Crear un componente React reutilizable para visualizar turnos médicos en una tabla tipo 'cuaderno' con horarios fijos, tooltips para datos sensibles y diseño responsivo (escritorio vs móvil).

使用 Pandas 和 SQLAlchemy 将 DataFrame 同步到 MySQL，处理 Merge 后缀，并应用复杂的字段比较逻辑（JSON解析、数值归一化、条件排除、字符串排序）以实现精确的 Upsert。

Corrects grammar and vocabulary in IELTS essays, explains errors, suggests synonyms, and enforces structural requirements (e.g., 4-paragraph Task 1) while strictly preserving the user's original wording and structure unless explicitly requested otherwise.

Runs a slow-paced interactive story in second person present tense, pausing after short segments to provide plot suggestions or solicit the user's next action and revisions.

Implement a PyTorch Transformer model using nn.Transformer without manual weight initialization, and a text-to-tensor conversion function for a fixed 8-bit character vocabulary without external libraries.

Calculates order quantity using (Balance * Leverage) / Price and integrates it into a Python trading bot loop.

Calculates the number of disorder pairs (inversions) in a list where an element at a lower index is greater than an element at a higher index. Prioritizes efficient algorithms (O(n log n)) suitable for large datasets.

Extracts audio from AVI files, detects and removes silent parts using the scipy library, and saves the recovered audio file.

Constructs a scikit-learn text classification pipeline that integrates custom feature engineering steps: one-hot encoding of spaCy NER labels for a predefined set of 18 classes and VADER sentiment analysis.

Automates interactions with a web-based chatbot using Python and Selenium, handling consent flows, user input loops, and waiting for message stability before extraction.

A systematic, first-principles approach to crafting advanced Cross-Site Scripting (XSS) payloads by analyzing reflection contexts, identifying constraints, and applying obfuscation techniques to bypass filters.

Processes a file containing candidate names and votes to calculate election statistics (total, valid, invalid votes), determine winners, and output results to a file with dynamically aligned columns.

Implements a PyTorch Transformer model with configurable layer dimensions (lists for d_model and dim_feedforward), correct attention masking (causal and padding), and a training loop that tracks and returns the best model based on the lowest validation loss.

Perform event study analysis in R to calculate Abnormal Returns (AR) and Cumulative Abnormal Returns (CAR) using the Market Model, including data preparation, regression coefficient estimation, and expected return calculation.

Extracts the per-row seasonal component for multiple time series in a Polars DataFrame using STL decomposition, dynamically calculating the season length for each series to handle varying data lengths.

Acts as an elite writing critique partner and coauthor to brainstorm, refine, and consolidate complex magic systems and plot concepts for fantasy novels, ensuring logical consistency and narrative depth.

Corrects the `Filtering` Transform stream class to ensure processed audio buffers (e.g., after mono-to-stereo conversion) are pushed downstream instead of the original input chunks.

Calculates the required diameter of PE4710 pontoon pipes for floating docks and performs comprehensive structural verification (ULS/SLS), including buoyancy, detailed lateral load checks (wind/berthing) with mooring pile mechanics, wave-induced flexure, and vibration.

Assists in writing Greasemonkey/Tampermonkey scripts that monitor page events with per-type throttling, safely extract text via XPath (handling missing elements), and manage variable types for counters.

Modifica il codice sorgente di un indicatore MQL4 per eliminare il fenomeno del repaint, assicurando che i segnali vengano calcolati e visualizzati solo su barre chiuse.

A Python function to load and preprocess paired screenshot and HTML files from separate directories, matching them by base filename (e.g., screen_13.png with html_13.html), resizing images, and normalizing pixel values for model training.

Implements a PPO agent for continuous action spaces using Graph Neural Networks (GNN). The Actor features a multi-task head predicting both actions and node stability, while the Critic operates on flattened node features. Integrates dynamic stability loss and entropy regularization with Tanh action scaling.

Writes paragraphs following the 'It's good - but there is a problem - and this is how you solve it' structure, ensuring no conclusion is provided and transitioning smoothly to the next topic.

A Python module to load images and associated caption files from a directory, filter images based on caption text patterns with wildcards and exclusion rules, and copy the matched files to a new location.

Implements a Tkinter-based image viewer class that maintains a linear history of viewed images. Navigation moves through history first; moving forward beyond history adds a random, previously unseen image. Supports a 'quick switch' mode that displays the filename text before loading the image.

Develop a real-time chat application using WebSockets (Node.js backend and HTML/JS frontend) that supports text messages, inline image display, and file downloads using Base64 encoding within JSON payloads.

