agent-skills

Triage an email inbox into a small action queue. Use when the user asks to process, clean up, rank, label, archive, or draft replies for email.

Rewrite any writing so it sounds clear, human, and plain. Use for landing pages, emails, docs, posts, scripts, lessons, prompts, and messages with AI slop, purple prose, cliches, em dashes, hype, vague claims, or over-polished language.

Manage an engineering backlog for humans and AI agents: classify issues, improve issue quality, sync PR state, and label safe tickets for agent execution. Use when GitHub Issues, GitHub Projects, Linear, or an explicit local backlog path is the source of truth.

Turns vague, messy, voice-dictated, or multi-part asks into a self-contained prompt a fresh agent can execute. Use when the user asks to clarify, stress-test, tighten a plan, or resolve references like "the thing". Interviews one question at a time, then outputs a final prompt.

Creates a responsive HTML explainer with source-grounded copy, teaching diagrams, and browser-verified layout. Use when the user asks to visualize, diagram, or explain something as an HTML artifact.

Explains one technical theme as a teachable document with mechanism-first sections, examples, edge cases, and an exercise. Use when the user asks to explain, teach, or document a concept as a course lesson, YouTube reference, or newsletter basis.

Rewrites a rough prompt, voice dump, or half-written instruction into an agent-ready prompt. Use when the user asks to make a prompt better, enhance/refine a prompt, clean up instructions for an agent, or improve pasted prompt text. One-shot transformer; does not interview.

Simplifies skills, prompts, and agent instructions to their most basic useful form: load-bearing verbs, nouns, constraints, examples, and checks. Use when the user asks to compress, simplify, shorten, tighten, de-noop, remove noise, or trim a prompt, spec, plan, or skill file.