Agent skills for Codex CLI

Agent communication toolkit — verb commands for WhatsApp, Telegram, Discord, Slack.

Manage the LLM response cache. View cache statistics, clear entries, configure TTL policies, and control semantic-similarity caching…

Manage CLI tool integrations exposed via the API.

Trigger system backups, restore from backup files, and manage the SQLite database lifecycle.

Omni v2 message execution specialist — use for sending messages (text, TTS, media, reactions, stickers, polls), searching messages, batch…

Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent…

Query available AI models across all configured providers.

Platform operations — instances, routes, providers, config, events, automations, webhooks, prompts, contacts, batch processing.

Automates cross-platform social media publishing and account management for video and image-text content.

Always-on Omni router for messaging across WhatsApp, Telegram, Discord, Slack.

Manage agent routing rules: create per-chat or per-user routes to specific providers/agents, test route resolution, and view routing…

Send outbound messages with Omni CLI: text, media, TTS, reactions, stickers, contacts, locations, polls, embeds, presence, forwards, and…

Synchronise OmniRoute configuration, provider connections, and settings to/from cloud storage.

Install, start, stop, restart, and update embedded services (9Router, CLIProxyAPI).

When the user wants to optimize omnichannel fulfillment, manage buy-online-pickup-in-store (BOPIS), ship-from-store, or multi-channel…

Deep reference on Omnigent config format, executor types, skill/tool structure, and conventions.

Interact with OmniRoute via JSON-RPC 2.0 agent-to-agent protocol. 6 built-in A2A skills: smart-routing, quota-management…

Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with…

Manage provider connections from the CLI: list available/configured providers, add, test, test-all, validate, rotate API keys, and view…

Configure RTK (command output), Caveman (prose), and stacked compression modes.

Build private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp.