coding-toolbelt

Memory-aware code review. Combines code-review-graph blast-radius (MCP) with Hindsight long-term memory (local) so review feedback compounds across PRs. Recalls past lessons for the impacted modules before reviewing, then retains new findings tagged by file/module so the next review benefits. Use when reviewing a PR or diff and you want recurring-bug patterns and prior reviewer feedback surfaced as context. Triggers on "review with memory", "memory-aware review", "review and remember", "review with hindsight". Requires Hindsight server on localhost:8888 and code-review-graph installed.

Eval-driven development pipeline for omoios-forge SaaS boilerplate. Reads app plan, generates comprehensive evals (schema, actions, pages, permissions, integration), then builds until all evals pass. No interview loops. Artifacts first. Trigger on "forge", "omoios-forge", "pipeline", "add feature", "build feature", or any project with STEERING_RULES.md or .agents/pipeline-config.json.

Track AI provider pricing, model capabilities, monthly costs, and usage. Includes cost optimization recommendations for oh-my-openagent configuration.

Enforces a 7-stage development workflow: Discover (Socratic questioning) → Explore (codebase scan) → Spec (acceptance criteria) → Eval (write tests FIRST) → Implement → Verify → Iterate. Supports deterministic tests (Playwright, unit), fuzzy evals (screenshot + LLM-as-judge), integration evals, QA dogfood, and regression suites. Strong nudge enforcement — agents are pressured to follow each stage but can override with justification. Trigger on "eval driven," "test first," "write tests first," "TDD," "eval," "acceptance criteria," "spec first," "workflow," "development process," "how should I build this," or any new feature request. Hooks into my-stack for skill routing and dogfood-complete for QA/test generation.

Hook system for OpenCode/oh-my-openagent that detects when an agent is stuck in a linter/build error loop and injects escalating guidance. 4-tier escalation: soft nudge (2 errors) → firm redirect (3 errors) → HARD STOP with model switch (4 errors) → NUCLEAR requiring Oracle consultation (5+ errors). Includes ping-pong detection, cross-session learning, and TRUE edit blocking via PreToolUse hook. Trigger on "linter loop," "stuck on error," "edit blocked," "escalate," "error loop," "hook system," or when agents appear stuck on repeated errors.

Master routing skill for the full SaaS stack: Next.js (next-forge) + Better Auth + Better Auth UI + Drizzle ORM + Stripe + Resend + React Email + Sentry + PostHog + shadcn/ui + Tailwind + Turborepo + Vercel + Playwright. Use for ANY task across the stack — routes to the right skills. Trigger on "my stack," "set up," "new project," "add feature," "scaffold," "deploy," "test," "integrate," "configure," "production," or any mention of the specific technologies. This is the top-level meta skill that coordinates 26 skills across auth, testing, infrastructure, and integrations.

Complete guide for oh-my-openagent (OMO) multi-model orchestration harness. Covers installation, agent selection, category system, cost optimization, and troubleshooting for OpenCode. Use when configuring OMO, setting up agents, optimizing costs, delegating to specialized models, or understanding the OMO agent team (Sisyphus, Hephaestus, Prometheus, Atlas, Oracle, etc.).

Bootstrap a full SaaS stack in minutes. Detects your project (next-forge, Next.js, etc.), installs all required skills from skills.sh, scaffolds config files, and generates browser automation scripts for getting API credentials from Stripe, Google, Resend, Sentry, PostHog. Opinionated defaults with opt-out. Trigger on "bootstrap," "set up my stack," "new project," "saas setup," "install skills," "configure stack," "get started," "scaffold," or "initialize." This skill orchestrates the entire onboarding flow for the full SaaS stack.

The all-in-one Better Auth implementation skill. Use for ANY auth task: scaffolding new auth, adding OAuth providers, setting up email verification, implementing 2FA, building organizations, writing auth tests with Playwright, securing for production, or troubleshooting. Routes to specialized skills and provides implementation guides that combine multiple skills for speed. Trigger on "auth," "better auth," "authentication," "login," "signup," "sign in," "session," "OAuth," "social login," "2FA," "MFA," "organization," "team," "RBAC," "permission," "role," "email verification," "password reset," "OTP," "auth test," "test auth," "auth security," "rate limit," "CSRF," "cookie," "session management," or "auth migration." This meta skill coordinates: better-auth-best-practices, better-auth-security-best-practices, create-auth-skill, email-and-password-best-practices, organization-best-practices, two-factor-authentication-best-practices, better-auth-test-utils, and playwright-best-practices.

Use when writing integration or E2E tests for apps using Better Auth. Covers the testUtils plugin for creating test users, authenticated sessions, cookie injection for Playwright/Puppeteer, OTP capture, database helpers, and test fixtures. Trigger on "test utils," "test helpers," "getCookies," "test factory," "mock auth," "test session," "OTP capture," "authenticated test," "e2e auth setup," "integration test auth," "Playwright cookies," or "test user factory." For auth configuration, see better-auth-best-practices. For security hardening, see better-auth-security-best-practices.

Pre-built shadcn/ui authentication components for Better Auth. Use when implementing auth pages (sign in, sign up, forgot password, magic link), user buttons, account settings, organization management, or API key management with Better Auth. Trigger on "auth UI," "auth components," "sign in page," "sign up page," "user button," "settings page," "auth card," "AuthUIProvider," "better-auth-ui," "shadcn auth," "auth view," "organization switcher," "account settings," or "auth form." Package: @daveyplate/better-auth-ui. For backend auth config, see better-auth-complete. For testing auth UI, see dogfood-complete.

Unified skill for exploring web apps, finding bugs with full evidence, AND generating Playwright tests from the same session. Uses agent-browser for video recording, annotated screenshots, console error capture, and session persistence. Produces both QA reports (with repro videos, severity classification, issue taxonomy) and Playwright test files (with Better Auth integration, POM generation, auth fixtures). Trigger on "dogfood," "QA," "find bugs," "exploratory test," "generate tests," "test my app," "check my app," "smoke test," "regression test," "record test," "annotated screenshot," or "test like a user." Coordinates: agent-browser, playwright-best-practices, better-auth-test-utils, and better-auth-complete.