Agent skills for Claude Code

Focused one-shot technical SEO audit for a domain: crawlability, indexability, security, mobile, structured data and JS rendering.

Comprehensive SEO analysis for any website or business type.

Run local SEO from your terminal via the SEOG MCP server — Google Business Profile management, map-pack rank tracking and geo-grid scans…

Analyze stocks using Mark Minervini's SEPA (Specific Entry Point Analysis) methodology.

Review one seller's pipeline; not one deal or a team.

Review design, implementation, and task documents produced by design.

Diagnose and optimize Lambda/serverless cold start performance.

Audit server-side paid-media measurement including server-side tag management, platform conversion APIs, event taxonomy, browser/server…

Implements server-state management and API caching in React applications using React Query to eliminate redundant data fetches.

Build a service catalog — schema, starter entries, and governance model.

Smart external service connection orchestrator.

Build or update services in `app/features/services` using the `_template/service` conventions (container/store/structure/lib/constants) so…

Scans the current Go project and identifies the Service → Module → Resource hierarchy for tenant-manager registration.

This skill should be used when the user asks about resource usage, CPU, memory, network, disk, or service performance.

Sesame HR via Apideck's Proxy API + managed Vault auth — Apideck handles auth and proxies HTTP calls to Sesame HR's native API.

Run a focused N-question study session on a subject — MBE, essay, or flashcards.

This skill should be used when the user asks to "analyze session", "세션 분석", "evaluate skill execution", "스킬 실행 검증", "check session logs"…

This skill should be used to save URLs or links found this session as Raindrop bookmarks — triggers: 'bookmark URLs from this session'…

Use when an agent session ran outside the repo whose commits should record it — e.g. launched from a higher-level folder, a non-Entire…

View active session status with progress and context information

Use when working on complex multi-step tasks, when a session is getting long (40+ tool calls), when the agent starts ignoring rules it…