Scripting

Add tensor shape validation and documentation to PyTorch code. This skill should be used when working with PyTorch models to ensure tensor shapes are correct and well-documented with inline comments.

Transcribes audio and video files to text using OpenAI's Whisper CLI with contextual grounding. Converts audio/video to text, transcribes recordings, and creates transcripts from media files. Use when asked to "whisper transcribe", "transcribe audio", "convert recording to text", or "speech to text". Uses markdown files in the same directory as context to improve transcription accuracy for technical terms, proper nouns, and domain-specific vocabulary.

Migration-first database development workflow using Drizzle ORM for TypeScript/J...

Comprehensive F* proof-oriented programming for formal verification including dependent types, refinement types, effect system, SMT solver integration, tactic-based interactive theorem proving, and verified code extraction to OCaml, F#, C, WebAssembly, and Assembly

Build and run AI agents using Claude Code CLI. Use when developing autonomous agents, multi-agent systems, CI/CD automation, or scripting Claude for programmatic tasks. Covers authentication, headless mode (-p), JSON output parsing, tool restrictions, subagents, and orchestration patterns.

Define custom Claude Code slash commands for agents in the Traycer enforcement framework. This skill should be used when creating or updating agents and needing to specify reusable prompts that agents can execute as slash commands. Commands are Markdown files stored in .claude/commands/ and referenced in agent config.yaml files. This is for Claude Code slash commands (/command-name), not bash/CLI commands.

Build complete agent prompts deterministically via Python script. Use BEFORE spawning any BAZINGA agent (Developer, QA, Tech Lead, PM, etc.).

Generate persistent test cases from project analysis, or add individual test cases interactively. Supports full project analysis or adding single test cases via prompt description with browser exploration.

This skill should be used when the user asks to "find code", "search codebase", "locate functions", "understand architecture", "find implementations", or needs intelligent code discovery using MorphLLM's AI-powered search tools.

TypeScript strictest patterns, type guards, optional properties (exactOptionalPropertyTypes), Drizzle query safety, null checks. Use when fixing type errors, implementing complex types, or when user mentions TypeScript/types/generics.

Implementation agent focused on high-integrity TDD-driven code generation.

Migrate a browser-based JavaScript/Canvas game to Unity (C#). Use for Shelter 2250 (or similar) when you need: (1) Unity project setup decisions (2D/URP/input/UI), (2) mapping existing JS classes/systems to Unity architecture, (3) porting core simulation loops (time/resources/rooms/dwellers/save), and (4) planning incremental milestones with parity checks.

Convert Python loops to vectorized PyTorch tensor operations for performance. This skill should be used when optimizing computational bottlenecks in PyTorch code during Phase 4 performance optimization.

Comprehensive BDD testing with Cucumber and Gherkin syntax. Use when writing feature files (.feature), step definitions, hooks, or implementing Behaviour-Driven Development. Covers Gherkin keywords (Feature, Scenario, Given/When/Then, Background, Scenario Outline, Rule), step definition patterns for Ruby/JavaScript/Java/Python, hooks (Before/After/BeforeAll/AfterAll), tags, data tables, doc strings, and best practices. Triggers on cucumber, gherkin, BDD, feature files, step definitions, acceptance testing, executable specifications.

Enforces local testing before any deployment. MUST be used before running vercel, git push, or any deployment command. Prevents deploying untested code.

Guide and run a SharePoint audit locally. Collect inputs, confirm PowerShell 7.4+ and Python 3.10+ are available, call PowerShell with certificate auth via wrapper, parse audit.json, and render Markdown/HTML. Use only local shell commands.

Use when writing Hotwire (Turbo/Stimulus) code in Rails - enforces dom_id helpers, morph updates, focused Stimulus controllers, and JavaScript private methods

Browser automation with Playwright for Python. Recommended for visual testing. (project)

Security best practices for Python development. Activated when working with security concerns, input validation, injection prevention, or threat modeling.

Analyzes Claude Code chat history to identify optimization opportunities, track Skills/Commands utilization, detect repetitive patterns, measure token usage, and recommend improvements. This skill should be used when reviewing productivity, identifying underutilized resources, or finding patterns that could become new Skills.