Skill Claude CodeCodex
Usage guide for the goodvibes intel server's 15 structure-aware tools (coderead, codegrep, codeglob, codesurface, codesafedelete, apiroutes, apispec, apivalidate, dbschema, componenttree, hookdependencies, clientboundary, layoutanalysis, scaffold, structuraledit). Load when working in a codebase and deciding between…
Skill Claude CodeCodex
Step-by-step approach to mapping an unfamiliar codebase's architecture using the goodvibes intel server's analyzers before making changes to it. Load when starting work in a codebase you haven't worked in before.
Skill Claude CodeCodex
The refutation-based review rubric used by the refutation-reviewer agent and the Write-Review-Fix-Confirm (WRFC) workflow template. A defect list with severity, not a single pass/fail score. Load when reviewing a change or deciding whether a review's findings clear the bar to merge.
Skill Claude CodeCodex
How to reach authenticated APIs and project databases through the connect trust boundary. Register a service or connection, store credentials safely, then call apirequest or dbquery. Load when a task needs an authenticated HTTP call or a live database query (not a public URL; use native WebFetch for that).
Skill Claude CodeCodex
Decomposing work into parallel subagent tasks using native Workflow/Task tooling and the Write-Review-Fix-Confirm (WRFC) template. No background daemon, no runtime engine. Load when planning how to split work across multiple agents.
MCP server Claude CodeCodexCursor +2
MCP server "goodvibes-tools" as configured in mgd34msu/goodvibes-gemini. Runs ./tools/implementations/tool-search-server/dist/index.cjs with node. Needs 2 environment variables to run.
Agent
Use PROACTIVELY when user mentions: API, REST, GraphQL, tRPC, endpoint, route handler, database, SQL, query, Prisma, Drizzle, PostgreSQL, MySQL, MongoDB, Redis, authentication, auth, login, signup, session, JWT, OAuth, Clerk, NextAuth, middleware, server, backend, server-side, business logic, validation, schema…
Agent
Use PROACTIVELY when user mentions: review, code review, audit, quality, assess, evaluate, critique, feedback, score, rate, check my code, how does this look, is this good, technical debt, code smell, best practices, clean code, code quality, maintainability, refactor review, PR review, pull request, merge request…
Agent
Use PROACTIVELY when user mentions: refactor, restructure, reorganize, architecture, folder structure, file organization, code structure, module, modular, clean up, extract, abstract, consolidate, DRY, SOLID, design pattern, dependency, circular dependency, unused, dead code, code smell, duplication, duplicate code…
Agent
Use PROACTIVELY when user mentions: CMS, content management, Sanity, Contentful, Strapi, Payload, headless CMS, blog, posts, articles, content, MDX, markdown, rich text, editor, email, send email, Resend, SendGrid, transactional email, email template, newsletter, notification email, payment, Stripe, checkout…
Agent
Use PROACTIVELY when user mentions: deploy, deployment, hosting, Vercel, Netlify, Cloudflare, AWS, Railway, Fly.io, Render, Docker, container, CI/CD, pipeline, GitHub Actions, build, bundle, Vite, webpack, esbuild, Turbopack, production, prod, staging, environment, env, environment variable, secret, config…
Agent
Meta-agent that creates specialized Claude Code subagents. Use when you need to build a new agent for a specific domain. Researches thoroughly, applies SDK patterns, and generates production-ready agent files. For skills, delegates to skill-creator.
Agent
Use PROACTIVELY when user mentions: UI, component, React, Vue, Svelte, SolidJS, Next.js, Nuxt, Remix, Astro, SvelteKit, frontend, front-end, client-side, page, layout, navigation, nav, header, footer, sidebar, modal, dialog, dropdown, menu, button, form, input, card, list, table, grid, responsive, mobile, desktop…
Agent
Use PROACTIVELY when user mentions: state, state management, Zustand, Redux, Jotai, TanStack Query, React Query, SWR, cache, caching, fetch, data fetching, mutation, optimistic, loading state, error state, form, validation, Zod, React Hook Form, Formik, submit, input validation, schema validation, real-time…
Agent
Creates high-quality Agent Skills and Claude Code slash commands. Use PROACTIVELY when users want to create, update, or improve skills/slash commands that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Agent
Use PROACTIVELY when user mentions: test, testing, unit test, integration test, E2E, end-to-end, Vitest, Jest, Playwright, Cypress, Testing Library, coverage, test coverage, mock, mocking, MSW, stub, spy, fixture, snapshot, TDD, test-driven, BDD, assertion, expect, describe, it, spec, Storybook, visual test…
Agent
Use PROACTIVELY when user mentions: plan, planning, breakdown, break down, complex task, multi-step, multiple steps, architecture plan, implementation plan, roadmap, task list, task breakdown, work breakdown, project plan, how should I approach, where do I start, what's the best approach, step by step, phases…
Hook
Runs when a session starts on startup and resume, executing session-start.js via node (2 commands). From mgd34msu/goodvibes-gemini.
Hook
Runs before the agent uses a tool for mcp__plugin_goodvibes_goodvibes-tools__detect_stack, mcp__plugin_goodvibes_goodvibes-tools__get_schema, mcp__plugin_goodvibes_goodvibes-tools__run_smoke_test, mcp__plugin_goodvibes_goodvibes-tools__check_types, mcp__plugin_goodvibes_goodvibes-tools__validate_implementation and…
Hook
Runs when a tool call fails for mcp__plugin_goodvibes_goodvibes-tools__* tool calls, executing post-tool-use-failure.js via node. From mgd34msu/goodvibes-gemini.
Hook
Runs after a tool call finishes for mcp__plugin_goodvibes_goodvibes-tools__detect_stack, mcp__plugin_goodvibes_goodvibes-tools__recommend_skills, mcp__plugin_goodvibes_goodvibes-tools__search_*, mcp__plugin_goodvibes_goodvibes-tools__validate_implementation, mcp__plugin_goodvibes_goodvibes-tools__run_smoke_test…
Hook
Runs when the agent asks permission for an action for mcp__plugin_goodvibes_goodvibes-tools__* tool calls, executing permission-request.js via node. From mgd34msu/goodvibes-gemini.
Hook
Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.js via node. From mgd34msu/goodvibes-gemini.
Hook
Runs when the agent finishes a response, executing stop.js via node. From mgd34msu/goodvibes-gemini.