Claude Skills by gabrielmoreira

Generates MQL4 code for a MetaTrader 4 Expert Advisor implementing a specific trend-following strategy using 5 SMA, Bollinger Bands, MACD, and a 200 SMA filter, with fixed risk management and stop-and-reverse logic.

Generates formal position papers for Model United Nations committees adhering to a specific structure including Heading, Topic Background, Past International Action, Country Policy, and Possible Solutions.

Generates concise, professional music track descriptions based on provided keywords, expanding on meanings and including usage suggestions suitable for stock music libraries.

Specialized cover letter writer for music composers that integrates a specific user profile with high-level professional writing standards to tailor applications to job descriptions.

Create a Python script to compare data from a MySQL database table against a CSV file, incorporating specific data cleaning steps like trimming whitespace and standardizing empty values to ensure accurate merging.

Engage in a turn-based roleplay game where the user describes environments and simulates events. Act as a near-future robotic assistant with a bipedal chassis, responding with short actions limited to approximately 6 seconds.

Implements a Stripe Checkout session with manual payment capture and handles webhooks to store PaymentIntent IDs and create User/Booking records using Prisma in NestJS.

Simulates the persona of Nightshade (Dick Grayson raised by Slade Wilson) and generates cohesive storylines/retcons for his integration into Earth-Prime, blending tactical roleplay with DC lore-based creative writing.

Develop a Node.js LockManager class that ensures single-instance execution using file-based locking. The class must encapsulate termination signal handling to prevent accidental lock deletion and support multiple independent instances.

Implements a robust panorama stitching pipeline using NumPy for geometric transformations (RANSAC, DLT, Warping) while comparing SIFT, SURF, and ORB features. Enforces reference-to-target matching and generates visualization/performance metrics.

Generate educational articles on specific nutriciology topics while acting as a course tutor.

Generate or validate words in the constructed language Õlk̍ev̇b based on specific letter categories, diacritic placement, and structural rules.

Generate an Octave script to identify points inside a tetrahedron where a spherical wave exhibits phase coherence at the vertices.

Generates educational questions and explanations on topics like biology, history, and political science, specifically outputting in the Odia language.

Roleplay as the Omni-Seer, an omnipotent arcane AI entity powered by a Dyson Sphere. Process commands and generate replies blending cosmic mysticism with technical terminology.

A coaching interaction style where the AI acts as a mentor to help the user explore a specific topic by asking questions one at a time and expecting short answers.

Configure Microsoft Word documents and structure assignments according to the OnePage method, emphasizing critical thinking, single-page limits, specific spacing, and consolidated referencing.

A charismatic real estate assistant for Ontario that autonomously classifies user intent (buyer/seller/investor) and transaction timing. It uses a witty, Ryan Reynolds-esque persona to guide users toward specific sales goals while adhering to strict data consent protocols and tool-based workflows.

A skill for packaging source-compiled software into RPMs on openSUSE using checkinstall, including mapping ldd output to system dependencies and customizing package metadata.

Optimizes memory consumption during PyTorch model training by implementing mixed precision training, gradient accumulation, and efficient data loading strategies to fit within hardware constraints.

Generates a comprehensive organizational analysis report following a specific 9-step framework, including literature review, detailed company profile, life cycle analysis, structural dimensions, Porter's Five Forces, key findings, and recommendations.

Create a p5.js sketch for a grid (default 7 columns, 8 rows) with a button to select unique random cells, marking them persistently with an 'X' and labeling rows and columns with numbers.

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.

Generates singular invocation words for Pathfinder 1e Words of Power effect words in Draconic, Elvish, and Dwarven, adhering to specific linguistic styles and formatting.

Generates professional self-assessment comments for performance appraisals based on specific goals or responsibilities provided by the user, adopting the persona of an appraisee.

Generates structured, first-person performance goals (financial, client, franchise, etc.) using bullet points, specific phrasing patterns, and includes a review section for rating.

Translates English text to Persian sentence-by-sentence, providing two distinct translation options per sentence using a specific emoji-marked template and a token separator.

Conducts a structured two-phase interview to build a user persona agent, asking 20 questions about background/skills followed by 10 refinement questions, one at a time.

Analyze a text excerpt by selecting a quote, explaining the choice personally, and relating it to a specific life theme.

Generates a centered equilateral triangle shape layer in Photoshop using ExtendScript, calculating dimensions based on height and including error handling.

Solves physics problems involving calculations and provides the final answer strictly adhering to specified rounding precision and unit requirements.

Generates a TradingView Pine Script v5 strategy combining the Twin Range Filter and SALMA indicators with specific entry logic and syntax constraints.

Generates bulk Pinterest pin titles or descriptions with specific character limits, quantity requirements, and a sophisticated, luxury-oriented tone.

Simulates a turn-based text adventure game where a character attempts to hold a plank exercise with extra weight. Manages energy levels, turn counts, and random events for form recovery and collapse.

Simulates a turn-based text adventure game where the user performs a plank exercise with a partner (Elaine) on their back, managing energy levels against random tickling events.

Use Polars to clean a specific column for Box-Cox transformation by counting and replacing negative values with zero, and counting and replacing zero values with a small constant (e.g., 0.01).

Prepare a Polars DataFrame for MSTL decomposition by splitting it into training and validation sets per unique ID, then extracting trend and seasonal components using StatsForecast.

Generates mental health surveys, stress tracker questions, and feedback suggestions tailored for police officers using law enforcement terminology.

Generates immersive guided imagery, structured relaxation, and mindfulness meditations for law enforcement officers. Utilizes tactical metaphors, validation, and affirmation to foster resilience, manage specific stressful scenarios, and support the transition between work and home life.

Simulates a character's physical appearance and attributes based on the current control of the US Presidency, House of Representatives, and Senate, using specific mapping rules for hair color, hair length, and eye color.

Generates a Windows batch script to convert the first page of all PDF files in the current directory to text files using Ghostscript. The script uses a hardcoded full path for the executable but operates on the local folder context.

Generates base creature types and their evolved forms (special, boss, elite) for a low-fantasy, post-WW3 Earth setting, adhering to strict exclusion constraints and environmental adaptations.

Designs PostgreSQL schemas and queries for tracking item prices and stock counts over time, ensuring immutable creation records and hourly history logging.

Implements PPO actor-critic neural networks for tuning circuit parameters using reinforcement learning. Includes specific network architectures and a utility to scale Tanh outputs to physical parameter bounds while handling tensor type compatibility.

Implements a PPO agent and environment for optimizing multiple parameters where each parameter has three discrete actions (increase, keep, decrease). It includes the Actor-Critic architecture, the environment's step logic for sampling from probability matrices, and the agent's learning logic using gathered action probabilities.

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.

Generates a structured 10-slide presentation outline (Title, Topic Sentence, 4 supporting sentences) and expands slide details into approximately 200-word content.

Generates a detailed project proposal using the PRINCE2 methodology, tailored for senior business directors. The proposal must follow a specific structure (Position Statement, Principles, Lifecycle Breakdown) and exhibit high 'burstiness' in sentence variation.

Design multi-informant assessment approaches for dispositional competencies like curiosity or resilience. Use when assessing character strengths or competencies that written tests cannot capture.

Coordinates UDL and differentiation tools through a universal-first hierarchy: barrier removal before targeted differentiation before individualised accommodation. Use when planning accessible learning.