Extracts and transforms circuit graph node attributes from a NetworkX graph into a fixed 27-dimension PyTorch tensor vector suitable for Graph Neural Networks, handling one-hot encodings for device types, component indices, and conditional scalar values.

Manages the full lifecycle of Firestore expense data, including date-based initialization, additive array updates across time granularities, and time-series visualization using Jetpack Compose and Vico.

Performs comprehensive structural analysis and sizing for floating dock pontoons (PE4710), including buoyancy calculations, detailed ULS lateral load checks (wind, berthing) with explicit stress and deflection formulas for cantilever piles, wave action analysis, and serviceability limit state (SLS) verification.

Implement a PyTorch-based MoE-Mamba model featuring an input-dependent selection mechanism and Mixture of Experts (MoE) layer for text generation tasks, including data loading, training, and evaluation workflows.

Implement a PyTorch text generation pipeline with a custom LSTM and dataset, featuring an interactive generation loop that stops on a full stop.

Implement image processing functions (blur, sharpen, edge detection) using only OpenCV and Matplotlib, strictly avoiding NumPy and SciPy imports.

Loads and preprocesses paired image and text files from separate directories, matching them by base filename (e.g., screen_13.png with html_13.html) for machine learning training.

Implements a Python-based query executor that converts informal keywords to SQL commands, parses queries preserving string literals, and executes operations on pandas DataFrames.

Implements a PyTorch Transformer model with configurable layer dimensions and attention masking, and a training loop that retains the best performing model based on validation loss.

根据预定义的规则和枚举值，将用户输入的自然语言指令解析为包含动作、事项、范围和参数的JSON格式。

Automates browser interactions via CLI using agent-browser by Vercel Labs. Covers navigation, clicking, form filling, snapshots, refs-based selectors, agent mode with JSON output, session management, and CDP integration. Use when the user needs to automate web browsing, scrape pages, fill forms, or integrate browser automation into AI agent workflows.

Build cross-platform desktop applications with Electron, covering main/renderer process architecture, IPC communication, BrowserWindow management, menus, tray icons, packaging, and security best practices. Use when the user asks about Electron, needs to create desktop applications, implement Electron features, or build cross-platform desktop apps.

OCRmyPDF Python API and plugin skill — use OCRmyPDF programmatically from Python, integrate with applications, and extend with plugins (EasyOCR, PaddleOCR, AppleOCR). Use when the user needs to call OCRmyPDF from Python code, build OCR pipelines, or use alternative OCR engines.

Factory skill for creating new pencil-ui-design-system-* skills. Use when you need to add support for a new design system layui antd bootstrap element uview uviewpro vant ucharts echarts etc. to the Pencil ecosystem.

Initialize Ant Design (antd) design tokens and component overview frames in a Pencil .pen file. Use when the user mentions Pencil with Ant Design or antd, needs to set up antd color palette and typography variables, or wants to create component library frames for Button, Form, Table, Modal, and other antd components.

Provides comprehensive guidance for Spring Cloud microservices including service discovery, configuration management, load balancing, circuit breakers, API gateways, and distributed tracing. Use when the user asks about Spring Cloud, needs to build microservices, implement service discovery, or work with Spring Cloud components.

three.js node-based shading: Nodes API surface, NodeMaterial and MeshStandardNodeMaterial-style families, TSL (Three.js Shading Language) entry at TSL.html, WebGPURenderer pairing, and core PostProcessing (class) versus addon EffectComposer at a high level. Use when authoring shaders as graphs, using TSL builtins, compute-oriented nodes, or modern WebGPU pipelines; for classic ShaderMaterial GLSL use threejs-materials; for stock EffectComposer passes use threejs-postprocessing; for WebGLRenderer-only tuning use threejs-renderers.

Browser automation CLI for AI agents. Uses Chrome/Chromium via CDP directly.

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through diagnosing the failure via OPENCLI_DIAGNOSTIC, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

Make websites accessible for AI agents. Navigate, click, type, extract, wait — using Chrome with existing login sessions. No LLM API key needed.

Transform academic papers into university press releases for general.

Extracts clinical trial baseline data (study, region, participants, etc.) from article text or PMID. Checks PubMed for metadata; always falls back to LLM extraction for full details.

NGS analysis toolkit. Used for BAM to bigWig conversion, quality control (correlation, PCA, fingerprint plots), heatmaps/feature plots (TSS, peaks), suitable for ChIP-seq, RNA-seq, ATAC-seq visualization.

DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, process FASTQ/BAM/VCF, for developing and executing genomics pipelines.