Position in workflow: v0.7 Epic Scoping → **v0.7 Test Planning** → v0.7 Implementation Loop

Run Playwright smoke tests for Denser blog application. Executes 15 tests (SMOKE-01 to SMOKE-15) against configurable environment (production, dev, or localhost) with retry support (max 3 attempts per failing test). Supports headed (visible browser) and headless modes. Collects artifacts (screenshots, trace.zip) on failures and generates HTML report. Use when testing blog functionality, verifying deployments, checking UI/API consistency, or when user requests smoke tests, playwright tests, or blog testing.

End-to-end smoke test of all MemCan MCP endpoints. Creates, searches, updates, deletes memories and checks logs. Use when verifying MemCan installation or after upgrades.

>

Build the project (all modules or specific service) and run test suites. Reports build status, test results, and coverage.

Reviews GitHub pull requests for the Medusa repository. Checks PR template compliance, contribution guidelines, code conventions, and community contribution limits. Posts a review comment and applies initial-approval or requires-more label. Use when a PR is opened or updated.

Analyze a GitHub pull request including diff, comments, related issues, and local code context

Diagnose and resolve managed clusters stuck in "Pending Import" state after switchover.

GraphQL is a query language and runtime for APIs that enables clients to request exactly the data they need. It provides a strongly-typed schema, single endpoint architecture, and eliminates over-fetc

>

Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples

Comprehensive pull request review using specialized agents

Angular 21.x SPA development skill with TailwindCSS 4.x and daisyUI 5.5.5. Use when building Angular standalone components, services, lazy-loaded routes, unit tests, or creating UI with TailwindCSS + daisyUI. Covers component scaffolding, UI/UX design, accessibility audits, and design systems.

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

How to run scenario tests against Gorlami fork RPCs (dry runs) before broadcasting live transactions. Covers config, seeding balances, runner flags, and safe script patterns.

Use when writing code that redirects users to a URL from request parameters,

Use after code changes, before releases, or when testing features - runs the right level of QA based on what changed

Universal validation and knowledge capture. Detects what changed, runs governance gates, captures knowledge, verifies deployment. Works for any project.

Use for QUICK PR reviews with structured checklists (architecture, patterns, security, performance). Provides step-by-step review process, git diff commands, and review report templates. Best for pull request reviews and pre-commit checks. NOT for deep refactoring analysis (use code-review instead).

REST and GraphQL API testing with Playwright. Use when testing APIs, mocking endpoints, validating responses, or integrating API tests with E2E flows.

Plan a project and generate PRD for execution. Creates prd.json + README.md with full HQ context awareness. Runtime-agnostic — executes identically in Claude Code and Codex. Adapts interview depth to brainstorm context if available.

'Use when schemas have changed and example JSON files need regeneration and validation'

'PR creation workflow, title format, description template, and quality gates'

Create isolated git worktree for parallel development in monorepos.

Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.

Run the full orchestrator → developer → qa pipeline for a game implementation task. Use when the user asks to implement, add, or change something in the PICO-8 codebase.

Autonomous end-to-end execution skill. Use when the user gives a broad directive (improve, audit, fix, ship, polish) that should run from audit through deploy without check-ins. This skill codifies the loop-until-live pattern and the stop conditions.

Pre-commit checklist + context update — runs deterministic checks, updates PILOT.md and SESSION-CONTEXT.md. Does NOT commit.

Use when adding authentication to Android applications (Kotlin/Java) with Web Auth, biometric-protected credentials, and MFA - integrates com.auth0.android:auth0 SDK for native Android apps

'[Skill Management] Fix the agent skill based on `logs.txt` file. Triggers on: fix skill logs, skill error, skill broken, skill not working.'

Sepolia Testnet Deployment — verifier deployment, batch submission, on-chain verification

Python development principles and decision-making. Framework selection,

React 19 and Next.js 16 performance optimization for the Arcanea platform. Use when writing, reviewing, or refactoring React components, data fetching logic, bundle optimization, or any frontend performance work. Triggers on: React components, Next.js pages, hooks, data fetching, bundle size, re-renders, Server Components, Client Components, hydration. Sourced from Vercel Engineering's official React best practices (57 rules, 8 categories) and adapted for the Arcanea stack.

Use when scanning code, skills, dependencies, or configurations for security vulnerabilities, threat modeling, secrets exposure, insecure defaults, auth issues, and hardening opportunities.

Audit SoulMap AI evals so datasets, assertions, source markers, and golden responses stay source-backed, failure-oriented, and hard to game.

Release management with versioning, stability assessment, changelog generation, and release gates. TRIGGER on: release, version, changelog, tag, cut release, release status, what version, stability, release gate.

Roll back a bad release to the previous known-good version (Marcus workflow)

After each edit of typescript files, run this to catch type errors immediately.

Derives the project's dependency list from **actual imports in source files** — one

Refactoring assessment and patterns. Use after mutation testing validates test strength (MUTATE phase) to assess improvement opportunities.

Run MovieFinder project QA pipeline - detekt, unit tests, jacoco coverage report

Refactoring

Use when creating HTML email templates with React components - welcome emails, password resets, notifications, order confirmations, newsletters, or transactional emails.

Use when the Integrator is performing git operations — committing, branching, merging feature branches, resolving conflicts, managing branch lifecycle, or maintaining commit history. Activates for any git-related work.

Design and document database schemas for BenchSight tables, relationships, and data models. Use when adding new tables or modifying existing schema.

* BDD Style: `describe/it` syntax for tests

Create an isolated worktree in `.worktrees/` branched from up-to-date main, with spec directory scaffolded.

Implements a game from its architecture document using strict TDD. Use after architect-game produces an architecture doc.

Best practices and patterns for generating clean, secure, maintainable code

description: Automated pipeline from SPEC.md to ready-to-execute tasks — runs autonomously by default with parallel task execution