cc-dev-tools

This skill should be used whenever the user names codex as the actor for ANY task, regardless of verb or phrasing — "use codex" / "using codex", "ask codex", "run codex", "call codex", "have/let/tell/get codex do X", "delegate this to codex", "with/via codex", "codex cli", "codex: <task>", or bare imperatives like "codex review/fix/implement …" — or explicitly asks to delegate work to a frontier reasoning model (e.g., "have GPT-5 review this", "get the OpenAI reasoning model to design X", "ask the high-reasoning model"). Also triggers on "continue codex" / "resume the codex session" for iterative development, and on "have codex review this PR / branch / diff / my changes" for delegated code review. Do NOT trigger when codex / GPT-5 is merely a discussion topic rather than the requested actor.

This skill should be used when the agent needs to drive, observe, or manage ANOTHER interactive command-line program inside tmux — especially other agent CLIs such as codex, gemini, or aider. Triggers on spawning or reusing a tmux session/window/pane for a long-lived CLI, typing input with send-keys, reading output with capture-pane, detecting when the driven CLI is idle/done, binding one Claude session to its sub-process, serializing concurrent drivers (sync/locking), and lifecycle/cleanup of those windows. Do NOT trigger for plain one-shot shell commands that finish on their own, for tmux questions unrelated to driving an interactive program, or when the user is merely discussing tmux as a topic.

This skill should be used when the user asks to send a file, artifact, image, document, PDF, video, audio, or text message to their Telegram chat. Triggers include "use asun:telegram to send …", "send this to telegram", "telegram this file", "post to telegram", "share via telegram", or any phrase that asks Claude to push content through the user's personal Telegram channel. The skill is one-way (Claude → Telegram); it does not read incoming Telegram messages.

This skill should be used when the user wants to invoke Google Gemini CLI for complex reasoning tasks, research, and AI assistance. Trigger phrases include "use gemini", "ask gemini", "run gemini", "call gemini", "gemini cli", "Google AI", "Gemini reasoning", or when users request Google's AI models, need advanced reasoning capabilities, research with web search, or want to continue previous Gemini conversations. Automatically triggers on Gemini-related requests and supports session continuation for iterative development.

This skill should be used when the user wants to generate, create, make, draw, design, edit, or restore any image or visual content. Trigger phrases include "generate an image", "create an illustration", "make an icon", "draw a diagram", "design a pattern", "edit this photo", "restore a photo", "use nanobanana", "nano banana", "make a thumbnail", "featured image", "visual asset", "graphic", "artwork", "background image", "wallpaper", "texture". Standalone image generation using the Nano Banana MCP server with Gemini image models. No Gemini CLI required.