Seo aeo amplifier
Skill respira-press/agent-skills-wordpress/skills/seo-aeo-amplifier
Agent skills for WordPress — works in Claude Code, Codex, Antigravity, Cursor, and any agent supporting Skills + MCP. Audit, optimize, fix, and migrate WordPress sites.
npx -y skills add respira-press/agent-skills-wordpress --skill seo-aeo-amplifierAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
10.8 KB, as published. Nobody here has run it
SEO & AEO Amplifier
Version: 1.3.0 Updated: 2026-06-30 Freshly updated: v1.3.0 takes a snapshot with respira_get_snapshot before any edit so every change is one-click reversible, switches from full extract/inject to surgical respira_find_element + respira_update_element edits for meta titles, descriptions and H1s, applies schema and meta across many pages in a single safe pass with respira_batch_update, and wires respira_generate_activity_report into the "SEO work done -> client report" handoff. Also leans on the real SEO analysis tools (respira_analyze_seo, respira_analyze_aeo, respira_analyze_rankmath, respira_check_seo_issues, respira_check_structured_data) instead of hand-rolled scoring.
Comprehensive on-page SEO and Answer Engine Optimization (AEO) audit and auto-fix system for WordPress sites. Scans all content, detects issues, generates intelligent schema markup, and creates optimized duplicates for review.
What This Skill Does
Finds:
- Missing or weak title tags and meta descriptions
- Poor heading structure (multiple H1s, skipped heading levels, non-descriptive headings)
- Missing image alt text across all media
- Thin content (pages under 300 words)
- Broken internal links
- Orphaned pages (no internal links pointing to them)
- Non-descriptive URL slugs
- Content that could answer questions but lacks FAQ schema
- Missing structured data (Article, HowTo, Product, Event, Video, Review)
- Content not optimized for featured snippets
- Missing table of contents on long-form content
- No clear Q&A structure for "People Also Ask" boxes
Provides:
- Comprehensive SEO health score (0-100)
- Page-by-page opportunity analysis
- Automated duplicate creation with all fixes applied
- Intelligent schema markup generation based on content type
- Before/after comparison for every fix
- Plugin-specific guidance (Yoast SEO, Rank Math, or plugin-agnostic)
Generates Schema Markup:
- Article schema (blog posts, news)
- FAQ schema (Q&A content detected)
- HowTo schema (tutorial/guide content)
- Product schema (WooCommerce products - requires WooCommerce add-on)
- Event schema (event content detected)
- Video schema (embedded videos detected)
- Review schema (review content detected)
- Breadcrumb schema (site navigation)
- Organization/Website schema (site-wide)
Requirements
- Respira for WordPress plugin installed and connected
- MCP connection active (desktop or WebMCP)
- WooCommerce add-on (optional - for product schema)
- Read access to scan site, write access to create duplicates
Trigger Phrase
- "amplify my seo and aeo"
Alternative Triggers
- "optimize my site for search engines"
- "run seo aeo audit"
- "improve my search visibility"
- "scan for seo opportunities"
Execution Workflow
Phase 1: Comprehensive Audit
- Verify Respira + MCP connection via
respira_get_site_context. If unavailable, stop and show setup guidance. - Detect SEO plugin setup using
respira_list_plugins:- Yoast SEO
- Rank Math
- No SEO plugin
- Scan all published pages and posts:
respira_list_pagesrespira_list_posts
- For each content item, load content and metadata:
respira_read_pageorrespira_read_postrespira_get_builder_infowhen needed
- Analyze on-page SEO. Prefer the real analysis tools over hand-rolled checks:
respira_analyze_seofor the on-page SEO pass (title, meta, headings, content depth, links)respira_check_seo_issuesfor the prioritized issue list per pagerespira_analyze_rankmathwhen Rank Math is detected (reads its score and recommendations)respira_check_structured_datato see which schema types already exist vs are missing- Supplement with
respira_list_media+ in-content image checks for alt text coverage - Cross-checks the tools cover: title quality, meta description quality, heading hierarchy (single H1, no level skips), content depth, internal links / orphaned pages, URL slug descriptiveness
- Analyze AEO opportunities with
respira_analyze_aeo(answer-engine readiness), plusrespira_check_structured_data:- FAQ potential (question patterns)
- HowTo potential (step-by-step patterns)
- Featured snippet opportunities
- Missing table of contents on long-form pages
- Missing structured data per content type
- Build opportunity scoring:
- Critical / High / Medium / Low
- Per-page opportunity score (0-100)
- Produce full report with:
- Overall health score
- Priority matrix
- Top opportunity pages
- Plugin-specific integration notes
Phase 2: Ask for Confirmation
After report, ask:
I found [X] pages with SEO/AEO opportunities. Would you like me to create optimized duplicates for all of them? You will review before publishing.
