Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

agentic-seo

Étoiles4

Forks1

Mis à jour10 juillet 2026 à 08:50

Master skill for SEO auditing, optimization, and Core Web Vitals tracking on any web project. Delegates to the correct narrow leaf skill. Use when auditing SEO health, updating meta descriptions or title tags, adding structured data (JSON-LD), comparing audit snapshots, setting up performance monitoring, optimizing for AI/GEO citation, writing AEO content blocks, or planning programmatic SEO pages. Triggers on: "SEO audit", "meta description", "structured data", "schema markup", "title tags", "open graph", "core web vitals", "LCP", "CLS", "INP", "seo compare", "seo optimize", "ranking", "sitemap", "GEO", "AI citation", "AI Overviews", "llms.txt", "programmatic SEO", "pSEO", "answer engine", "featured snippets", "E-E-A-T", "content patterns".

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

alexander-kastil

alexander-kastil/agentic-sw-engineering

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en études de marché et spécialistes en marketingProfessions des affaires et des opérations financières·SOC 13-1161

Explorateur de fichiers

4 fichiers

SKILL.md

readonly

name	agentic-seo
description	Master skill for SEO auditing, optimization, and Core Web Vitals tracking on any web project. Delegates to the correct narrow leaf skill. Use when auditing SEO health, updating meta descriptions or title tags, adding structured data (JSON-LD), comparing audit snapshots, setting up performance monitoring, optimizing for AI/GEO citation, writing AEO content blocks, or planning programmatic SEO pages. Triggers on: "SEO audit", "meta description", "structured data", "schema markup", "title tags", "open graph", "core web vitals", "LCP", "CLS", "INP", "seo compare", "seo optimize", "ranking", "sitemap", "GEO", "AI citation", "AI Overviews", "llms.txt", "programmatic SEO", "pSEO", "answer engine", "featured snippets", "E-E-A-T", "content patterns".
license	Complete terms in LICENSE.txt

agentic-seo — SEO & Performance Router

Routes SEO, structured data, and performance requests to the appropriate leaf skill references. For full audits, default to the core audit references first and load additional leaf skills only when the user explicitly asks for them or when a confirmed public finding requires them.

Default Execution Rule (Full Analysis)

Unless the user explicitly restricts scope (e.g. "only check technical SEO", "just update the meta tags"), load and apply the core audit references in this order:

Load references/agentic-seo-audit-general.md — health review & roadmap
Load references/agentic-seo-audit-technical.md — technical runtime audit
Load references/seo-on-page.md — titles, headings, E-E-A-T, internal linking
Load references/seo-technical.md — robots.txt, sitemap, canonicals, hreflang, CWV
Load references/seo-ai-geo.md — AI Overviews, GEO, llms.txt, AI bot rules
Load references/seo-schema-markup.md — JSON-LD schema templates
Load references/agentic-seo-compare.md — before/after snapshot comparison, but only after the current audit is fully scored

Load these only when the user explicitly asks for them or when the task changes from auditing to implementation/planning:

references/agentic-seo-optimize.md
references/seo-content-patterns.md
references/seo-programmatic.md
references/setup-vitals.md

Run findings from the core audit set in sequence. Consolidate into a single prioritized output unless the user asks for separate reports per area.

Blocking Audit Boundary

For SEO audits, score only what a crawler can discover from robots.txt, sitemap.xml, visible navigation, and public links reachable from audited pages.
Do not create findings from hidden CMS structure, configuration internals, non-public sections, or checked-in generated output unless those details leak into public runtime output.
Do not force-check guessed routes or hidden collection URLs unless they appear in the visible nav, sitemap, robots rules, public HTML, or the user explicitly names them.
Use code inspection only to confirm the root cause of a public finding. Code inspection is not audit evidence by itself.
Do not score local preview host/port mismatches as SEO defects. Treat them as audit-environment notes unless the same mismatch is visible on a public deployment or the user explicitly asks to debug the local setup.

Local-First Audit Policy

For audits and optimization work, use the local preview or dev instance first.
Reuse an existing local app and browser session when the user has already provided one.
Prefer browser/runtime inspection over terminal-driven process discovery.
Do not test production URLs by default.
Only inspect production when the user explicitly asks for production validation.
Core Web Vitals monitoring setup remains a separate workflow and may target production when the user asks for monitoring infrastructure.

When to Use This Skill

Running a full SEO health audit across the site
Updating meta descriptions, title tags, or Open Graph data for a page
Adding or updating JSON-LD structured data (Course, Service, Organization schemas)
Comparing two SEO audit snapshots to measure progress
Setting up or monitoring Core Web Vitals (LCP, INP, CLS)
Optimizing for AI citation, GEO, and answer engine visibility

Trigger keywords: SEO audit, seo check, meta description, title tag, open graph, schema markup, JSON-LD, structured data, core web vitals, LCP, CLS, INP, ranking, sitemap, lastmod, seo compare, GEO, AI citation, AI Overviews, llms.txt, programmatic SEO, pSEO, answer engine, featured snippets, E-E-A-T, content patterns

Delegate Map

All leaf skills are loaded by default. Use this table for scoped requests or to find a specific reference.

