bytonylee

Teach Claude Code built-in commands versus bundled skills such as debug, batch, loop, claude-api, and fewer-permission-prompts.

Teach Claude Code MCP installation, /mcp, OAuth/remote MCP, and MCP prompts as slash commands.

Teach Claude Code skills as custom slash commands, arguments, allowed-tools, context fork, and legacy commands compatibility.

Teach Claude Code /agents, custom subagents, @ mentions, foreground/background behavior, subagent memory, scoped MCP, and AskUserQuestion limits.

Teach Codex diff review, working-tree review mode, and copy/export habits before committing.

Teach Codex MCP setup, /mcp diagnostics, apps, plugins, and external tool trust boundaries.

Teach Codex skills, $skill invocation, .agents/skills layout, references/scripts/assets, and imagegen as a Codex skill example.

Teach Codex subagents, /agent thread switching, parallel exploration, and background terminal control.

Build single-file HTML horizontal-swipe presentation decks using the Tightened Slide process with locked layouts, strict grid rules, theme presets, image slot discipline, and validation.

End-to-end GPT image slide workflow. Trigger when the user wants to create a slide deck as generated images from a reference slide, source files, and a deck prompt. Runs design, plan, prompt, and render stages in order.

End-to-end HTML slide workflow. Trigger when the user wants a slide deck as editable HTML/CSS/JS from a reference design, source files, and a deck prompt. Runs design, plan, prompt, and render stages in order.

Shared slide-style extraction skill for GPT-image and HTML slide workflows. Converts one or more reference visuals into a reusable DESIGN.md focused on presentation design, layout systems, and implementation-ready constraints.

Persuasive GPT image deck-planning skill. Uses extracted DESIGN.md, user files, and the user's goal to decide slide ordering, page count, evidence placement, and narrative flow in JSON.

Page-level GPT image slide prompting skill. Converts DESIGN.md and slide_plan.json into detailed slide-generation prompts in JSON while preserving theme, body-slide consistency, and layout discipline.

Render slide images sequentially from DESIGN.md and slide prompt JSON using Codex native image generation, saving each output into the workspace with page-number filenames.

Second HTML slide stage. Trigger when the user wants only deck planning, slide ordering, evidence mapping, or slide_plan.json before implementing an HTML slide deck.

Polish an existing KRDS-based website/app to maximize rule compliance, accessibility, and consistency.

Start from initial state and produce a KRDS-compliant implementation plan for website or app UI.

Transform an existing website/app theme and structure to KRDS UIUX rules while preserving behavior.

Create game-ready fixed-cell pixel-art character spritesheets from text concepts, reference images, or existing character art. Use when Codex needs to design, generate, clean up, validate, and package 2D game characters with native 32x32, 64x64, or 128x128 cells; 4-way or 8-way directions; idle, walk/run, jump, attack, archer, caster, or other animation strips; transparent GIF/WebP previews; and per-direction targeted regeneration.

Use this skill when setting up, validating, or explaining codex-linker in this repository. It covers onboarding multiple Codex ChatGPT OAuth accounts with separate CODEX_HOME auth files, shared non-auth config symlinks, shell aliases, doctor checks, and optional usage/reset-ticket status checks.

Use this skill whenever the user asks to generate, create, render, draw, or make an image, picture, illustration, icon, logo, or any other visual asset. Also use it when the user wants to edit, modify, restyle, or combine existing images (provide them as reference_file inputs). The skill drives the `imagegen` CLI in this repo, which uses the user's local Codex ChatGPT authentication to call the private image-generation backend. Trigger phrases include "generate an image", "create a picture", "make an image of", "draw me a", "render this", "make this cat wear a hat", and similar. Prefer this skill over describing images in text.