If user declines, stop after delivering recommendations.
Phase 3: Auto-Fix on Duplicates (Only If Approved)
- Snapshot first. Before touching anything, take a snapshot with
respira_get_snapshotso the whole pass is one-click reversible viarespira_restore_snapshotif a fix looks wrong. - For each selected page/post:
- Create the review copy with
respira_create_page_duplicate(pages) orrespira_create_post_duplicate(posts)
- Create the review copy with
- Apply fixes on the duplicate only. Use surgical edits, not full extract/inject:
- Locate the exact node first with
respira_find_element(find the meta title, meta description, and the H1 / heading elements), then change only that node withrespira_update_element. This avoids re-writing the whole page and keeps the builder's structure intact. - Optimize title tags (target < 60 chars)
- Generate/rewrite meta descriptions (target 150-160 chars)
- Fix heading structure (single H1, logical hierarchy)
- Add/repair image alt text
- Add table of contents for long-form pages
- Restructure Q&A blocks for FAQ readiness
- Generate and inject JSON-LD schema markup
- Improve URL slug when safe and requested
- Locate the exact node first with
- Apply the same fix across many pages in one safe pass with
respira_batch_update(for example, the same Organization/WebSite schema or a meta pattern across a set of duplicates) instead of looping one slow update at a time. - Save remaining page-level changes with
respira_update_page/respira_update_post. - Verify with
respira_check_seo_issues/respira_check_structured_dataon a sample of the fixed duplicates to confirm the issues actually cleared. - Produce before/after comparison snapshots for representative pages.
- Summarize totals:
- Duplicates created
- Titles/meta/schema/alt/headings fixed
- Snapshot id (so the user knows the rollback point)
Plugin Integration Behavior
Yoast SEO detected
- Read Yoast metadata
- Populate Yoast-compatible meta fields on duplicates
- Add JSON-LD schema only where Yoast does not already cover the content type
- Suggest focus keywords and readability improvements
Rank Math detected
- Read Rank Math metadata
- Populate Rank Math-compatible meta fields on duplicates
- Add JSON-LD schema where missing
No SEO plugin detected
- Insert meta tags and JSON-LD directly in duplicate content
- Recommend optional Yoast or Rank Math adoption
Schema Generation Rules
Generate schema based on detected content intent:
- Article: blog/news/editorial content
- FAQPage: clear Q&A content patterns
- HowTo: procedural/step-by-step content
- Product: WooCommerce products (if add-on/tools available)
- Event: event date/location content
- VideoObject: embedded YouTube/Vimeo/video blocks
- Review: clear review/rating content
- BreadcrumbList: URL hierarchy
- Organization / WebSite: site-level identity signals
All schema must be JSON-LD and valid structure-first (no fabricated claims).
