# Sf Google Quality Content > Generate and refine SEO/editorial content aligned with Google Search Quality Evaluator Guidelines (QRG), with explicit E-E-A-T, YMYL risk handling, and anti-spam quality controls. Use when creating or revising blog posts, landing pages, guides, product/category content, FAQs, editorial calendars, and content briefs in the Search Foundry (SF) method, especially when quality, trust, originality, an… - **Type:** Skill - **Install:** `agentstack add skill-search-foundry-sf-ai-skills-sf-google-quality-content` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [Search-Foundry](https://agentstack.voostack.com/s/search-foundry) - **Installs:** 0 - **Category:** [Search](https://agentstack.voostack.com/c/search) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [Search-Foundry](https://github.com/Search-Foundry) - **Source:** https://github.com/Search-Foundry/sf-ai-skills/tree/main/skills/content/sf-google-quality-content ## Install ```sh agentstack add skill-search-foundry-sf-ai-skills-sf-google-quality-content ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # SF Google Quality Content Use this skill to produce or audit SEO/editorial content that is genuinely helpful, trustworthy, and aligned with Google QRG. ## Language mode - Default to Italian if the user writes in Italian. - Default to English if the user writes in English. - If the target market is specified, adapt language, examples, and terminology to that market. - Preserve the same quality controls in both languages. ## Workflow (EN) ### 1) Frame the task before writing - Define audience, locale, funnel stage, and business goal. - Define the query intent cluster: informational, transactional, navigational, local, mixed. - State the page purpose in one sentence. - Classify YMYL risk (`none`, `moderate`, `high`) and required trust threshold. ### 2) Build the evidence base - Collect source facts, first-hand signals, and brand-owned proof points. - Mark each key claim with a source type: first-party data, expert statement, primary source, secondary source. - If claims are sensitive (health, finance, legal, civic), require high-confidence sourcing and clear attribution. ### 3) Define E-E-A-T strategy (explicitly) - Experience: add direct use, lived context, tests, real cases, or operational details. - Expertise: show qualified knowledge level needed for topic risk. - Authoritativeness: connect to recognized entities, references, or track record. - Trust: prioritize accuracy, transparency, edit quality, and absence of deception. - For YMYL content, trust and correctness are mandatory gates, not optional enhancements. ### 4) Produce the content - Write for the dominant intent first; cover secondary intents only if they help users. - Use clear information hierarchy: answer first, then depth, then supporting detail. - Prefer concrete examples, comparisons, and practical steps over generic prose. - Separate facts, interpretation, and opinion. - Declare uncertainties and limits when present. ### 5) Run the quality gate (required) - Reject content if it appears mass-produced, derivative, or with little added value. - Reject content with sensational, misleading, or manipulative framing. - Reject content missing who-is-responsible signals when needed (author/site accountability). - Reject YMYL content with mild inaccuracies or weak trust signals. - Check ads/monetization and UX do not obstruct main content comprehension. ### 6) Final output package - Deliver: - Final content draft. - Metadata block: intent, audience, YMYL level, E-E-A-T notes. - Risk notes: potential quality issues and mitigations. - Editorial checklist result (`pass` or `revise`). - If user requests only an audit, return prioritized fixes instead of a rewrite. ## Flusso operativo (IT) ### 1) Imposta il task prima di scrivere - Definisci audience, mercato/lingua, fase del funnel e obiettivo business. - Definisci il cluster di intento: informativo, transazionale, navigazionale, local, misto. - Scrivi in una frase lo scopo della pagina. - Classifica rischio YMYL (`none`, `moderate`, `high`) e soglia di trust richiesta. ### 2) Costruisci la base di evidenze - Raccogli fatti, segnali di esperienza diretta e prove proprietarie del brand. - Etichetta ogni claim con tipo fonte: first-party data, expert statement, primary source, secondary source. - Per claim sensibili (salute, finanza, legale, civico), richiedi fonti solide e attribuzione esplicita. ### 3) Definisci la strategia E-E-A-T in modo esplicito - Experience: inserisci prove di uso diretto, test, casi reali, dettagli operativi. - Expertise: calibra profondità e precisione sul rischio del tema. - Authoritativeness: collega il contenuto a entità/fonti riconoscibili. - Trust: priorità a accuratezza, trasparenza, qualità editoriale e chiarezza su limiti. - Per YMYL, trust e correttezza sono gate obbligatori. ### 4) Produci il contenuto - Copri prima l'intento dominante; gli intenti secondari solo se utili. - Usa gerarchia chiara: risposta rapida, approfondimento, supporto. - Preferisci esempi concreti, comparazioni e passaggi applicabili. - Separa fatti, interpretazione e opinioni. - Dichiara incertezze e limiti quando presenti. ### 5) Esegui il quality gate (obbligatorio) - Scarta contenuti derivativi, generici o con scarso valore aggiunto. - Scarta framing fuorviante/sensazionalistico. - Scarta contenuti senza segnali chiari di responsabilità editoriale quando necessari. - Scarta YMYL con imprecisioni anche lievi o segnali di trust deboli. - Verifica che monetizzazione/UX non ostacolino la comprensione del main content. ### 6) Pacchetto di output finale - Consegna: - Bozza finale. - Blocco metadati: intento, audience, livello YMYL, note E-E-A-T. - Note rischio con mitigazioni. - Esito checklist (`pass` o `revise`). - Se la richiesta è solo audit, restituisci fix prioritizzati invece del rewrite completo. ## Search Foundry defaults - Anchor every piece to brand position and searchable user problem. - Prefer topic depth and distinct perspective over volume. - Treat originality as user value, not novelty for its own sake. - Keep claims falsifiable and easy to verify. - Optimize for long-term trust signals, not short-term ranking hacks. ## Output standards ### Required sections for long-form content - Summary answer (short, direct) - Main explanation (structured by intent sub-questions) - Evidence/experience elements - Limits, caveats, or conditions - Next action for the reader ### Required checks before delivery - Intent coverage check completed - E-E-A-T strategy explicitly visible in text - No "low effort / low originality / low value" segments - No unsupported claims in sensitive sections - Tone and structure align with target audience and brand ## Quick prompt patterns - "Create a content brief for [topic] with intent map, YMYL risk, E-E-A-T plan, and quality gate criteria." - "Rewrite this article to improve trust and originality while preserving factual accuracy." - "Audit this page against QRG-style risks and return top fixes by severity." - "Generate a category page draft that prioritizes helpfulness and decision support." - "Crea un brief contenuto su [topic] con intent map, rischio YMYL, piano E-E-A-T e criteri quality gate." - "Rivedi questo articolo per aumentare trust e originalità mantenendo accuratezza fattuale." - "Fai audit di questa pagina con rischi QRG e piano fix per severità." ## References - Read `references/qrg-sf-playbook.md` for compact rating-to-writing guidance. - Read `references/ready-to-use-examples.md` for reusable templates and examples in EN/IT. ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [Search-Foundry](https://github.com/Search-Foundry) - **Source:** [Search-Foundry/sf-ai-skills](https://github.com/Search-Foundry/sf-ai-skills) - **License:** Apache-2.0 Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-search-foundry-sf-ai-skills-sf-google-quality-content - Seller: https://agentstack.voostack.com/s/search-foundry - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.