amajorai

Harden a self-hosted Linux server. Detects current state, runs a full interview to understand what the user wants, warns about edge cases (no SSH keys, password-only auth, provider firewalls), then implements only the selected steps in a safe order.

Systematic edge case discovery, test coverage, and hardening for any feature or codebase area. Spawns parallel subagents to enumerate edge cases across eight categories, writes tests for each, runs them, and fixes unhandled cases. Use after implementation to ensure robustness before shipping.

Add a time-boxed free trial to any app with a payment integration. Handles trial start, expiry tracking, gating, expiry emails, and the upgrade prompt flow. Use when adding a trial period to an existing subscription or paywall.

Convert any YouTube video into a reusable Claude Code skill. Paste a YouTube URL and this skill fetches the transcript, extracts the actionable content, and writes a ready-to-use .claude/skills/<name>.md file. Best for tutorial videos, how-to guides, workflow demos, or instructional content.

Make a site agent-ready using Cloudflare AI Search and the isitagentready.com checklist. Audits the current site, then implements: Cloudflare AI Search (hybrid vector + keyword), markdown content negotiation (acceptmarkdown.com), robots.txt AI rules, sitemap, MCP Server Card, and Agent Skills discovery. Use when asked to add search, make a site agent-ready, or optimize for AI agents.

Scaffolds a Better T Stack project via a structured interview. Uses AskUserQuestion to let the user pick frontend, backend, runtime, database, ORM, API layer, auth, payments, addons, example templates, and where to create the project. Assembles and runs the exact create-better-t-stack CLI command with no manual prompts.

Scans conversation history (current session and/or past transcripts) to identify repeated multi-step workflows, then extracts them into new reusable Claude Code skills written to .claude/skills/<name>.md. Turns what you keep doing manually into a one-word command.

End-to-end test authoring and execution for web, mobile, React Native, or Flutter apps. Discovers user flows, sets up the E2E framework if needed, writes tests covering the golden path and critical edge cases, runs them, and fixes failures. Primary tool is agent-browser (web). Falls back to Playwright (desktop/complex web), Maestro (iOS/Android/React Native/Flutter), or Claude for Chrome (web, last resort).

Server setup skill. Detects local vs. remote environment. If local, provisions a VPS on the chosen cloud provider. If already on a server, asks whether this is an orchestrator (manages more servers) or a standalone master (everything on one machine, like Coolify). Installs Bun, GitHub CLI, Dokploy/Coolify, and optional Wrangler, then opens the firewall for the platform UIs. Ends by offering to install the ship and hardening skills.

Provision a new worker server from an orchestrator. Reads /etc/vibemd/server.json for provider, platform, and AI CLI preferences, spins up a new VPS, registers it with Dokploy or Coolify, optionally installs AI coding CLIs, and records the worker in server.json.

Reconfigure an existing vibe server. Change server role (master ↔ orchestrator), swap or add a deployment platform (Dokploy/Coolify), or add/remove edge deployment (Wrangler). Safe to run on a live server — detects current state first and only applies the delta.

Full-cycle development workflow for any non-trivial feature or fix. Runs up to 10 phases (explore+interview loop, plan, implement, verify, edge cases, e2e tests, code review, security review, final verify) using the strongest available model for planning and autonomous goal loops for quality gates. Use when asked to implement a feature, fix a bug, or ship something with full quality assurance.

Quick implementation workflow for simple features and fixes that don't need the full pipeline. Skips security review, edge case hardening, and simplification. Four phases: explore+interview (explore first, one question at a time), plan, implement, verify.

Initialize CLAUDE.md and AGENTS.md for the current workspace. Explores the codebase, interviews for gaps, and writes structured context files so every agent starts fully oriented.

Update CLAUDE.md and AGENTS.md for the current workspace. Detects what has changed since the last update, interviews the user for new context, and surgically refreshes stale sections.

Discover and explore AI developer tools, agent frameworks, MCP servers, and AI news using the Update Night catalog. Use when the user asks about AI tools, wants to find something for a specific task, or wants to browse the latest AI dev tool news.

Discover and explore AI developer tools, agent frameworks, MCP servers, and AI news using the Update Night catalog and CLI. Use when the user asks about AI tools, wants to find something for a specific task, or wants to browse the latest AI dev tool news.

Spec-driven development. Takes any task from a one-liner to a full product brief and breaks it into atomic, agent-ready GitHub issues. The first step before /ship or /party. One interview, one spec, nothing missed.

Cloud app recording skill. Detects your environment, launches your app in an isolated environment, drives it with browser automation or Computer Use, records a video, and uploads to your chosen storage provider (Cloudflare R2, Hetzner, YouTube, or local). Works standalone or with a vibe-provisioned server. Complements vibe (server setup) and ship (dev cycle).

GitHub Projects kanban board agent. On first run, sets up a GitHub Project with Backlog → Ready → In Progress → In Review → Done + Blocked columns and saves your preferences for build skill, merge strategy, and refinement mode. On subsequent runs (via /loop or GitHub Actions), scans for new issues, handles refinement via issue comments, spawns parallel build subagents, tracks PRs, and updates project status automatically. Your kanban board builds itself.

Systematic bug-fixing workflow. Reproduces the bug, instruments the code with targeted logging, reads and interprets logs to pinpoint root cause, makes a surgical fix, verifies the fix, and cleans up instrumentation. Use when asked to fix a bug, investigate unexpected behavior, or diagnose a crash/error.

Master directory of all A Major skills. Use to discover, pick, and install the right skill for any task. Lists flagship skills (ship.md, vibe.md, party.md, replay.md, fix.md) and 30+ utility skills from amajorai/skills.