AI Agent Workflow Collection

Use when you need to measure (not just describe) brand citation frequency across AI search surfaces over time. Runs a configurable brand-mention prompt set weekly against ChatGPT (OpenAI API), Perplexity (Sonar API), and optionally Google AI Mode / AI Overviews / Bing Copilot / Claude.ai (manual workflow). Stores NDJSON history for trend analysis. Triggers from "track AI citations", "AI Overview citation tracker", "ChatGPT brand mention monitoring", "Perplexity citation tracking", "AI-Sichtbarkeit messen", "wie oft erwähnt ChatGPT meine Marke". Complements [[ai-search-rescue]]: that skill is the framework, this skill is the measurement loop.

Use when an e-commerce business sells across multiple channels (own shop, Amazon, OTTO, eBay, Etsy, Zalando, etc.) and wants to know which channel is actually profitable vs which is bleeding money — e.g. "which channel makes money?", "is OTTO/Amazon worth it?", "channel break-even calculation", "marketplace profitability", "Kanal-Ökonomie", "soll ich den Channel zumachen?". Also triggers when ad budget allocation decisions are needed across channels, or when consolidating to fewer channels is being considered.

Use when the user wants Google Search Console data pulled directly into the session instead of manually screenshotting / CSV-exporting from search.google.com. Pulls top queries, top pages, coverage status, manual actions, security issues, and Core Web Vitals field data via the GSC API in one call. Triggers from "pull GSC data for example.com", "Search Console deep dive", "GSC queries last 90 days", "GSC coverage report", "GSC indexing status", "GSC manual actions check", "GSC Core Web Vitals field data". Removes the manual GSC click-through that is the friction point of every recovery / audit session.

Use when a website experienced a sudden visibility/ranking drop that correlates with a published Google Core Update — symptoms include broad ranking loss across many keywords in a short window (1–6 weeks), Sistrix VI dropping 30 %+ from peak, sales/leads falling despite no technical changes, the owner saying "we used to rank, now we don''t" but pages still load and index normally. Distinguishes Core-Update damage from CWV/technical drops and produces a phased 6–12 month recovery plan focused on Authority and EEAT.

Use when setting up automated weekly PageSpeed Insights tracking for a set of URLs — to catch performance regressions before users notice, or to validate that performance optimizations actually stuck over time. Triggers from "weekly PSI tracking", "PageSpeed monitoring", "Core Web Vitals over time", "PSI cron", "performance drift detection", "set up automated lighthouse runs". Uses the free Google PSI v5 API (25k calls/day quota with API key). Stores historical data as NDJSON for trend analysis and triggers alerts on regressions.

Audits all SEO changes made to a domain within a given period (read-only). Reconstructs change history from cache, Shopware updatedAt fields and crawl diffs when logs are missing. Detects Settlement-Gate-triggering Major Batches, writes recovery-gate.json, and emits the hypothesisregistry that recovery-plan needs for live-fix-eligible actions.

Screaming Frog MCP crawl + issue classification. Crawls up to 500 URLs, extracts broken links, redirect chains, missing H1s, canonical errors, and missing meta descriptions. Classifies issues by severity with upgrade rules. Outputs structured issues.json to cache.

Automatic domain diagnosis for Core Update recovery. Calls Sistrix + DataForSEO MCP, quantifies VI drop, identifies keyword losses, scans backlink profile, correlates with known Core Update dates. Outputs structured befund.json to cache. Use when starting recovery analysis for a domain.

Full recovery workflow orchestrator. Chains recovery-diagnose, recovery-crawl, recovery-plan, and recovery-monitor in sequence. One command for complete domain recovery analysis from diagnosis to monitoring setup. Gracefully degrades if individual steps fail.

Weekly recovery tracking. Fetches current VI + keyword positions, computes 0-100 recovery score, appends to NDJSON history, outputs delta report. Run weekly or on-demand to track recovery progress over time.

Generates a prioritized recovery action plan from diagnosis + crawl data. Determines recovery phase (R1-R5), builds Do-Not-Touch list for stable keywords, prioritizes actions by Impact x Effort x Risk, enforces batch-change limits. Requires recovery-diagnose to have run first.

Orchestrator and entry point for the seo-rescue plugin. Routes to the nine sub-skills covering SEO rescue work after Google Core Updates: free-tier audit, recovery framework, decision-maker PDF reports, channel economics, competitor gap analysis, weekly PSI tracking, AI search rescue, AI citations tracker (NEW v0.4 — weekly cron measuring brand citations in ChatGPT/Perplexity/AI Overviews), and GSC deep-dive (NEW v0.4 — one-call Google Search Console API snapshot). Type /seo-rescue:rescue to see the routing table or call sub-skills directly via their namespaced slash command.

