Terminal-first browser control with playwright-cli — navigate, fill forms, screenshot, mock networks, trace, and generate Playwright tests.
Production-tested Playwright guidance for writing, debugging and scaling E2E, API, component, visual and accessibility test suites.
A production-tested Playwright playbook for writing and debugging reliable E2E, API, component, visual, and accessibility tests.
Turns an app full of hardcoded strings into a fully localized i18next app, with optional Locize sync and AI translation.
29 production scripts that let Claude Code build, drive and audit iOS apps on the Simulator without pixel coordinates.
Scans any repository and produces an annotated ASCII directory tree plus a module table and suggested entry points.
Generates and verifies API tests strictly from real OpenAPI specs, route code and existing tests, keeping test generation separate from executing live requests.
A CLI-backed skill that replaces bloated MCP tool schemas with a tiny name index (~99% fewer tokens) and manages one skill catalog across every agent.
Diagnose a running web app that misbehaves while the console is empty and the code looks fine, ending at the exact file:line to open.
A TDD skill that forces you to declare the expected consequence before writing code, verified against the real running app instead of mocks.
Builds a behavior-first Markdown guide to any repository and keeps it in sync as the code changes.
Builds and maintains a Markdown guide that explains a repository through one real, evidence-backed behavior instead of a file-tree tour.
Installs and refines a repo quality framework where every agent rule names a gate that fails a commit, push, or CI run.
A persona skill that forces the laziest solution that actually works — stdlib and native features first, shortest diff, no unrequested abstractions.
Drives the Compass CLI's local code knowledge graph so Claude answers architecture, dependency, and change-impact questions with cited evidence.
Compresses an approved game design and art direction into a minimal BUILD_BRIEF and produces a runnable game candidate on the target runtime.
Runs a full codebase hygiene scan for dead code, tech debt, outdated dependencies and code smells, then writes a prioritized report.
Generates a pre-change blast-radius report showing what breaks if you rename, refactor, or delete a symbol or file.
Read and write GitHub repositories through the REST API and raw URLs when git clone is blocked in sandboxed containers.
A diagnose-first Terraform/OpenTofu companion that classifies the failure mode, applies version-aware guards, and always ships validation and rollback steps.