Loading...
Loading...
Found 1,981 Skills
Challenges AI-generated plans, code, designs, and decisions before you commit. Pairs with any other skill as a review layer. Uses pre-mortem analysis, inversion thinking, and Socratic questioning to find what AI missed — blind spots, hidden assumptions, failure modes, and optimistic shortcuts. The skill that asks "are you sure about that?" so you don't have to. Triggers on: "challenge this", "devils advocate", "stress test this plan", "what could go wrong", "poke holes in this", "review this critically", "second opinion on this design", "what am I missing". Use this skill when you need critical review of any AI-generated output, architecture decision, implementation plan, or code before committing to it.
Generate hand-drawn style `.excalidraw` diagrams that can be opened directly in Excalidraw based on text descriptions or structural information; supports system architecture diagrams, flowcharts, data structure diagrams and free whiteboard sketches, and outputs standard Excalidraw JSON.
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.
Stress-test a plan, design, or architecture through relentless interviewing. Use when user says "grill me", "challenge this", "stress test my design", "review my plan", wants a design interview, or needs to think through decisions before building. Two modes — collaborative interview (default) and devil's advocate.
Deploy applications to AWS. Triggers on phrases like: deploy to AWS, host on AWS, run this on AWS, AWS architecture, estimate AWS cost, generate infrastructure. Analyzes any codebase and deploys to optimal AWS services.
MemPalace — Local AI memory with 96.6% recall. Semantic search, temporal knowledge graph, palace architecture (wings/rooms/drawers). Free, no cloud, no API keys.
Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory, or memory benchmarks (LoCoMo, LongMemEval). A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of durable agent knowledge and cross-session persistence.
The foundational context engineering skill — start here when exploring the discipline. This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Also activates when the user mentions "context engineering" or "context-engineering" for foundational understanding of AI agent context systems.
[Pragmatic DDD Architecture] Guide for creating Next.js Server Actions exactly tied to zod, neverthrow, and the domain architecture. Use when creating or editing any file in presentation/actions/. Covers "use server" placement, unknown parameters validated with `zod`, discriminated union response types, auth-first pattern, Value Object validation with TypeScript narrowing, use-case error mapping via `assertNever`, serviceContainer invocation, and revalidation strategy.
[Pragmatic DDD Architecture] Interactive guide for scaffolding and bootstrapping a new project or module from scratch. Use this skill when the user asks to start a new project or add a massive new feature. It instructs the agent to run an assessment wizard, define the PRD, evaluate serverless tech, and set up the foundation.
[Pragmatic DDD Architecture] Guide for internationalization. Use when adding or editing translations in any component, page, or layout — also when wrapping a subtree in LocaleProvider, reading the active locale in a new component, building or modifying a locale switcher, or touching any file that calls determineLocale() or useLocale(). Covers the custom library-free implementation, Translations co-location, Server vs Client locale access patterns, and setLocaleAction.
Decomposes a spec or architecture into buildable tasks with acceptance criteria, dependencies, and implementation order for AI agents or engineers. Produces `.agents/tasks.md`. Not for clarifying unclear requirements (use discover) or designing architecture (use system-architecture). For code quality checks after building, see review-chain. For packaging and PRs, see ship.