发现 Skills

1. **Content generation**: Generate a complete Xiaohongshu (Little Red Book) post copy based on user-provided keywords or themes.

Sub-skill of pdf: OpenAI Codex Conversion.

Mobile app debugging for iOS, Android, and cross‑platform frameworks. Use it for crashes, memory leaks, performance issues, network problems, or when encountering Xcode Instruments, Android Profiler, React Native debugger, or native-bridge errors.

Deploy ML models with FastAPI, Docker, Kubernetes. Use for serving predictions, containerization, monitoring, drift detection, or encountering latency issues, health check failures, version conflicts.

Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, Claude) for second opinions. Use for debugging failures, architectural decisions, security validation, or when you need a fresh perspective with synthesis.

Validate test effectiveness with mutation testing using Stryker (TypeScript/JavaScript with Vitest or bun test via @hughescr/stryker-bun-runner) and mutmut (Python). Find weak tests that pass despite code mutations. Use to improve test quality.

Integrates payment processing with Stripe, PayPal, or Square including subscriptions, webhooks, and PCI compliance. Use when implementing checkout flows, recurring billing, or handling refunds and disputes.

Add or modify WooCommerce backend PHP code while following project conventions. Use this when creating new classes, methods, hooks, or when modifying existing backend code in WooCommerce projects.

Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.

Expert in secure mobile coding practices specializing in input validation, WebView security, and mobile-specific security patterns. Use PROACTIVELY for mobile security implementations or mobile security code reviews.

Analyze and optimize individual pages for conversion performance. Use when the user wants to improve conversion rates, diagnose why a page is underperforming, or increase the effectiveness of marketing pages (homepage, landing pages, pricing, feature pages, or blog posts). This skill focuses on diagnosis, prioritization, and testable recommendations — not blind optimization.

This skill should be used when the user asks to "create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or requests 3-5 year financial planning for a startup.

An automatically evolving Code Review (CR) expert. Intelligently detects project types and applies corresponding Skill rules (e.g., vue-best-practices). Maintains consistency of a project's "implicit rules."

Deep Research via Gemini. Use when user says "deep research", "research this topic", or needs comprehensive analysis with sources.

Develops reactive Livewire 4 components. Activates when creating, updating, or modifying Livewire components; working with wire:model, wire:click, wire:loading, or any wire: directives; adding real-time updates, loading states, or reactivity; debugging component behavior; writing Livewire tests; or when the user mentions Livewire, component, counter, or reactive UI.

Tests applications using the Pest 4 PHP framework. Activates when writing tests, creating unit or feature tests, adding assertions, testing Livewire components, browser testing, debugging test failures, working with datasets or mocking; or when the user mentions test, spec, TDD, expects, assertion, coverage, or needs to verify functionality works.

Transform, clean, reshape, and preprocess data using pandas and numpy. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).

Prompt injection testing. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot vulnerabilities.

Builds and deploys ESP32 firmware with PlatformIO for the VanDaemon LED dimmer hardware. Use when: Building, uploading, or debugging ESP32 firmware in hw/LEDDimmer/

Use the Synth AI SDK end-to-end for policy optimization (GEPA), graph optimization, eval, and inference

Load when making decisions that require external knowledge - technology evaluation, standards/compliance checking, market data, or current best practices not in your training data.

BK-CI project design patterns practical guide, covering the factory pattern, strategy pattern, observer pattern, decorator pattern, template method, and their practical applications within the project. Intended for users learning design patterns, refactoring code, designing extensible architectures, or understanding project design.

Find and evaluate Claude skills for specific use cases using semantic search, Anthropic best-practice assessment, and fitness scoring. Use when the user asks to find skills for a particular task (e.g., 'find me a skill for pitch decks'), not for generic 'show all skills' requests.

Create 3D models procedurally with Blender Python. Use when the user wants to generate meshes from code, build geometry with bmesh, apply modifiers, create parametric shapes, procedural landscapes, grids, curves, or any programmatic 3D modeling in Blender.