agent-skills

Thinking-partner skill for co-building shared understanding before action. Invoke only when the user explicitly asks to brainstorm, e.g. "brainstorm" or "let's brainstorm this". Do not invoke for ordinary requests that merely involve thinking, design, analysis, planning, or implementation.

Use when refining the scope, audience, reader takeaways, hooks, evidence plan, examples, code snippets, benchmark/performance claims, narrative angle, or outline for a blog post before drafting. Trigger for requests to clarify what a post should be about, who it is for, what readers should learn or believe, how to avoid fluffy ideas, or how to show claims through concrete demos, examples, data, or artifacts.

Use when writing, drafting, or editing blog posts. Applies the user's preferred writing style — informal, personable, technically focused, and narrative-driven. Trigger when creating new blog content or revising existing prose.

Layer on top of the brainstorming loop when the session has more density, structure, or comparison than chat alone can carry. Externalizes maps, diagrams, comparisons, plans, and dense explanations into focused supporting artifacts so the conversation stays readable. What this skill does: defines how to reduce cognitive load during brainstorming by creating interleaved one-way artifacts that own structural or visual material — branch maps, decision maps, comparison pages, architecture and sequence diagrams, state machines, dependency maps, risk and validation matrices, implementation-plan explainers, concept walkthroughs, and similar explanatory outputs. Chat continues to carry the two-way conversation; artifacts carry the heavy lifting. Why use it: when active branches multiply, tradeoffs get hard to hold in head, or an explanation would balloon the chat, prose-only conversation starts to lose the user. This skill keeps chat short and scannable by handing off heavy material to artifacts the user can open,