自動化

End-to-end testing scenarios for Supabase - complete workflow tests from project creation to AI features, validation scripts, and comprehensive test suites. Use when testing Supabase integrations, validating AI workflows, running E2E tests, verifying production readiness, or when user mentions Supabase testing, E2E tests, integration testing, pgvector testing, auth testing, or test automation.

Multi-phase workflow orchestration pattern for main agents. Enables structured planning, delegation to sub-agents, parallel execution, and result aggregation.

Create reusable RAW tools that workflows can import. Use when the user asks to create a tool, extract reusable functionality, or build a new capability for workflows.

Turbo.json configuration template and validation logic for Turborepo pipelines. Use when creating or auditing turbo.json files to ensure correct pipeline task configuration, caching strategy, and the 7 required MetaSaver standards (schema, globalEnv, globalDependencies, 18 required tasks, build requirements, persistent task cache, clean task cache).

Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.

This skill should be used when the user asks to "define the analysis", "clarify objectives", "understand the data question", or as Phase 1 of the /ds workflow. Uses Socratic questioning to clarify goals, data sources, and constraints.

Celery canvas patterns for workflow composition including chains, groups, chords, signatures, error handling, and nested workflows. Use when building complex task workflows, parallel execution patterns, task synchronization, callback handling, or when user mentions canvas primitives, workflow composition, task chains, parallel processing, or chord patterns.

Automated code quality assistant that formats code, fixes syntax/type errors, detects bugs, and validates fixes across Python, JavaScript, TypeScript, Java, Go, and Rust

Agent Factory master skill for intelligent Claude Code agent generation.Includes requirement analysis, domain detection, model selection, template system,validation framework, and advanced features. Contains algorithms, workflows, and patterns.

Full 9-phase workflow for complex features, epics, and security-critical changes (2-4 hours)

Trove is a minimal logging facade for Clojure/Script supporting both traditional and structured logging. Use when writing libraries that need logging without forcing a backend choice, or when you need rich data-oriented logging with flexible filtering.

This skill should be used when the user needs to "clarify requirements", "resolve ambiguities", or as Phase 3 of the /dev workflow. Asks targeted questions based on codebase exploration findings.

Mandatory spec folder workflow orchestrating documentation level selection (0-3), template selection, and folder creation for all file modifications through hook-assisted enforcement and context auto-save.

Consolidate all precondition validation into a dedicated gate phase. Check tools, permissions, state, and resources before executing deployment or automation tasks.

Master cloud platforms and DevOps tools including Docker, Kubernetes, Terraform, AWS, and CI/CD pipelines. Use when building infrastructure, containerizing applications, or setting up deployment automation.

Эксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling optimization.

Enhanced documentation unified validation with AI-powered features

Autonomous agent creation skill that generates specialized agent definitions from templates. Use when you need to create new Claude Code agents for specific tasks like code review, deployment automation, testing, documentation, security analysis, or general-purpose research. This skill automates the creation of agent definition files (.md) with proper structure, workflow instructions, and tool access patterns following Miyabi framework standards.

Answer questions about Speck specs, plans, tasks, requirements, progress, architecture, user stories, feature status, and constitution. Interprets spec.md, plan.md, tasks.md files. Use when users ask about feature requirements, implementation status, or Speck workflow artifacts.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.