发现 Skills

Use when the workflow feels too complex, has accumulated cruft, or has redundant steps and overlapping tools that need consolidation.

Prevents Cross-Site Request Forgery (CSRF) attacks in which malicious sites trick authenticated users into making unwanted requests. Use when handling state-changing operations via forms, POST/PUT/DELETE endpoints, or any request that modifies data on behalf of a logged-in user. Typical triggers: form submission, state change, cookie-based authentication, POST endpoints, delete actions, user actions, web forms, authenticated requests.

Apply released @aituber-onair/chat updates to @aituber-onair/core and core React examples. This includes aligning dependency versions across core packages, adding or updating core re-exports, synchronizing example model lists, refreshing documentation and changelogs, regenerating lockfiles (npm/yarn/pnpm), and running post-change verification (lint, build, tests). Use this after releasing or upgrading the chat package or when maintainers request that chat changes be propagated into core.

Interact with GitHub issues - create, list, and view issues.

DBOS Python SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Python code that defines workflows and steps, interacts with durable queues, or integrates with DBOSC controllers and workers.

Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.

Design and evaluate programmatic SEO strategies for creating SEO-driven pages at scale using templates and structured data. Use when the user mentions programmatic SEO, pages at scale, template pages, directory pages, location pages, comparison pages, integration pages, or keyword-pattern page generation. This skill focuses on feasibility, strategy, and page system design—not execution unless explicitly requested.

Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

Analyzes multiple pages you provide to identify keyword overlap and potential cannibalization issues. Recommends differentiation strategies. Use PROACTIVELY when reviewing similar content.

This skill should be used when the user asks to "plan team structure", "determine hiring needs", "design org chart", "calculate compensation", "plan equity allocation", or requests...

WordPress theme development workflow covering theme architecture, template hierarchy, custom post types, block editor support, and responsive design.

Create a new SigNoz dashboard from a natural-language intent — import a curated template (PostgreSQL, Redis, JVM, k8s, hostmetrics, APM, LLM, etc.) when one fits, or build a custom dashboard from scratch with metric / trace / log panels. Make sure to use this skill whenever the user says "create a dashboard for…", "set up monitoring for…", "build me a dashboard…", "I need observability for…", "import a dashboard template", or asks to track / visualize a service, database, cluster, or AI/LLM platform — even if they don't explicitly say "dashboard". Also use it when someone wants to "monitor", "watch", or "see metrics for" a technology and the natural answer is a dashboard.

Look up information in SigNoz documentation. Make sure to use this skill whenever the user asks "how do I", "where in the docs", "what does the docs say about", "find docs for", or otherwise needs reference material on SigNoz instrumentation, OpenTelemetry setup, self-hosted deployment, API endpoints, auth headers, or troubleshooting steps — even if they don't say the word "docs" explicitly. Docs lookup only — for actions inside SigNoz, the agent will pick the matching `signoz-*` action skill.

Create a typed Route Handler API in app/api.

SDD step 5. Reviews the implemented feature code against language and framework best practices, checks for code duplication, security vulnerabilities, performance issues, test coverage, and alignment with feature.md acceptance criteria. Use after /sdd-implement or on any existing feature implementation.

Use when performing code review, pull request review, security review, architecture review, or change-impact review of NestJS applications; reviewing controllers, services, modules, providers, guards, interceptors, pipes, exception filters, DTOs, validation, configuration, ORM integration (TypeORM, Prisma, Mongoose, Drizzle, MikroORM, or similar), authentication, authorization, testing, or production readiness.

Execute implementation-plan.md with continuous standards discovery from docs/INDEX.md. Adapts execution mode based on plan complexity (1–3 steps = direct edits, 4–8 steps = delegate synthesis to an implementation-changes-planner subagent while the main agent still applies and commits file changes, 9+ steps = orchestrated multi-agent workflows). The main agent applies all file changes; subagents only create change plans. Follows a test-driven approach with incremental verification.

Download Canal+ videos and shows for personal offline viewing. Save your subscribed content in high quality for watching without an internet connection.

Navigate the Israeli education system including Bagrut (matriculation) exams, psychometric entrance test (PET), university admissions, and Ministry of Education school data. Use when user asks about Israeli schools, Bagrut requirements, psychometric exam, "psichometri", Israeli university admissions, sekhem calculation, Israeli education levels, Hebrew education terms, or school data from Ministry of Education. Covers K-12 system, exam structure, and higher education admissions. Do NOT use for non-Israeli education systems or post-graduate academic research.

Coordinate Israeli-built cybersecurity tools for security operations including threat triage, vulnerability management, compliance checking, and incident response. Use when user mentions security operations, "SOC", vulnerability scanning, threat triage, compliance assessment, or asks to coordinate Wiz, Snyk, Check Point, CyberArk, SentinelOne, Armis, Torq, or Pentera tools. Embeds Israeli security best practices including INCD guidelines and Israeli Privacy Protection Law compliance. Do NOT use for offensive security testing or creating exploits.

Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.

Reorganize scattered modules into subpackages while maintaining backwards compatibility via shims. Trigger when: (1) too many root-level files, (2) need to group related functionality, (3) cleaning up codebase structure.

Refactor Next.js code to improve maintainability, readability, and adherence to App Router best practices. Identifies and fixes God Components, prop drilling, inappropriate 'use client' usage, outdated Pages Router patterns, missing Suspense boundaries, incorrect caching strategies, and useEffect data fetching anti-patterns. Applies modern Next.js 15 patterns including Server Components, Client Components, Server Actions, streaming with Suspense, proper caching strategies, Container-Presentational pattern, layout composition, parallel routes, and intercepting routes.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.