Output Format
Always include:
- Executive summary
- Overall score + severity counts
- Top opportunities with impact rationale
- Plugin integration notes
- Clear confirmation prompt for duplicate creation
If auto-fix is run, also include:
- Fix summary totals
- Before/after samples
- Review instructions in WordPress admin
Safety Model
- Read-only audit first
- Snapshot via
respira_get_snapshotbefore any write, restore withrespira_restore_snapshot - Explicit user confirmation before changes
- Duplicate-first changes only
- Never auto-publish
- Provide rollback guidance
- Preserve live content unless user explicitly approves publishing workflow
Client Report Handoff
When the audit and (optional) fixes are done, turn the SEO work into a deliverable the customer can hand to a client or keep for their own records:
- Call
respira_generate_activity_reportto pull the actual edits made in this session (titles, meta, schema, alt text, headings) into a structured "SEO work done" report. - Pair it with the before/after samples and the snapshot id from Phase 3 so the report shows what changed and how to roll it back.
- Good fit for monthly retainers: run the audit, apply approved fixes on duplicates, then export the activity report as the month's SEO summary.
Honest Disclaimer
This skill identifies SEO/AEO opportunities and creates optimized duplicates for review.
It cannot:
- Guarantee rankings
- Fix off-page SEO or backlinks
- Fix server-level technical SEO by itself
- Publish without review
It can:
- Find broad on-page SEO and AEO gaps
- Generate structured schema recommendations and implementation
- Create transparent before/after duplicate drafts quickly
Tooling
Core WordPress tools
respira_get_site_contextrespira_list_pagesrespira_list_postsrespira_read_pagerespira_read_postrespira_get_builder_inforespira_list_mediarespira_list_pluginsrespira_create_page_duplicaterespira_create_post_duplicaterespira_update_pagerespira_update_post
SEO / AEO analysis tools
respira_analyze_seorespira_analyze_aeorespira_analyze_rankmathrespira_check_seo_issuesrespira_check_structured_data
Precision edit + safety tools
respira_find_element(locate meta title / description / H1 nodes)respira_update_element(change only that node)respira_batch_update(apply schema/meta across many pages in one pass)respira_get_snapshot(snapshot before edits)respira_restore_snapshot(one-click rollback)
Reporting
respira_generate_activity_report(SEO work done -> client report)
WooCommerce tools (optional)
woocommerce_list_productswoocommerce_get_product
Telemetry
After run completion, send fire-and-forget usage tracking to:
POST https://www.respira.press/api/skills/track-usage
Include:
skill_slug = seo-aeo-amplifier- site/version context
- duration and success
- issues found and fixes applied counts
- tools used
Never block user flow on telemetry failure.
Related Skills
- WordPress Site DNA
- Technical Debt Audit
- Mobile Experience Report
Built by Respira Team
https://respira.press/skills/seo-aeo-amplifier
Gives 0 of the 12 instructions most seo skills give
Counted across 454 of the 460 authors here whose files we hold, read 2026-08-06
- implement structured data using JSON-LDin 30 of 454, across 26 files
- write unique meta descriptions under 160 charactersin 27 of 454, across 20 files
- verify one H1 exists per pagein 24 of 454, across 15 files
- maintain a single h1 per pagein 24 of 454, across 15 files
- use JSON-LD format for all schema markupin 23 of 454, across 15 files
- use descriptive anchor text for internal linksin 21 of 454, across 16 files
- add descriptive alt text to imagesin 19 of 454, across 15 files
- read product marketing context before auditingin 19 of 454, across 10 files
- write unique title tags under 60 charactersin 19 of 454, across 14 files
- add unique title and meta description per pagein 19 of 454, across 17 files
- Reference the sitemap in robots.txtin 19 of 454, across 18 files
- verify core web vitals meet thresholdsin 17 of 454, across 9 files
Said here and by no other author read
- take a snapshot before any edits
- create duplicate pages for review instead of editing live
- use surgical edits instead of full content replacement
- apply identical fixes across pages in one batch
- generate schema markup based on content type
- produce before and after comparison snapshots
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.