Software Development

Build tools (Gradle KTS), Static Analysis (Detekt), and Testing standards. Use when configuring Gradle KTS build scripts, Detekt rules, or Kotlin build tooling.

Security standards for hardening Laravel applications. Use when securing authentication, authorization, input validation, or CSRF in Laravel.

Standards for Unit Tests, UI Tests (Compose), and Hilt Integration. Use when writing unit tests, Compose UI tests, or Hilt test modules in Android.

Code review, security audits, bug detection, alternative implementations, second opinions via OpenAI Codex. Use when user asks for code review, security analysis, implementation advice, bug detection, code patterns, or wants a second opinion on code. Supports uncommitted changes review. Do not use for architecture design or web searches.

SOLID principles for object-oriented design. Use when reviewing code quality, refactoring, designing classes or interfaces, or discussing architecture patterns.

A code analyzer skill that helps with code quality and best practices

Uses a tool from inventory on a target object or location to perform a specific environmental interaction, such as digging or cutting. Activate this skill when a task requires modifying the environment or manipulating materials, like using a shovel to dig soil. It takes the tool and target as inputs and outputs the result of the interaction, enabling physical task progression.

Use when implementing offline-first patterns with MMKV storage and React Query persistence in React Native.

Use before claiming work is complete - runs tests, checks git status, verifies changelog

Analyze codebase with parallel mapper agents

Go error handling patterns. Routes to specific patterns.

Stagehand automation patterns and best practices. Scripted browser flows, data seeding, and test orchestration. Trigger: When automating browser flows or test setup with Stagehand.

Switch the current session to work in an existing git worktree

This skill should be used when users need the MaxwellLink single-mode cavity solver for fast prototyping and regression, in either socket or embedded mode.

Bifunctors: two-argument functors for product categories.

Fast code hygiene validation (lints, formatters, tests, coverage) for quick development loop feedback.

Auto-grown skill at knight tour position 2

Auto-grown skill at knight tour position 3

Execute a frozen workflow contract and collect evidence by implementing only approved scope/files and checks. Use when PLAN_FROZEN=true and Execution Contract is complete, then hand off to review.

Tool: Cursor IDE automation and scripting

Virtual reality (VR) reality tech. Locomotion, comfort defaults, controllers/hands, performance budgets, and interaction patterns.

Run the quality loop (lint + test + build) to verify code quality and correctness. Use after making any code changes, before committing, or when asked to check/verify the project works.

Submit a pull request following DataProvider project standards

Review code changes for quality, security, and best practices

Development tooling: Deno runtime, JSR package registry, deno.json and package.json configuration, and editor settings. Use when setting up projects, choosing packages, or configuring build tools.

Expert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects. Covers Node.js and Python SDKs. Use when: hubspot, hubspot api, hubspot crm, hubspot integration, contacts api.

Trail of Bits security skills analysis for Solidity contracts. Use for deep smart contract security review with invariant suggestions.

Open and control Three.js views/examples in Annolid Bot sessions.

Run failing tests and update expected variables to match actual output from pytest

Produce concise, citation-backed explanations of module behavior, data flow, and important types/APIs.

Review the current changes and provide feedback.

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Interact with GitHub repositories, issues, and pull requests.

Use when changing frontend dashboard config, topology, or playground surfaces that reflect router behavior.

Design story architecture. Use when starting a new project or rethinking structure.

Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files.

Clear or swap equipped item. Returns success/failure

Use when changing local image build, serve or bootstrap logic, or canonical smoke behavior.

Use this skill when working with Spartacus Server-Side Rendering (SSR). Trigger when the user mentions SSR engine development, SSR E2E tests, server-side rendering issues, hydration problems, or needs to run SSR-related commands like 'npm run test:ssr' or 'npm run build:ssr'. Also trigger when working with files in 'core-libs/setup/ssr' or 'projects/ssr-tests/'.

Prefer vscode-uri over node:path. Use when .ts files in /src import from node:path or use path.join, path.basename, path.dirname, path.resolve.

处理代码审查反馈并修复审查中发现的问题。当用户要求修复审查问题、处理 review 反馈时触发。参数为 task-id。

Answer questions about the Velox codebase or pull requests. Use when asked a question via "/query" or when the user wants to understand code, architecture, or implementation details.

Command Pattern pattern for C development

How to read Hyperlend markets/time-series and execute lend/withdraw flows in Wayfinder Paths (inputs/outputs, unit handling, and safety).

How to use the Moonwell adapter for lending/borrowing on Base (market discovery, APYs, collateral management, and common gotchas).

A comprehensive code review skill that analyzes code for best practices, potential bugs, security issues, and suggests improvements.

Generate Homebrew formula for CLI distribution on macOS and Linux.

Enforces strict Spec-Driven Development. Prevents direct coding and ensures spec → generate → review loops.

Guidelines and checklists for creating a PR for Luxor.

Core Web Vitals optimization, Lighthouse audits, and performance monitoring.