shinshin86

Apply released @aituber-onair/chat updates to @aituber-onair/core and core React examples, including dependency alignment, core re-exports, example model lists, docs, version/changelog, lockfiles, and verification. Use after chat package upgrades or when…

Apply released @aituber-onair/chat updates to @aituber-onair/core and core React examples, including dependency alignment, core re-exports, example model lists, docs, version/changelog, lockfiles, and verification. Use after chat package upgrades or when…

Add a new chat model id to @aituber-onair/chat and wire it through constants, provider implementation, tests, example UI selector, docs, and versioning updates. Use when requests include adding a new model, supporting a specific model id, adding a provider…

Add a new chat model id to @aituber-onair/chat and wire it through constants, provider implementation, tests, example UI selector, docs, and versioning updates. Use when requests include adding a new model, supporting a specific model id, adding a provider…

Launch vLLM or llama.cpp as an OpenAI-compatible Chat Completions server on Google Colab through Colab MCP Go, issue a temporary trycloudflare URL with cloudflared, and verify it with the @aituber-onair/chat compatibility probe and an AITuber OnAir Core React…

Launch vLLM or llama.cpp as an OpenAI-compatible Chat Completions server on Google Colab through Colab MCP Go, issue a temporary trycloudflare URL with cloudflared, and verify it with the @aituber-onair/chat compatibility probe and an AITuber OnAir Core React…

Add a new TTS provider to @aituber-onair/voice and wire it through engine implementation, public voice option types, internal engine handlers, factory registration, tests, docs, examples, and optional versioning updates. Use when requests include adding a TTS…

Add a new TTS provider to @aituber-onair/voice and wire it through engine implementation, public voice option types, internal engine handlers, factory registration, tests, docs, examples, and optional versioning updates. Use when requests include adding a TTS…

Compose and send posts on X (Twitter) through ai-chrome-pilot. Use when the user wants to create a normal post, reply, quote post, or scheduled post, optionally with images, while choosing the correct mode from explicit inputs and verifying the result after…

Quote a specific post on X (Twitter) through ai-chrome-pilot. Use when the target post is already known and the user wants a focused quote-post workflow with safe composer input and post-submission verification.

Schedule a post with an image and AI-generated content label on X (Twitter). Use this when scheduling posts that include local image files and need the "AI-generated" disclosure toggle enabled.

Schedule a post on X (Twitter) and verify it was successfully scheduled. Use this when the task is specifically about scheduling and scheduled-post verification; prefer x-compose-post for general post creation, replies, quote posts, or mixed posting workflows.

Inspect the scheduled posts list on X (Twitter) through ai-chrome-pilot without creating or modifying posts. Use when the user wants a read-only inventory of currently scheduled posts, wants to know what is queued in a profile, or wants to export that list to…

Perform selected actions on X (Twitter) notifications through ai-chrome-pilot. Use when the user wants to open X notifications, identify reply or quote repost notifications, filter them by explicit criteria such as action, type, actor, text, date, or limit,…

Inspect notifications on X (Twitter) through ai-chrome-pilot and extract replies or quote reposts without performing likes or other engagement actions. Use when the user wants a read-only pass over X notifications, a candidate list for later review, or a safe…

Log in to X (Twitter) via browser. Launches the ai-chrome-pilot server, navigates to X, and asks the user to log in manually so the session is persisted to a profile. Use this as a prerequisite before any X posting or interaction skills.

Write or refine prompts for MiniMax H3 video generation via comfy-agent (minimax_h3_t2v / minimax_h3_i2v / minimax_h3_r2v presets). Use whenever composing the --104_prompt for an H3 run, when a user asks for a video clip on an H3 environment, or when an H3…

Generate images, video, or music/audio with ComfyUI via the comfy-agent CLI. Use when the user asks to create/generate an image, video clip, animation, song, BGM, or sound effect, or asks to set up / reconnect a ComfyUI environment (local or Google Colab).…

Convert a user-provided static anime character image into a verified rig-ready PSD by coordinating the Still2Rig PSD local job CLI with a user-approved Google Colab session through Colab MCP Go. Use for Still2Rig PSD conversion, repair, import, or QA…

Generate, repair, validate, and QA agmsg Office character spritesheets from character portraits. Use when adding or replacing character spritesheet.webp files under public/assets/characters, matching the Miko/Mai 8x9 animated atlas contract, or producing real…