MajesteitBart

Define and approve a measurable outcome and Spec. Use when a new delivery request has unclear scope, missing outcome, or missing owner.

Execute mapped tasks with stream discipline, dependency safety checks, and evidence updates. Use when tasks are ready for implementation.

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

Decompose an approved plan into atomic tasks with dependencies and acceptance criteria. Use when planning is complete and execution must be prepared.

Verify release readiness and enforce quality gates with risk-based checks and evidence capture. Use before closure or merge.

Open and run repo-native research intake before mutating canonical delivery artifacts. Use when a Delano request has unclear intent, unresolved options, external evidence needs, or material uncertainty that should be investigated before changing spec, plan, workstreams, or tasks.

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Decompose an approved plan into atomic tasks with dependencies and acceptance criteria. Use when planning is complete and execution must be prepared.

Close the delivery loop and capture completion evidence, status updates, and handoff artifacts. Use after quality gates pass.

Define and approve a measurable outcome and Spec. Use when a new delivery request has unclear scope, missing outcome, or missing owner.

Execute mapped tasks with stream discipline, dependency safety checks, and evidence updates. Use when tasks are ready for implementation.

Run a time-boxed Prototype Probe to retire material uncertainty before spec approval. Use when `spec.md` is still draft, `probe_required: true`, or a narrow experiment is needed to bound technical or delivery risk before planning.

Verify release readiness and enforce quality gates with risk-based checks and evidence capture. Use before closure or merge.

Helps query and understand JSONL change logs. Activates for activity queries, audit requests, session reviews, or questions about what changed. Read-only log analysis.

Helps gather and maintain project context. Activates for context questions, session startup help, onboarding, or detecting stale context. Read-only analysis.

Provides guidance on GUI testing setup, configuration, and troubleshooting. Activates when user asks about visual testing, Chrome browser testing, screenshot verification, design validation, or GUI testing configuration.

Analyzes codebase structure, technology stack, and development patterns. Invokes when user asks about project structure, tech stack, onboarding, or needs agent recommendations. Read-only analysis - never modifies files.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Guides users through the spec-driven development workflow (PRD → Epic → Task). Activates when planning features, asking about workflow, or needing help with PRDs/epics/tasks. Advisory only - suggests but never creates.

Repository-specific guidance for understanding, reviewing, debugging, changing, testing, and operating Strap. Use for tasks involving the Next.js application, Personal or Company profiles, editor and proposals, Supabase schema or RLS, OAuth/MCP, scoped keys, Vault, the Strap CLI, OpenRouter, GitHub synchronization, security boundaries, routing, or verification.

Distill reusable decisions and lessons into project memory and improvement actions. Use at milestones, closeout, or recurring failure patterns.

Repair and maintain `.project/context/` so it reflects current project reality. Use when context files are stale, contradictory, still template-like, after major scope or architecture changes, before handoff, or when execution friction suggests context debt.

Run a time-boxed Prototype Probe to retire material uncertainty before spec approval. Use when `spec.md` is still draft, `probe_required` is true, or a narrow experiment is needed to bound technical or delivery risk before planning.

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

Convert meeting discussions into concise, actionable notes with decisions, tasks, follow-ups, and open questions.

Research and prepare for a meeting by turning a meeting title, agenda, attendee list, transcript, prior notes, linked material, OpenClaw memory context, Obsidian notes, or user-provided context into an actionable Preparation.md with objectives, background, questions, agenda, decisions needed, risks, and follow-up prompts. Use when the user asks to prepare for a meeting, research participants or organizations before a meeting, build a briefing, or create/update preparation notes.

Create diarized meeting transcripts from a user-provided local audio recording using configured pyannoteAI diarization and Mistral speech-to-text models, then save an Obsidian-ready Transcript.md. Use when the user asks to transcribe, diarize, process, or generate a transcript for meeting audio and provides or points to the audio file and the desired existing or new Obsidian Meetings folder.

Model Kotlin persistence code correctly for Spring Data JPA and Hibernate. Covers entity design, identity and equality, uniqueness constraints, relationships, fetch plans, and common ORM (Object-Relational Mapping) traps specific to Kotlin. Use when creating or reviewing JPA (Java Persistence API) entities, diagnosing N+1 or LazyInitializationException, placing indexes and uniqueness rules, or preventing Kotlin-specific bugs such as data class entities and broken equals/hashCode.

Migrates Kotlin Multiplatform (KMP) projects to Android Gradle Plugin 9.0+. Handles plugin replacement (com.android.kotlin.multiplatform.library), module splitting, DSL migration, and the new default project structure. Use when upgrading AGP, when build fails due to KMP+AGP incompatibility, or when the user mentions AGP 9.0, android multiplatform plugin, KMP migration, or com.android.kotlin.multiplatform.library.

Open and run repo-native research intake before mutating canonical delivery artifacts. Use when a Delano request has unclear intent, unresolved options, external evidence needs, or material uncertainty that should be investigated before changing spec, plan, workstreams, or tasks.

Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.

Execute mapped tasks with stream discipline, dependency safety checks, and evidence updates. Use when tasks are ready for implementation.

Operate the t3code CLI to resolve folders or Git repositories into T3 Code projects, create missing projects according to policy, start new handover threads with prompts, inspect project state, and diagnose the local T3 connection. Use when an agent needs to hand current work to T3 Code or automate T3 project/thread creation from a terminal or application.

Sets up a Windows environment for Flutter development. Use when configuring a Windows machine to run, build, or deploy Flutter applications for Windows desktop or Android.