Database migrations can break applications when file names, rollback logic, or ORM conventions are wrong. This skill helps Claude, Codex, and Claude Code create convention-aligned migrations with rollback guidance.

Teams lose time when code follows different local habits. This skill reviews files against project conventions and recommends consistent style improvements.

Accessibility defects can block users and delay release reviews. This skill guides Claude, Codex, and Claude Code through WCAG-focused checks and practical fixes.

Generic assistants miss project conventions. This skill helps create specialized Claude Code agents using real architecture, domain, and tech stack details.

Incorrect structured data can prevent rich result eligibility and create search console errors. This skill creates accurate JSON-LD and guides validation for common page types.

Tree-sitter integrations often fail on malformed code, language differences, and inefficient traversal. This skill provides reusable parsing, query, visitor, error-handling, and optimization patterns.

Creating consistent test skeletons across mixed-language repositories takes time. This skill analyzes public symbols and generates framework-specific scaffolds with fixtures, mocks, and TODO markers.

Supabase projects can expose data when RLS, storage, and realtime rules are incomplete. This skill provides reusable security patterns, migrations, client examples, and review checklists.

Project teams may miss relevant AI development skills for their frameworks and workflows. This skill maps detected technologies to recommendations and optional project templates.

Starting separate AI coding sessions across different CLIs requires platform-specific commands. This skill launches supported agents in new terminals and can capture their output.

Interactive tools and long-running commands can block the current coding session. This skill opens them in separate terminals and optionally captures their output.

Database schemas and application models can diverge, causing runtime errors and failed deployments. This skill compares migrations, schemas, and ORM models to produce prioritized alignment reports.

Teams often write inconsistent tests that are hard to maintain. This skill gives Claude, Codex, and Claude Code a shared testing structure for fixtures, mocks, coverage, and CI scope.

Managing several AI coding CLIs requires provider routing, permissions, isolation, and result collection. This guide defines a repeatable Claude Code workflow for coordinated agent execution.

Selecting the right AI provider for each task is difficult and costly. This skill routes work by capability, availability, privacy, and cost.

Complex tasks benefit from independent perspectives, but comparing results manually takes time. This skill coordinates parallel workers and consolidates their outputs with structured rubrics.

Technology stacks become difficult to inventory when projects use multiple manifests. This skill inspects local metadata and returns a consistent stack summary.

New imports can leave dependency manifests incomplete and break builds. This skill detects missing packages, selects the package manager, and updates the relevant manifest.

Browser failures are difficult to diagnose when console, network, and performance evidence is scattered. This skill guides focused Chrome DevTools MCP investigations.

Unstructured LLM outputs create fragile integrations and repeated parsing work. This skill guides BAML schema design, client generation, synchronization, and wrapper implementation.