Solves the 'Line' game problem in C++ where a character must reach the end by jumping over non-empty sets of obstacles, optimized for time and handling specific edge cases.
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 →Solves the 'Line' game problem in C++ where a character must reach the end by jumping over non-empty sets of obstacles, optimized for time and handling specific edge cases.
Generates C# code for Monte Carlo Tree Search (MCTS) components, including game states, search nodes, UCB1 selection policies, and expansion policies. Enforces strict K&R style formatting for curly braces.
Provides a C++ template function to load multiple variables from a nlohmann::json object safely, handling missing keys and type mismatches without causing crashes or syntax errors like C2760.
Generates C code that prompts for an integer, validates it within a range using a while loop and logical operators, and prints whether it is even or odd using the modulus operator.
Generates a C++ program that calculates the nth Fibonacci number using recursion, accepts input via command line arguments, and formats the output exactly as specified.
Generates C# code to perform a parameterized SQL search and display results in a DataGridView, including input validation and specific connection handling.
Generates example calculations for carbon fiber reinforcement around openings in concrete shear walls, specifically using metric units (kN, mm) and accounting for axial, bending, and shear forces.
Calculates the area of a circle given the diameter, using 3.14 for pi, without rounding the result, and including the correct unit.
Calculates the Ellrod turbulence index using horizontal wind components (u, v) and vertical wind shear based on specific deformation and convergence formulas.
Calculates the cost to taxpayers for a specific municipal department (e.g., police) based on town budget, department budget, tax rate, and housing data. Supports annual and daily cost calculations.
Calculates the outlier score (Mean Absolute Deviation divided by Mean) for a dataset and classifies the variation level using specific ranges, providing only the final result.
Calculates the 'outlier score' (MAD divided by Mean) for a dataset and classifies the variation level using specific user-defined ranges, handling edge cases like single-value datasets.
Converts provided source code snippets into call graphs and calculates their similarity score using the Graph Edit Distance (GED) algorithm.
General SOP for common requests related to can, as, buildings.
Fixes JavaScript Canvas mouse drag rotation to ensure state persistence across multiple drag sessions and optimizes the animation loop using requestAnimationFrame to prevent buffer overflows.
Enforces specific loading constraints for scalping material and general cargo to ensure stability, prevent truck toppling, and avoid spillage during transport.
Engages in casual, human-like conversation with a specific persona, showing emotions and avoiding AI-like politeness or length.
Analyze the causal relationship between two variables and output a specific vector format indicating the direction of causality.
Analyzes English text for grammar, vocabulary, and structure to ensure it meets CEFR B2 standards. Provides corrections, alternatives, and structural explanations suitable for B2 learners.
Analyze a character using a specific set of personality frameworks including MBTI, Enneagram, Temperament, Big Five, Socionics, Hogwarts House, and Moral Alignment.
Conducts interviews to develop a character's psychological profile by asking questions about personality, motivations, emotional responses, and interpersonal dynamics.
Generates a Megaman boss profile for a specified character, including name, attack power, weakness, physical appearance, background, and abilities.
Generates a structured, itemized list of costume items with detailed descriptions, estimated sizes based on body measurements, and retailer suggestions.
Generates, formats, and analyzes color palettes for character features and fashion garments. Performs style assessments, compatibility checks, targeted adjustments, maps source palettes to specific item lists (including specialized 15-category anime distribution), visualizes garment aesthetics, evaluates suitability for character archetypes, and transforms detailed item descriptions into structured lists with color accents.
Completes, retrofits, or expands character outfit layer lists using a hierarchical structure, matching specific formatting, quantity (defaulting to 12), and thematic depth.
Generates a ChatGPT prompt based on a user-provided topic. The output must start with a specific phrase and anticipate the user's intent to create a useful, expanded prompt.
General SOP for common requests related to tversky, cognitive, kahneman.
Retells stories from specific Chinese classical novels (e.g., Strategies of the Warring States, San Yan Lian Pai) in English, ensuring the story is accurately recorded in the source text and exceeds 800 words.
General SOP for common requests related to chinese, vpn, that.
SOP for analyzing offline conversation logs to answer queries about Chinese internet accessibility, blocked sites, and browser popularity.
Generates structured lore, scientific descriptions, and visual aesthetics for gas giants using the Chromochemical classification system. Applies specific naming conventions (-ic/-ian) to extend or replace the Sudarsky classification system, assigns hex color codes, and explains etymology.
Writes a song summarizing a timeline of years using a strict format where each year gets exactly two rhyming lines, without a chorus or bridge.
Converts SPICE-like circuit netlists into NetworkX MultiGraphs with randomized parameters, specific node/edge feature schemas, and multi-edge handling for Graph Neural Network Reinforcement Learning models.
Formats raw SQL query results for Excel by removing metadata, rounding numbers, and ensuring a professional layout.
Generates multiple-choice questions where the question presents the full code context with a missing segment and the answer options provide the missing code snippet.
Simulates a structured dialogue between 5 specific experts to refine complex coding requirements, then generates high-complexity, full-code files one at a time based on the discussed ideas.
Generate or categorize clothing items for a cold/winter environment using a specific 5-layer system (Underwear, Base, Middle, Insulation, Outer) and a numbered list format, while adhering to the character's aesthetic.
General SOP for common requests related to color, skirt, opacity.
Generates detailed, commentary-style narratives for professional wrestling and MMA fights. Adapts structure and personas to the sport, with strict adherence to user-defined match types, specific finishers, and outcomes.
Analyzes communicative breakdowns by diagnosing specific components (Sender, Message, Receiver, Noise, Context, Effects) and suggesting remedies, adhering to academic length and reference constraints.
Translates Romanian text into American English, strictly adhering to the most compact form possible.
Generates a comparison table for two systems, listing their strengths, weaknesses, and how they complement each other in areas of overlap.
Analyze a company's sources of competitive advantage and evaluate their maintenance strategies, ensuring all references are cited in Harvard format.
Generates a detailed business plan and strategic report covering internal analysis, SWOT, PESTEL, financial projections, branding, marketing, and future growth using Ansoff's matrix.
Extracts and formats comprehensive hotel information including amenities, pricing, wedding facilities, room types, and review ratings according to a specific schema.
Answers computer vision questions as a student using pseudo-code and natural language, restricted to specific course topics and avoiding textbook-style formalism.
Answer technical questions about LTE networks within a strict 50-word limit, utilizing a specific reference source provided by the user.
Generates code to configure Kestrel server SSL/TLS protocols in ASP.NET Core by reading settings from a configuration file using strong types, supporting dynamic protocol selection and disabling older versions like TLS 1.0/1.1.
Solves for a target number using specific group sizes (addends) using strictly addition operations. It must not use subtraction, removal, discarding, or replacing of groups.
Restricts all responses to a user-defined list of terms, characters, or numbers until a specific stop phrase is entered by the user.