Leaf skill reference	Covers
`agentic-seo-audit-general`	General SEO health review, scoring, and backlog
`agentic-seo-audit-technical`	Technical local runtime SEO audit
`agentic-seo-optimize`	Meta tags, OG data, JSON-LD schema updates
`agentic-seo-compare`	Before/after audit snapshot comparison
`setup-vitals`	Core Web Vitals automated monitoring setup
`seo-on-page`	Titles, meta descriptions, headings, E-E-A-T, internal linking
`seo-technical`	robots.txt, sitemap, canonicals, hreflang, CWV thresholds, mobile
`seo-ai-geo`	AI Overviews, ChatGPT/Perplexity citation, GEO methods, llms.txt
`seo-schema-markup`	JSON-LD templates for all schema types
`seo-content-patterns`	AEO/GEO content block patterns (definition, FAQ, stats, quotes)
`seo-programmatic`	Programmatic SEO at scale: 12 playbooks, templates, locations

Example Prompts

"Run an SEO audit." — loads all leaf skills, produces consolidated report
"Run a full SEO audit of the site." — same, full analysis across all dimensions
"Run only a technical SEO audit." — loads agentic-seo-audit-technical + seo-technical only
"Update the meta description and JSON-LD schema for the training page." — loads agentic-seo-optimize only
"Compare the March SEO audit against the February baseline." — loads agentic-seo-compare only
"Set up automated Core Web Vitals monitoring." — loads setup-vitals only

Plus depuis ce dépôt

même dépôt

claude-learn

alexander-kastil/agentic-sw-engineering

Master skill for the reflect->capture->distribute learning loop in any repository: its MAIN TASK is to reflect on a session/task and turn what it taught into durable, reusable knowledge, then distribute it. Reflect on what a session revealed, capture it by authoring/updating skills, agents, docs, and a lessons file, and distribute it both to the team (repo-local `.claude/skills/`, committed) and across projects (global `~/.claude/skills/`) via push learnings up, pull skills down, or reconcile, all through the bundled skill-sync leaf. Delegates each step to the correct leaf skill. Triggers on: "reflect", "review session", "what did we do", "session summary", "learnings", "capture lessons", "update lessons", "improve skills", "update docs", "analyze conversation", "learning loop", "create skill", "update skill", "new skill", "write a skill", "global skill", "promote skill", "sync skills", "reconcile skills", "pull global skill", "skills out of sync", "drift audit", "skill drift".

2026-07-184

brand-voice-gh-copilot

alexander-kastil/agentic-sw-engineering

Audit and fix Markdown files for brand-voice quality in the "Agentic Software Engineering using GitHub Copilot" masterclass (audience: software engineers): em dashes, Mermaid label syntax, paragraph length, and topic-specific slash command tables. Trigger phrases: brand voice check, quality check, check writing quality, fix em dashes.

2026-07-184

compliance

alexander-kastil/agentic-sw-engineering

Master skill for regulatory compliance assessment of a product: routes to the matching leaf and covers both the AI-specific and the personal-data regulations. Leaf `eu-ai-act` handles EU AI Act risk-tier classification (prohibited / high-risk / limited-risk transparency / minimal), the Article 50 transparency-disclosure pattern for consent screens and Terms of Service, and stakeholder/owner checklists. Leaf `dsgvo` handles DSGVO / GDPR personal-data compliance: lawful basis, data-subject rights, privacy notice, processor (Art. 28) agreements, records of processing, DPIA, breach notification, third-country transfers, and the compliance-check checklist. Use when asked to "check compliance", "compliance checklist", "EU AI Act compliance", "is our AI high-risk", "Article 50 transparency", "DSGVO compliance", "GDPR compliance", "check for DSGVO", "are we GDPR compliant", "do we need a privacy notice / Datenschutzerklärung", "lawful basis", "data subject rights", "data processing agreement", "AVV", "DPIA", "data br

2026-07-184

create-guide

alexander-kastil/agentic-sw-engineering

Author a single demo or lab guide for a hands-on class of any audience, in one of three styles chosen by audience: prompt-recipe (business/maker, the five-part step model), guided (initial project setup), or walkthrough (code, Microsoft-Learn style with run commands and expected output). Places the file at the module root as demo-NN-slug.md or lab-NN-slug.md, scaffolds any runnable project and companion assets, and updates the folder TOC. Peer skill the create-class master delegates to; also invocable directly. Trigger phrases: create a guide, write a demo, author a lab, demo guide, lab guide, prompt recipe, walkthrough guide, learn style guide, run-verified guide.

2026-07-184

create-slides

alexander-kastil/agentic-sw-engineering

Turn a topic readme into presentation slides for a hands-on class, via one of two first-class paths chosen per class. Gamma path: analyse a topic readme and emit Gamma-ready slide spec files (frontmatter plus heading, bullets, optional Mermaid) into the module pptx/ folder, with a merge-slides sub-capability that combines multiple Gamma PPTX exports to beat Gamma's ~10-item-per-call cap. PPTX path: generate a local .pptx deck directly with python-pptx (via the pptx skill) for classes that do not use Gamma. The master create-class skill delegates here; also invocable on its own. Trigger phrases: create slides, topic to slides, gamma slides, pptx deck, slide spec, merge slides, generate deck, slides from readme, build a deck.

2026-07-184

create-teaching

alexander-kastil/agentic-sw-engineering

Enrich a module README with a use-case intro, a topic-specific slash-command table, and key documentation links, adapted to the module's audience (developer, low-code maker, or business user). Peer skill that the create-class master delegates to by name; also invocable directly. Trigger phrases: enrich module readme, module readme, use case intro, slash command table, key links, teaching content, enhance for business owner, business audience, adapt readme for business users, topic-specific slash commands.

2026-07-184