发现 Skills

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

Use this skill when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use it for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

WRAP decision framework countering the four villains—narrow framing, confirmation bias, short-term emotion, and overconfidence. Use for major decisions or when stuck between options.

Anti-detect browser automation using Camoufox (Firefox-based). Use instead of Chrome/Playwright for bot-detection-heavy sites like X/Twitter, Naver, and other protected sites. Provides stealth browsing with OS/browser fingerprint spoofing, humanized mouse movements, and persistent sessions.

Core craft principles for writing high-quality epic/high fantasy prose. Use this skill whenever the user asks Claude to write, draft, continue, or revise any fantasy fiction — scenes, chapters, passages, dialogue, descriptions, openings, or any creative writing in a fantasy setting. Also trigger when the user asks for help with voice, style, tone, or prose quality in their fantasy work. When in doubt, load this skill — good fantasy prose is hard and this skill exists to make Claude's output genuinely excellent rather than generically competent.

Expert IoT engineer specializing in connected device architectures, edge computing, and IoT platform development. Masters IoT protocols, device management, and data pipelines with focus on building scalable, secure, and reliable IoT solutions.

Caching strategies across the RAG stack. Semantic caching with GPTCache and LangChain, Redis-based embedding-similarity cache, cache key design, TTL/invalidation, partial caching (cache retrieval only), provider-native prompt caching (Anthropic, OpenAI), and hierarchical L1/L2 caches. USE WHEN: user mentions "semantic cache", "GPTCache", "LLM cache", "prompt caching", "Redis vector cache", "cache invalidation for RAG", "reduce LLM cost", "latency reduction LLM" DO NOT USE FOR: retrieval accuracy - use `rag-patterns`; groundedness checks - use `rag-guardrails`; incremental indexing - use `rag-production`

Rust code quality with Clippy, rustfmt, and cargo tools. Covers linting, formatting, and idiomatic Rust patterns. USE WHEN: user works with "Rust", "Cargo", "Actix", "Axum", asks about "Clippy", "rustfmt", "Rust linting", "Rust best practices", "idiomatic Rust" DO NOT USE FOR: SonarQube - use `sonarqube` skill, security - use `rust-security` skill

SeedSigner: DIY Bitcoin signing device. Raspberry Pi Zero + camera + screen. Boots from microSD, no permanent state. Stateless airgap signing. USE WHEN: building / supporting SeedSigner, designing stateless signing flows.

Thymeleaf template engine for Java/Spring. Covers HTML templates, expressions, fragments, i18n, and email templates. USE WHEN: user mentions "thymeleaf", "spring template", "HTML template Spring", "email template Java", "th:text", "th:each", "th:if", "fragments", "layout" DO NOT USE FOR: REST API JSON - use `spring-rest` skill, SPA frontend - use React/Vue/Angular skills, PDF generation - use JasperReports or iText

Unified Azure OpenAI model deployment Skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/Responsible AI (RAI) policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy GPT, create deployment, model deployment, deploy OpenAI model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

Expert embedded Rust development for ESP32 microcontrollers using no-std, the Embassy async framework, and the ESP-RS ecosystem (esp-hal, esp-rtos, esp-radio). Use when building, debugging, flashing, or adding features to ESP32 projects. Covers sensor integration (ADC, GPIO, I2C, SPI), power management (deep sleep, RTC memory), WiFi networking, MQTT clients, display drivers, async task patterns, memory allocation, error handling, and dependency management. Ideal for LilyGO boards, Espressif chips (ESP32, ESP32-S3, ESP32-C3), and any no-std Xtensa/RISC-V embedded development.

Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling `connect()`), configuring connection pools, troubleshooting connection errors (ECONNREFUSED, timeouts, pool exhaustion), optimizing performance issues related to connections. This includes scenarios like building serverless functions with MongoDB, creating API endpoints that use MongoDB, optimizing high-traffic MongoDB applications, creating long-running tasks and concurrency, or debugging connection-related failures.

Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.

Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.

Evidence-grounded target validation scoring with GO/NO-GO decisions for drug discovery campaigns

Use when the user asks to "generate daily paper", "search arXiv for EEG papers", "find EEG decoding papers", "review brain-computer interface papers", or wants to create paper summaries for EEG/brain decoding/speech decoding research. This skill automates searching arXiv for recent papers on EEG decoding, EEG speech decoding, or brain foundation models, reviewing paper quality, and generating structured Chinese/English summaries.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria: methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE/PRISMA), and constructive feedback. Best for actual review writing and manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B–70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. Hugging Face's official library integrated with the Transformers ecosystem.

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.