefly.
- Rewrite with
stos_wp_posts_updateafter the user approves the plan — preserve voice; restructure, don't flatten.
Cautions
- Keep the author's voice — restructure paragraphs, don't sand the prose down to listicle mush.
- Never invent facts to fill an FAQ; pull answers from what the post already establishes.
- For published posts, keep the slug and title intent stable (see wordpress-seo's redirect caution).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

