Research → verify → score → plan → improve loop for SEO / AEO / GEO across the Unite-Group portfolio. Ingests Obsidian source data and (when supplied) YouTube channels, cross-verifies every claim against ≥4 sources, scores ranking opportunity / decay / freshness / GEO visibility with confidence-adjusted prioritisation, and produces human-gated site-improvement tickets. Never fabricates metrics. Orchestrates — does not duplicate — the existing google-search-console, google-business-profile, local-seo-agent, google-updates-sentinel, competitive-local-strategy and algorithm-knowledge-base skills.
EnglishComplete browser debugging workflow - element inspection, layout diagnostics, interaction tracking, visual tools via agnt proxy.
EnglishSupabase authentication patterns including getUser vs getSession, deadlock avoidance, session handling, and bypass patterns. Use when working with auth, sessions, cookies, or encountering auth hangs/timeouts. Keywords: auth, getUser, getSession, session, deadlock, timeout, cookie, token, Web Locks.
EnglishScan documents and slides for off-brand colors, fonts, and logos. Validate against brand guidelines and suggest corrections.
EnglishDetect breaking changes in Claude Code updates by comparing current API surface against changelog. Maps impacts to specific plugin files.
EnglishDrives an authenticated browser session on synthex.social (or localhost) WITHOUT the flaky Chrome extension. The reliable path is a committed Playwright script (scripts/browser/dashboard-audit.mjs) that logs in with the SYNTHEXTESTEMAIL / SYNTHEXTESTPASSWORD test account and audits every integration surface. Use whenever asked to "log in", "authenticate", "audit the dashboard", "check what's connected", or before browser-verify / site-smoke-test on /dashboard/ routes.
EnglishResearch a topic, draft the content, and package the approved publication bundle.
EnglishAI creative director with recursive self-assessment. Generates concepts using world-class methodologies (SIT, TRIZ, Lateral Thinking, bisociation), scores against 6 weighted criteria with Cannes/D&AD/HumanKind calibration, and recursively refines until the 9+ threshold is reached. Accepts briefs in any format — text, voice transcript, PDF, or raw notes. Use when the user asks to generate creative concepts, brainstorm campaign ideas, develop a Big Idea or campaign platform, evaluate or critique existing creative work, find consumer insights, or shares a brief for ideation. Do not use for media planning, production budgeting, brand identity/logo design, copywriting final drafts, or market research data collection.
EnglishPrisma ORM and PostgreSQL database management for EFT-Tracker. Handles schema design, migrations, client generation, and Neon database branches. Activates when user mentions: database, schema, migration, Prisma, model, relation, PostgreSQL, Neon, db push, db pull.
EnglishReview database schema design, query patterns, and data access layer for correctness and performance. Checks normalization balance, index coverage against actual queries, constraint completeness (NOT NULL, FK, unique, check, defaults), data type correctness (money as DECIMAL not FLOAT, timestamps with timezone), N+1 query detection, connection pooling configuration, transaction safety, and migration hygiene. Supports PostgreSQL, MySQL, SQLite, MongoDB, Firestore, DynamoDB, and all major ORMs. Use when you need to review a database schema, find missing indexes, detect N+1 queries, audit data types, check constraint coverage, optimize query patterns, or assess database scaling readiness.
EnglishThe "no invaders" gate for Synthex. The ship already carries everything it needs. NEVER add a new npm dependency, external SaaS, framework, datastore, or auth system to solve a problem an existing system already solves — adding one is a CEO-gated decision. ALWAYS prove the capability isn't already present (grep package.json, lib/, the skills list, Vercel env) before integrating anything new. Activate on ANY request to "add a package / install / npm i / integrate X / we need a tool / use library Y / add a provider / new database".
EnglishQuery Google Search Console analytics, inspect URL indexing status, manage sitemaps, and run PageSpeed Insights audits. Use when the user needs SEO data, search performance reports, indexing diagnostics, or Core Web Vitals analysis.
