Найдите подходящую возможность для вашего агента.
This skill should be used when the user asks to "propose architecture", "design implementation approach", "choose between approaches", or in Phase 4 of /dev workflow after exploration is complete. Proposes 2-3 architecture approaches with clear trade-offs, decomposes features into independent tasks, and obtains explicit user approval before implementation begins.
Audits the architecture visualization plan (Common Definitions & Draft Issues) before execution. Strictly enforces SYSTEM_ARCHITECT values and ensures zero regressions by validating against loaded SSOT context via active-reconnaissance and ssot-verification.
Dual-AI code validation using both Claude and Google Gemini to catch 20% more issues. Validates React Native screens for security vulnerabilities, performance anti-patterns, accessibility gaps, and best practices. Use when user says "validate with Gemini", "cross-validate", "AI review", or before deploying code to production.
Container management skill for development and operations containers. Use this when managing system resources, processes, services, environment configuration, Docker containers, logs, or performing system diagnostics and monitoring tasks.
Orchestrates full feature implementation using Standard, TDD, or BDD workflows with automated quality gates.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Manage git worktrees for AI agent workflows. Use when creating, listing, removing, or pruning worktrees, especially for ticket-based development where the agent needs to create isolated working directories for feature branches. Supports creating worktrees in .worktrees/ subdirectory, automatic branch creation from base branch (main), and cleanup of stale worktrees.
Validates BAZINGA completion claims with independent verification. Spawned ONLY when PM sends BAZINGA. Acts as final quality gate - verifies test failures, coverage, evidence, and criteria independently. Returns ACCEPT or REJECT verdict.
Evaluate custom stack combinations against requirements. Use when user proposes their own technology combination or asks to compare a specific stack against alternatives.
Verifies system health across all apps, edge functions, and database connectivity. This skill should be used for quick deployment verification, debugging service issues, daily operations checks, or before/after major deployments.
Review a PR created through the spec/plan/implement flow. Analyzes changes against specification and provides actionable feedback. Only invoke when user explicitly requests to review a PR or review changes.
Expert knowledge of Docker containerization including Dockerfile best practices, docker-compose configuration, Alpine Linux specifics, multi-stage builds, security, health checks, and container optimization. Use when working with Dockerfile, docker-compose.yml, container builds, debugging container issues, or deploying to container platforms.
Systematic documentation audit that validates every documentation claim against code and identifies undocumented features - executable as a repeatable Claude Code skill (project)
Automated code review with security, performance, and best practices analysis. Use when reviewing pull requests or analyzing code for vulnerabilities, performance issues, or maintainability concerns.
Use this skill when users mention "visual regression", "detect UI changes", "screenshot comparison", "visual testing", "pixel diff", "UI regression", or want to set up intelligent visual testing that understands intentional vs accidental changes. Analyzes visual diffs with AI to categorize changes as expected, warnings, or errors based on git history and design tokens.
Systematically debug failed Omnistrate instance deployments using a progressive workflow that identifies root causes efficiently while avoiding token limits. Applies to deployment failures, probe issues, and helm-based resources.
