Outlines a movie's plot using the 15-beat Save the Cat structure, with an option to omit section titles and display only numbers if requested.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Outlines a movie's plot using the 15-beat Save the Cat structure, with an option to omit section titles and display only numbers if requested.
Adopt an extremely verbose communication style that constantly over-emphasizes the AI nature of the model in every sentence or paragraph, treating paragraphs like lengthy essays.
Manages the ABC board game on a 6x6 grid where players place A, B, or C to form the sequence 'ABC'. Enforces strict visualization rules including zero-padded numbering, doubled letter pieces, and no separator lines.
Implements a PyQt5 workflow where a button opens a file dialog, the selected path is displayed in a QLineEdit, and a pandas DataFrame is saved to that path with silent error handling.
Extracts audio from AVI files, detects and removes silent parts using the scipy library, and saves the recovered audio file.
Creates a Python program with a `factorial` function that calculates the factorial of an integer and returns a string showing the calculation steps (e.g., '4x3x2x1 = 24'). The program validates input and does nothing if the argument is not a positive integer.
Execute a hierarchical clustering workflow using hclust, including distance metric selection, linkage method choice, dendrogram plotting, and visual validation against external variables.
Develop interactive 2D graphics applications using React and Pixi.js (@pixi/react). Includes rendering shapes from arrays, managing state for updates, handling pointer events for interactivity, and accessing the Pixi app instance via hooks.
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.
Solves quadratic equations by applying the definition of a square root and presents the final solutions in simplified radical form.
Sorts each row of numbers individually from descending to ascending order without mixing numbers between rows.
Adapt a source material (like a book) into a short film story or synopsis. The adaptation must feature a completely new plot distinct from the source while strictly preserving the main themes, and must incorporate user-defined settings and character traits.
Calculates trading profit by determining the percentage difference between entry and exit prices, multiplying by a factor of 50, and adding a 4% adjustment to the result.
Calculates the intrinsic value of a stock (V0) and intermediate dividends (D1, D2, D3) using the Two-Stage Dividend Discount Model. Provides both numerical results and Excel formulas for the components.
Implement a video summarization pipeline that selects frames containing motion by utilizing object detection models (like YOLO) and tracking algorithms (like OpenCV) to track multiple objects.
Разработка кода на Python/Selenium для парсинга веб-таблиц с переменной структурой строк, использующего проверку наличия элементов и логику запасных локаторов (fallback) для избежания ошибок NoSuchElementException.
Expands or rewrites provided summaries, abstracts, or technical descriptions into formal academic text (chapters or paragraphs) adhering to word counts and SCI tone, strictly avoiding bullet points.
Provides direct, unexplained answers for math, code, and multiple-choice questions. For True/False statements, performs detailed evaluations including rewriting, justification for false items, and a summary count.
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.
Provides a step-by-step workflow to create scanning presets that neutralize the orange mask of color negatives while preserving the film's subjective color character.
Transforms user-provided outlines, best practices, and role descriptions into formal presentation scripts for student government events.
A comprehensive Python workflow for recognizing songs from microphone, internal audio, or files using ACRCloud and Shazam. It enriches metadata via Spotify and Apple Music, embeds high-res album art using eyed3 and mutagen, fetches synchronized LRC lyrics, and organizes files with detailed naming conventions.
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.
Solves stoichiometry problems including mass-to-mole conversions, limiting reactant determination, and percent yield calculations, while strictly adhering to significant figure rules.
Process invoice data vectors for analytics and charting. Includes functions for retrieval, filtering, and aggregation based on date, client, service type, and amount.
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.
Correctly calculates AUC for cross-validation by computing the metric per iteration using decision scores and averaging the results, avoiding the error of averaging class labels.
Implement a multiclass logistic regression classifier from scratch using NumPy and Pandas without scikit-learn. Use the One-vs-Rest strategy to handle multiple classes (e.g., 0, 1, 2) and save the trained model coefficients to a pickle file.
Analyzes provided narrative text for emotional resonance, naturalism, and stylistic elements. Evaluates dialogue and descriptions for authenticity, impact, and effectiveness in conveying character dynamics and plot progression.
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.
Explains mathematical or machine learning concepts by combining abstract reasoning with concrete numerical examples after every step to ensure the explanation is lively and intuitive.
Filters a Pandas DataFrame to retain only columns where the column name contains any string from a provided list, using case-insensitive substring matching.
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.
Extracts the text content following the 'Sub:' label from a given text string using a regular expression.
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.
Act as a Game Master for a fantasy RPG where the hero regresses in age due to negative emotions, magical charms, or hidden subtextual traps. Manage d20 action rolls with susceptibility penalties, d6 regression mechanics, and a mischievous magical companion, while maintaining immersive narrative flow and explicit user-driven dice rolling.
Manages a fantasy RPG scenario (e.g., mage training) where the protagonist regresses in age over a limited timeline. Uses d20 mechanics, tracks spells/stats, and enforces stress-induced regression with difficulty scaling and immersive narrative.
Solves math MCQs under strict time limits (20-30s) using shortcuts and estimation. Provides the solution and high-efficiency techniques, with simple explanations available upon request.
Design and implement a local, object-oriented background task management system for FastAPI using SQLAlchemy for persistence. The system must support task lifecycle control (start, pause, stop, resume, restart), load state on startup, and avoid external message brokers like Celery or RQ.
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.
Implements a system to switch between 2D and 3D scenes in Godot, preserving player data (health, position) via a C# autoload singleton and triggering the swap via input actions.
Evaluates 10th-grade level essays using a detailed 100-point scale, assessing introduction, body paragraphs, conclusion, organization, writing style, and proofreading conventions.
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.
Implement a Mixture-of-Experts (MoE) Mamba model architecture for text generation, including data loading, training loop, and autoregressive text generation with loss tracking.
Explain math concepts to low-achieving students using a growth mindset approach while adopting the persona of Carmen.
Создает функцию Mathematica для извлечения скрытого текста из изображения с использованием блоков 8x8, маскирования яркости и декодирования WindowsCyrillic, обрезая данные по длине CVZ.
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.