moniro

Create and manage AI agent sessions with multiple backends (SDK, Claude CLI, Codex, Cursor). Also supports multi-agent workflows with shared context, @mention coordination, and collaborative voting. Use for "start agent session", "create worker", "run agent", "multi-agent workflow", "agent collaboration", "test with tools", or when orchestrating AI conversations programmatically.

Discover, record, and execute E2E test cases using browser exploration. Use when exploring test scenarios, recording user flows, organizing test structure, or executing YAML-based tests.

Guide for authoring effective Agent Skills using principle-based approach (Progressive Disclosure, Respect Intelligence, Enable Discovery). Covers creating, improving, refactoring, and reviewing skills. Use for skill authoring, design questions, best practices, anti-patterns, or structure decisions.

Dives deep into project questions using layered investigation (docs → code → analysis) to provide evidence-based answers with file:line citations. Use when asking "how does X work", "what is Y", "where is Z", or investigating features, APIs, configuration, codebase structure, or technical decisions.

Guides technical decisions, architecture, and implementation. Use for tech choices, system design, API design, refactoring, or "how should I build this" questions.

Initialize frontend projects with opinionated modern toolchain - Bun (package manager), Oxfmt (formatter), Oxlint (linter), tsdown (npm bundler), tsgo (type checker). Use when creating new frontend/TypeScript projects, setting up project tooling, or mentions "init project", "new frontend", "setup tooling".

Manages project housekeeping including documentation organization, dependency management, directory structure, code cleanup, technical debt tracking, and infrastructure configuration. Use when organizing documentation, cleaning up dependencies, reorganizing folders, removing dead code, addressing tech debt, or maintaining project structure.

Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "todo", or session handoff.

Orients agents in new projects by scanning entry documents and discovering capabilities. Use at session start, when entering unfamiliar territory, or when asking "what can you do" or "where do I start".

Test, validate, and improve agent instructions (CLAUDE.md, system prompts) using sub-agents as experiment subjects. Measures instruction compliance, context decay, and constraint strength. Use for "test prompt", "validate instructions", "prompt effectiveness", "instruction decay", or when designing robust agent behaviors.

Refines code changes for better reviewability. Validates change cohesion (no mixed concerns), generates clear commit messages, creates PR/MR with reviewer-focused descriptions. Use when committing, reviewing, creating PR/MR, or mentions "commit", "review", "PR", "MR", "pull request", "merge request", "refine", "提交", "审查".

Bootstrap agent working system for a new project. Triggers on "setup agent system", "initialize claude", "bootstrap project".

Unified validation orchestration for code quality, consistency, and project health. Auto-triggers on code changes, PR creation, or explicit validation requests. Coordinates refining, housekeeping, and custom validators into cohesive pipelines. Use for "validate", "check", "verify", "验证", "检查", or when quality assurance is needed.