Loading...
Loading...
Found 82 Skills
Automatically loads domain README.md context when you start working in a registered library or module. Reads architecture, public API, and patterns before touching domain-specific code. Activate when the task involves a specific library, domain path, or module the user references.
Use when starting a new project, adding a major feature to an existing system, or when unsure which skills to run and in what order. Supports macOS, iOS, web, full-stack, voice agent, and edge/IoT+ML projects.
Conversational SDD (Specification-Driven Development) guidance skill based on OpenSpec. It is automatically triggered when a user describes development requirements, and guides the user through the entire SDD process via conversations without any manual command input.
Archive completed plans from plans/active/ to plans/completed/, supplement verification results and completion time. Suitable for calling after implementation is finished.
Create or update the project constitution through interactive phase-based
Bounded codebase exploration and architecture mapping. Use when discovery is needed before implementation. Do NOT use for broad refactoring — use do-plan instead.
Bence's code style, tech stack, and workflow conventions
Integration patterns for Mapbox MCP DevKit Server in AI coding assistants. Covers setup, style management, token management, validation workflows, and documentation access through MCP. Use when building Mapbox applications with AI coding assistance.
Create structured GitHub issues from conversation context using gh CLI
Agent development workflow and discipline skills. Use when developing features, debugging issues, managing code branches, writing plans, or ensuring code quality through TDD and systematic processes. Triggers on any software development task that benefits from structured workflows.
Execute a GRACE development plan in controller-managed parallel waves with selectable safety profiles, batched graph sync, and scoped reviews.
Use when you have a spec or requirements for a multi-step task, before writing implementation code. Helps break down complex features into bite-sized, verifiable tasks.