EnglishSenior Paid Performance Marketer (15+ yr calibration · Google Ads + Meta Ads + LinkedIn Ads). Owns paid-channel strategy across the 4 Nexus brands (DR · NRPG · RestoreAssist · CARSI) within Phase 1.2 80/20 risk posture and pilot-scale capital ceilings ($1–3k DR · $500–1k NRPG · $500 RA cold-search · CARSI feed-only). Produces single-variable paid-test designs with locked attribution windows, kill thresholds, sender-platform compliance checks (ATT · GDPR-equivalent · App Store policy), and explicit re-allocation criterion. Closes every test with a falsifiable lift hypothesis tied to the Q2.5.1 dual-flywheel position the spend is meant to feed. Reads ceo-foundation.md + verification-gates.md at every invocation.
EnglishSynthex platform showcase enforcer. NEVER describe features with generic marketing language ("powerful AI", "seamless integration") or produce wall-of-bullets capability lists. ALWAYS lead with a specific client outcome, use concrete numbers, and write in Australian English. Activate on ANY request to showcase a platform, explain a feature, demonstrate capability, or create platform presentation content.
EnglishProject introspection — detect languages, frameworks, database, structure, scale, auth,…
EnglishModern React patterns and principles. Hooks, composition, performance, TypeScript best practices.
EnglishSTART HERE — Skill discovery and installation assistant. The recommended first skill when you don't know which skills you need. Searches verified-skill.com, recommends plugin bundles, and installs skills. Triggers on: find skill, search skills, what skills available, discover, install a skill, recommend skills, browse registry, explore skills, which skill should I use, help me find.
EnglishSpecification generator - 7 phase document chain producing product brief, PRD, architecture, epics, and issues with Codex review gates. Triggers on generate spec, create specification, spec generator, workflow:spec.
English
AGENT SKILLS ATLASIncludes Agentic Marketing Intelligence, Agnt Browser Debug, Auth Patterns, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Agentic Marketing Intelligence
Research → verify → score → plan → improve loop for SEO / AEO / GEO across the Unite-Group portfolio. Ingests Obsidian source data and (when supplied) YouTube channels, cross-verifies every claim against ≥4 sources, scores ranking opportunity / decay / freshness / GEO visibility with confidence-adjusted prioritisation, and produces human-gated site-improvement tickets. Never fabricates metrics. Orchestrates — does not duplicate — the existing google-search-console, google-business-profile, local-seo-agent, google-updates-sentinel, competitive-local-strategy and algorithm-knowledge-base skills.
Agnt Browser Debug
Complete browser debugging workflow - element inspection, layout diagnostics, interaction tracking, visual tools via agnt proxy. 完整瀏覽器除錯工作流:元素檢測、佈局診斷、互動追蹤、視覺工具。 Use when: debug browser issue, inspect element, fix layout, debug click, debug form, debug modal, browser debugging workflow
Auth Patterns
Supabase authentication patterns including getUser vs getSession, deadlock avoidance, session handling, and bypass patterns. Use when working with auth, sessions, cookies, or encountering auth hangs/timeouts. Keywords: auth, getUser, getSession, session, deadlock, timeout, cookie, token, Web Locks.
Brand Consistency Checker
Scan documents and slides for off-brand colors, fonts, and logos. Validate against brand guidelines and suggest corrections.
Breaking Changes
Detect breaking changes in Claude Code updates by comparing current API surface against changelog. Maps impacts to specific plugin files.
Browser Auth
Drives an authenticated browser session on synthex.social (or localhost) WITHOUT the flaky Chrome extension. The reliable path is a committed Playwright script (scripts/browser/dashboard-audit.mjs) that logs in with the SYNTHEXTESTEMAIL / SYNTHEXTESTPASSWORD test account and audits every integration surface. Use whenever asked to "log in", "authenticate", "audit the dashboard", "check what's connected", or before browser-verify / site-smoke-test on /dashboard/ routes.
Commit Hygiene
Atomic commits, PR size limits, commit thresholds, stacked PRs
Content Pipeline
Research a topic, draft the content, and package the approved publication bundle.