Use when generating a polished single-PDF SEO snapshot for a third-party domain owner. The output is a decision-maker-friendly document in plain language for non-SEO-experts (shop owners, founders, executives), not a technical site audit. Triggers include "send the owner of X.de an SEO snapshot", "generate a report for the owner", "show X.de their SEO status", "make a PDF for a non-technical decision maker about their SEO". Complements claude-seo:seo-audit when the goal is communication for a non-technical audience rather than technical depth. Complements make-pdf when the input is a domain (not a markdown file) and the workflow needs editorial narrative integrated with Sistrix / DataForSEO / PSI data.

CSV-first weekly recovery review during an active SEO recovery. No SISTRIX API key required. Compares current and previous SISTRIX keyword exports and produces a structured Monday Check report with Recovery Signal Score, per-cluster recovery stage, winner/loser neutralization analysis, money-keyword protection list, URL-level recovery table, optional GSC cross-check, optional conversion-rate validation, and one of six recommended actions (Observe / Protect / Strengthen / Investigate / Correct / Escalate) with an explicit What-Not-To-Touch guard for winning URLs. Triggers from "Monday recovery check", "SISTRIX recovery review", "weekly Monday SEO ritual", "compare this Monday SISTRIX to last Monday", "is the visibility index lagging behind ranking gains", "winner-loser neutralization check", "are my money keywords protected". Full output contract in SISTRIXMONDAYRECOVERYCHECK.md; operational detail in RECOVERYSYSTEM.md sections 4-10.

Use when analyzing a subscription or recurring-revenue business (news site, paywall publisher, SaaS-light, membership platform, e-commerce with subscription tier) for monetization gaps and revenue-growth levers. Combines outside-in detection (paywall structure, tier visibility, ad density, trust signals) with optional inside-out import of MRR / churn / cohort data from a Stripe / Chargebee / Recurly CSV export. Triggers include "wir verbrennen Geld und wissen nicht woher das Wachstum kommen soll", "MRR stagniert", "Abo-Konversion ist zu niedrig", "subscription revenue model review", "premium tier evaluation", "warum wachsen wir nicht mehr", "Burn-Rate vs. Revenue-Lücke schließen". Anti-Use: NICHT für reine transaktionale E-Commerce-Shops ohne Subscription (channel-economics-analyzer ist dafür), NICHT für B2B-Enterprise-SaaS mit Custom-Pricing (anderes Playbook), NICHT für Pre-Revenue-Startups (Skill setzt eine bestehende Subscription-Basis voraus).

Use when a site has lost visibility in AI search surfaces (Google AI Overviews, Google AI Mode, ChatGPT citations, Perplexity citations) or wants to systematically work toward being cited rather than just ranked. Trigger phrases include "AI Overviews recovery", "ChatGPT zitiert uns nicht mehr", "wir sind aus den AI Overviews rausgeflogen", "generative engine optimization", "GEO strategy", "AI search visibility", "warum zitiert AI Overview den Wettbewerber statt uns", "Perplexity-Citations aufbauen". Anti-Use: NICHT für klassische SERP-Rankings — dafür existieren seo-outreach-report und competitor-deep-audit.

Use when an e-commerce or content site wants to deeply understand WHO their organic competitors are (often surprising — not the brands they think) and WHERE the competitors outrank them — e.g. "competitor analysis", "keyword gap analysis", "who outranks me", "Wettbewerber-Lücken", "wo verlieren wir gegen die Konkurrenz", "content opportunities from competitor SERPs". Produces a prioritized opportunity list (keyword + search volume + competitor URL + your current position) for the next content-roadmap quarter. Triggers also from "Sistrix Konkurrenten" or "DataForSEO competitors".

Use when the user wants a basic SEO health check on a domain WITHOUT paying for any SEO tools — e.g. "kostenloser SEO-Check", "SEO ohne Sistrix", "ich habe nur Google Search Console und nichts anderes", "Anfänger-Audit", "wo fange ich beim SEO an", "billiges SEO" oder als Vorstufe vor dem entscheidet ob die kostenpflichtigen Tools (Sistrix, DataForSEO) sinnvoll sind. Anti-Use: NICHT für tiefere Wettbewerbsanalyse, Sichtbarkeitsverlauf, oder professionelle Outreach-Reports — dafür existiert seo-outreach-report mit den paid APIs.