This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash…
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDEPLUGINROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop…
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
How to build a working dashboard — the exact dashboard.json contract, how to explore a schema and test SQL before it becomes a panel, which chart answers which question, and how to lay panels out so the important number is where the eye lands. Use for EVERY dashboard request, before writing anything.
How to plan and design presentation decks — content architecture first, then a deliberate style system, then slide-by-slide craft. Use for EVERY deck request, before touching any slide tool.
How to make a film that holds together — the submit-and-poll loop, the storyboard you agree before spending anything, how a character stays the same person across shots, what each capability can and cannot do today, and how the timeline becomes one exported video. Use for EVERY video request, before generating…
Keep AGENTS.md and skills in sync with code. Read before committing any change that touches paths, scripts, ports, names, configs, or workflows referenced in agent docs.
OpenAI Codex CLI running inside an aicodebox container, put on the network. Exposes seven ways in — interactive shell, one-shot exec, an HTTP REST API (workspace file ops, sync/async prompt runs with run-id polling), an OpenAI-compatible /openai/v1/chat/completions endpoint (streaming, client-executed…