> Generate one unified performance report that brings together SEO rankings, AI-search visibility (SE Ranking) and social engagement (Planable) — delivered as a short text summary in chat plus a self-contained interactive HTML report. Use this skill whenever the user wants a combined cross-channel report, or says things like "give me a full report across SEO and social", "how did we do this month across search and social", "combined SEO + AI + social report for [client]", "build a cross-channel dashboard", or "one report that covers rankings, AI visibility and social". Always activate when the request spans both search (SE Ranking) and social (Planable) in a single report.
npx skills add https://github.com/seranking/seo-skills --skill seo-ai-social-report
Most reporting forces clients to read three tools separately. This produces one view: search rankings and AI-search visibility from SE Ranking, social engagement from Planable, with quick text conclusions for the inbox and an interactive HTML report for the detail.
us), the Planable workspace, the reporting period (default: previous calendar month), and optionally competitors for share-of-voice.Before doing anything else, verify both MCPs are reachable:
DATA_getSubscription. If it fails or returns an auth error, stop immediately and tell the user:> "The SE Ranking connector isn't responding — please reconnect it before we continue. Setup guide: https://seranking.com/api/integrations/mcp/"
list_workspaces. If it fails or returns an auth error, stop immediately and tell the user:> "The Planable connector isn't responding — please reconnect it before we continue. Setup guide: https://help.planable.io/hc/en-us/articles/27538577098780-How-to-connect-Planable-MCP-to-your-AI-tools"
Only continue to the process steps below once both calls return a successful response.
Confirm domain, Planable workspace, period, and competitors. Resolve the period to explicit start/end dates.
PROJECT_getSummary and PROJECT_getPositionHistory(site_id, type: avg_pos | visibility, date_from, date_to) for the ranking trend; optionally reuse a finished audit (PROJECT_listAudits → getAuditReport) for a site-health number.DATA_getDomainOverviewWorldwide for the snapshot.organic_traffic / overall_traffic streams for the chosen country — you can reuse those for the organic-trend chart instead of a separate history call.DATA_getAiSearchOverview(target, source, brand?) with the default time-series view — brand presence, link presence, AI opportunity traffic, average position, plus monthly trend streams (including organic/overall traffic). If previous is null, treat it as a baseline — don't render the change_percent of 100 as growth.DATA_getAiSearchLeaderboard(primary, competitors[], source, engines[]) — share of voice vs competitors (only if competitors were provided). Query it narrowly (few engines/competitors per call) — it can time out on large requests.list_pages(workspaceId) → page IDs.get_page_metrics_summary(workspaceId, pageIds, startDate, endDate) — account-level audience/impressions/engagement-rate.get_post_metrics_summary(workspaceId, pageIds, startDate, endDate) — published-post totals in the window. (Different scope from page impressions — keep them separate.)get_post_metrics(workspaceId, pageIds, ..., limit: 5) — top posts.list_posts(...) — posts published in the period (volume/cadence).get_page_metrics_summary once per month bucket.A ~10–15 line plain-text summary: the headline move in each of the three areas (SEO, AI search, social), then 2–3 specific callouts ("what moved", "what to watch"). This is the part most people actually read — make it sharp and number-led, no filler.
Use the bundled template at assets/report-template.html as the starting point — it has the Planable colour palette, the card/section layout, and Chart.js (CDN) wired up, including a dual-axis trend chart. Populate it with the real data you pulled:
Inline the data as JavaScript arrays in the file (no external data files, no localStorage). Save to the outputs folder as {client}-{period}-cross-channel-report.html, then share it with present_files. Validate the inline script parses (a quick node --check-style pass) before presenting.
present_files, with KPI cards, hoverable trend charts, share-of-voice, and top posts.unsupportedPages; base totals on supported channels and note the rest as "data not available".A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
Take seranking/seo-ai-social-report from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.