Essential command-line tools and system utilities.
Creates high-quality Claude skills following official best practices. Use when the user asks to create a new skill, improve an existing skill, or needs guidance on skill authoring. Includes proper structure, naming conventions, progressive disclosure patterns, and quality validation.
Guided workflow for building custom AI agents using the OpenHands Software Agent SDK. Use when you want to create a new agent through an interactive interview process that gathers requirements and generates implementation plans.
USE WHEN: writing system prompts, structuring complex instructions, engineering context for Claude agents, optimizing attention efficiency in long prompts. DO NOT USE WHEN: writing regular code, simple messages, or content where Markdown suffices. For optimal context architecture, trigger deep thinking with "think harder" or "ultrathink" to analyze attention economics thoroughly.
Expertise in validating that the codebase matches a specific plan. Use when the user asks to "validate the plan", "check implementation", or "audit the code".
Manages Kirby multi-language workflows, translations, and localized labels. Use when dealing with languages, translation keys, placeholders, or importing/exporting translations.
Comprehensive guide to Fastlane automation for iOS and Android app deployment. Use when helping with mobile app releases, code signing, screenshots, TestFlight, App Store Connect, Google Play Store, beta distribution, CI/CD pipelines, or any Fastlane actions/lanes. Covers gym, match, pilot, deliver, supply, snapshot, screengrab, and 100+ other actions.
Secures Kirby sites with access restriction, user roles, permissions, and protected downloads. Use when implementing login/role-based access, permissions, or file protection.
Plans and applies safe Kirby content migrations using runtime content tools, update schemas, and explicit confirmation. Use when users need to rename/move/transform fields, clean up content, or bulk-update pages/files across languages.
Expertise in interactively explaining the codebase. Use when the user asks to "explain the project", "explore the code", or "how does this work".
Expert guidance for Nuxt 4 projects with app/ directory structure, Vue 3 Composition API, TypeScript, Vitest, ESLint, and Tailwind CSS 4 with Vite plugin. Use when creating components, composables, tests, or any frontend code. Enforces Tailwind-only styling (no inline styles or custom CSS). Supports Nuxt layers.
Configure domains, routing, CORS, VPC, static IPs, and inter-service communication for DigitalOcean App Platform. Use when setting up custom domains, subdomain routing, cross-origin API access, or secure database connectivity.
Git commit guidelines for incremental commits. Read this when user asks you to auto commit as you go
Structured code review covering style, readability, and security concerns with actionable feedback. Use when reviewing pull requests or merge requests to identify issues and suggest improvements.
USE WHEN: needing real code examples from GitHub, finding API usage patterns, looking up framework setup, verifying library implementations, eliminating hallucinations with working code. DO NOT USE WHEN: working on proprietary code, questions about the current codebase, or when local context is sufficient. Requires Exa API key configured in environment.
Improves IDE autocomplete and static analysis in Kirby projects with PHPDoc hints and Kirby IDE helper generation. Use when types are missing or IDE support is degraded.
When python, flask, or jinja are being written or edited.
Generate formatted changelogs from git history since the last release tag. Use when preparing release notes that categorize changes into breaking changes, features, fixes, and other sections.
Upgrades Kirby and maintains dependencies safely using composer audit, plugin compatibility checks, and official docs. Use when updating Kirby versions or making maintenance changes that affect runtime.
All modes that write scripts or code follow these app standards for communication, modularization, simplification, naming conventions
Verify the current task and output a completion marker. Use this to check if a task is complete and signal the stop hook to allow session exit.
