adr-scaffold
Specializes in generating Action-Domain-Responder (ADR) boilerplate for Gravito projects. Trigger this when adding new features or modules using the ADR pattern.
Найдите подходящую возможность для вашего агента.
Specializes in generating Action-Domain-Responder (ADR) boilerplate for Gravito projects. Trigger this when adding new features or modules using the ADR pattern.
Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Git-backed JSONL files are the source of truth, with SQLite as local cache. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.
Configure CI/CD pipelines, troubleshoot test failures, set up pre-commit hooks, and manage GitHub Actions for trading indicator development. Use when setting up testing infrastructure, diagnosing build failures, configuring branch protection, or running tests locally. Triggers: "CI failing", "set up tests", "pre-commit hooks", "GitHub Actions", "Docker testing".
Enforce ThemeGPT complexity budgets and prevent over-engineering. Activates automatically when writing, reviewing, or refactoring code. Validates against 6 anti-patterns from SynthAI archaeology (Specification Inflation, Enterprise Pattern Obsession, Premature Abstraction, Configuration Explosion, Framework Absorption, Test Suite Inflation). Use when creating features, adding abstractions, writing tests, or configuring projects.
Multi-service orchestration with Docker Compose, focusing on network isolation, environment-specific profiles, and service discovery. Triggers: docker-compose, container-networking, docker-profiles, service-discovery, yaml-config.
Skill for structuring requirements based on Domain-Driven Design (DDD) principles. Used for (1) defining bounded contexts and aggregates, (2) establishing ubiquitous language, and (3) clarifying domain responsibilities for ADRs, System Contexts, or Design Docs.
Generate service objects for complex business logic. Use when controller/model is too fat, multiple models interaction, external API calls, or says "extract logic", "create service", "business logic", "refactor controller", "complex operation".
Cascading error recovery for multi-agent workflows following 2024-2025 patterns. Use when: - Agent task fails and needs retry strategy - Tool call returns error - Build or test failures need diagnosis - Rate limiting encountered - Context window overflow - Subagent produces invalid output - Need graceful degradation strategy Do NOT use for: - User-facing error messages (use standard error handling) - Expected validation failures - Intentional test failures (TDD red phase)
Explain the codebase architecture, project structure, how components work together, API endpoints, data flow. Use when explaining code, understanding structure, or learning about the project.
Apply Clean Architecture layering and dependency rules (Domain, Application, Infrastructure, Presentation layers). Use when structuring applications or ensuring dependencies point inward.
Single-responsibility components with clear boundaries. Orchestration separate from execution. Build maintainable systems through component isolation.
Clean Architecture + Screaming Architecture patterns for React/React Native. Trigger: When structuring features, separating concerns, or defining domain boundaries.
Full-stack debugging specialist for Faiston NEXO. Use when encountering errors, bugs, test failures, or unexpected behavior in Frontend (React, TypeScript, Vite), Backend (FastAPI, Lambda), Agents (Google ADK, AgentCore), AWS (S3, Cognito, CloudFront), or Terraform.
C# best practices with .NET 8, ASP.NET Core, Entity Framework, and modern async programming for 2025
This skill should be used when the user asks to "implement a feature in Elixir", "refactor this module", "should I use a GenServer here?", "how should I structure this?", "use the pipe operator", "add error handling", "make this concurrent", or mentions protocols, behaviours, pattern matching, with statements, comprehensions, structs, or coming from an OOP background. Contains paradigm-shifting insights.
Apply 37signals/DHH Rails conventions when writing Ruby on Rails code. Use when building Rails applications, reviewing Rails code, or making architectural decisions. Covers various aspects of Rails application architecture, design and dependencies.
Perform deep, expert-level codebase and architecture audits to identify technical strengths, weaknesses, risks, and opportunities. Use when a user asks for an assessment of a codebase's structure, quality, or readiness for scale. Deliver detailed, actionable, and prioritized recommendations grounded in engineering best practices.