Playwright E2E test debugging and interactive browser exploration. Runs tests with action capture (DOM snapshots, network, console, screenshots), diagnoses failures, and provides browser tools for navigating, clicking, and inspecting pages through ARIA snapshots.
Opinionated GitHub-native development workflow with 51 skills for autonomous, issue-driven software development. Enforces TDD, strict typing, IPv6-first networking, comprehensive code review, local service testing, and continuous issue tracking. Features GitHub-based state management (no local state files)…
Project health and permission management, dev sessions, team updates with feedback triage, GitHub releases, multi-model brains trust, git workflows, UX audits, responsive layout testing, and browser automation.
Maps user journeys, visualizes UI test coverage with Mermaid flowcharts, and generates framework-correct E2E tests to fill gaps. Supports Playwright, Cypress, Maestro, Detox, XCUITest, Espresso, and Flutter.
Turn AI software engineering into an auditable, on-disk state machine. A staged PDLC workflow (PRD, design, TDD, implement, review, ship, retro) enforces hard contracts — artifacts on disk, per-feature state machine, tests-before-code, objective checks from real command exit codes, single-shot auto-repair — so AI work.
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
38 engineering discipline skills for Claude Code & OpenAI Codex — research, quality gates, testing patterns, deployment, learning, gap analysis, spec sync, and more. Extracted from real-world development.
AI agent testing toolkit to generate, review, and debug Playwright and Cypress E2E tests. Four agent skills: generate tests from scratch with live exploration only on local/disposable or externally isolated approved non-production targets and explicit user approval; review existing specs or PR/diff-scoped test changes.
A dynamic build workflow for Claude Code: hand it a goal and it plans the work into tasks, builds each one test-first, reviews every step, and (with --thorough) loops a critic that adds tasks until nothing's left to fix, then hands back a branch ready for your review. Built on and complements superpowers by Jesse…
Self-improving Compose Multiplatform UI harness for Claude Code. A render -> grade -> ratchet loop: inspection tests render every screen across a stress matrix, a deterministic Tier-1 asserter plus a vision evaluator grade them in a separate lane, and recurring findings ratchet into permanent gates via a compounding…