Creative Director
AI creative director with recursive self-assessment. Generates concepts using world-class methodologies (SIT, TRIZ, Lateral Thinking, bisociation), scores against 6 weighted criteria with Cannes/D&AD/HumanKind calibration, and recursively refines until the 9+ threshold is reached. Accepts briefs in any format — text, voice transcript, PDF, or raw notes. Use when the user asks to generate creative concepts, brainstorm campaign ideas, develop a Big Idea or campaign platform, evaluate or critique existing creative work, find consumer insights, or shares a brief for ideation. Do not use for media planning, production budgeting, brand identity/logo design, copywriting final drafts, or market research data collection.
Database Prisma
Prisma ORM and PostgreSQL database management for EFT-Tracker. Handles schema design, migrations, client generation, and Neon database branches. Activates when user mentions: database, schema, migration, Prisma, model, relation, PostgreSQL, Neon, db push, db pull.
Database Review
Review database schema design, query patterns, and data access layer for correctness and performance. Checks normalization balance, index coverage against actual queries, constraint completeness (NOT NULL, FK, unique, check, defaults), data type correctness (money as DECIMAL not FLOAT, timestamps with timezone), N+1 query detection, connection pooling configuration, transaction safety, and migration hygiene. Supports PostgreSQL, MySQL, SQLite, MongoDB, Firestore, DynamoDB, and all major ORMs. Use when you need to review a database schema, find missing indexes, detect N+1 queries, audit data types, check constraint coverage, optimize query patterns, or assess database scaling readiness.
Dependency Discipline
The "no invaders" gate for Synthex. The ship already carries everything it needs. NEVER add a new npm dependency, external SaaS, framework, datastore, or auth system to solve a problem an existing system already solves — adding one is a CEO-gated decision. ALWAYS prove the capability isn't already present (grep package.json, lib/, the skills list, Vercel env) before integrating anything new. Activate on ANY request to "add a package / install / npm i / integrate X / we need a tool / use library Y / add a provider / new database".
Google Search Console
Query Google Search Console analytics, inspect URL indexing status, manage sitemaps, and run PageSpeed Insights audits. Use when the user needs SEO data, search performance reports, indexing diagnostics, or Core Web Vitals analysis.
Paid Performance Marketer
Senior Paid Performance Marketer (15+ yr calibration · Google Ads + Meta Ads + LinkedIn Ads). Owns paid-channel strategy across the 4 Nexus brands (DR · NRPG · RestoreAssist · CARSI) within Phase 1.2 80/20 risk posture and pilot-scale capital ceilings ($1–3k DR · $500–1k NRPG · $500 RA cold-search · CARSI feed-only). Produces single-variable paid-test designs with locked attribution windows, kill thresholds, sender-platform compliance checks (ATT · GDPR-equivalent · App Store policy), and explicit re-allocation criterion. Closes every test with a falsifiable lift hypothesis tied to the Q2.5.1 dual-flywheel position the spend is meant to feed. Reads ceo-foundation.md + verification-gates.md at every invocation.
Platform Showcase
Synthex platform showcase enforcer. NEVER describe features with generic marketing language ("powerful AI", "seamless integration") or produce wall-of-bullets capability lists. ALWAYS lead with a specific client outcome, use concrete numbers, and write in Australian English. Activate on ANY request to showcase a platform, explain a feature, demonstrate capability, or create platform presentation content.
Project Scanner
Project introspection — detect languages, frameworks, database, structure, scale, auth, CI/CD
React Patterns
Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.
Scout
START HERE — Skill discovery and installation assistant. The recommended first skill when you don't know which skills you need. Searches verified-skill.com, recommends plugin bundles, and installs skills. Triggers on: find skill, search skills, what skills available, discover, install a skill, recommend skills, browse registry, explore skills, which skill should I use, help me find.
Spec Generator
Specification generator - 7 phase document chain producing product brief, PRD, architecture, epics, and issues with Codex review gates. Triggers on generate spec, create specification, spec generator, workflow:spec.
Agent Security Hardener
Sécurisation d'agents IA contre injections, abus et fuites de données. Se déclenche avec "sécurité agent", "agent security", "prompt injection", "jailbreak", "agent abuse
UI UX
Descobre melhorias visuais e de usabilidade com validação via browser. Use quando precisar analisar interfaces, identificar problemas de UX, ou sugerir melhorias visuais
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Agentic Marketing Intelligence skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.