Agent skills for ChatGPT

Classic block-game inspired design with playful colors, bold display fonts, and compact, high-energy layouts.

Reviews, polishes, and proofreads existing Japanese and English text while strictly preserving factual accuracy and intent.

Automate Text To PDF tasks via Rube MCP (Composio).

Converts text and script files into high-quality speech using MiniMax TTS, local Kokoro TTS, or Edge TTS.

Generate matching visuals from text via Picsart gen-ai.

Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy.

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human…

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

A relentless interview to sharpen a plan or design.

Elite frontend image-direction skill for generating premium, conversion-aware website design references.

Spring Security best practices for authn/authz, validation, CSRF, secrets, headers, rate limiting, and dependency security in Java Spring…

Use when implementing any feature or bugfix, before writing implementation code

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including…

Generates executive-ready Google Slides presentations matching "The AI Factory Blueprint" visual style.

Generic, low-effort, look-the-same AI output.

How the chain layer of a dapp front-end is built: the react-query carve-out for chain hooks, native bigint numerics, one address/ABI…

Use when (a) operator describes a situation OR a plan step OR the agent shows an inverse pattern, and agent should NAME the right chengyu…

Use when building features with TCA (The Composable Architecture), structuring reducers, managing state, handling effects, navigation, or…

Applies CQRS and Event Sourcing for read/write separation and audit trails.

Generate and edit images using Google Gemini image models.

This skill should be used when the user asks about "how to research", "research best practices", "evaluate sources", "source credibility"…