kivo360

19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.

Guide Alfred sub-agents to actively invoke AskUserQuestion for ambiguous decisions.

Master-Clone pattern implementation guide for complex multi-step tasks with full project context

Systematic code review guidance and automation. Apply TRUST 5 principles, check code quality, validate SOLID principles, identify security issues, and ensure maintainability. Use when conducting code reviews, setting review standards, or implementing review automation.

.moai/config.json official schema documentation, structure validation, project metadata, language settings, and configuration migration guide. Use when setting up project configuration or understanding config.json structure.

Claude Code context window optimization strategies, JIT retrieval, progressive loading, memory file patterns, and cleanup practices. Use when optimizing context usage, managing large projects, or implementing efficient workflows.

Guides agents through SPEC-First TDD workflow with context engineering, TRUST principles, and @TAG traceability. Essential for /alfred:1-plan, /alfred:2-run, /alfred:3-sync commands. Covers EARS requirements, JIT context loading, TDD RED-GREEN-REFACTOR cycle, and TAG chain validation.

Guide Alfred to detect user expertise level (Beginner/Intermediate/Expert) through in-session behavioral signals without memory file access

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.

Profile a repository, inspect existing Litho/deepwiki-rs cache state, generate a repo-local Litho config that preserves the user's current global model/provider, and run deepwiki-rs within a target time budget. Use when Claude needs to analyze a repo quickly with Litho, auto-tune exclusions and boundary settings by repo size, reuse cache intelligently, or create a filtered local copy for very large repos.

Create OmoiOS Improvement Proposals (OIPs) through an interactive workflow. Gathers context from the user via clarifying questions, researches relevant codebase files, then writes a complete proposal following the OIP template. Use when requesting "create a proposal", "write an OIP", "new proposal", "propose a feature", "OIP", "improvement proposal", or when the user wants to formally propose a product, architecture, or process change for OmoiOS.

Spec-driven development workflow for turning feature ideas into structured PRDs, requirements, designs, tickets, and tasks. Uses a state machine approach with EXPLORE → REQUIREMENTS → DESIGN → TASKS → SYNC phases. Each phase has validation gates, checkpointing, and session transcript support for cross-sandbox resumption.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Headless browser automation CLI for AI agents. Use for web scraping, testing, form filling, screenshots, and any browser interaction. Triggers: "browse", "open website", "click button", "fill form", "screenshot", "scrape", "test login flow", "automate browser", "web automation".

Spec-driven development workflow for turning feature ideas into structured PRDs, requirements, designs, tickets, and tasks. Uses a state machine approach with EXPLORE → REQUIREMENTS → DESIGN → TASKS → SYNC phases. Each phase has validation gates, checkpointing, and session transcript support for cross-sandbox resumption.

Build automated billing systems for recurring payments, invoicing, subscription lifecycle, and dunning management. Use when implementing subscription billing, automating invoicing, or managing recurring payment systems.

Expand and enrich documentation using DeepWiki (GitHub repos) and Context7 (libraries). Use when the user wants to research a library/framework, expand existing docs, generate comprehensive documentation from questions, or fill gaps in markdown files. Generates research questions, queries multiple sources, and synthesizes findings into structured documentation.

This skill should be used when the user asks to "detect asyncpg usage", "find asyncpg patterns", "scan for asyncpg imports", or "identify asyncpg database code in FastAPI projects". It automatically scans Python files to identify asyncpg imports, connection patterns, and query execution methods that need conversion to SQLAlchemy.

This skill should be used when the user asks to "convert asyncpg to SQLAlchemy", "convert database queries", "migrate asyncpg code", "transform asyncpg patterns to SQLAlchemy", or "update FastAPI database layer". It provides systematic conversion of asyncpg code to SQLAlchemy async patterns with proper error handling and transaction management.

This skill should be used when the user asks to "configure Supabase with SQLAlchemy", "set up Supabase async engine", "create Supabase models", "handle Supabase authentication with SQLAlchemy", or "integrate Supabase pooling with SQLAlchemy async patterns". It provides complete Supabase integration patterns for SQLAlchemy with async support, authentication, and connection pooling optimizations.