/difference

name: difference
description: Compare A vs B, weigh pros and cons of A, B, C, ..., or explain the nuance between sentences — a quick answer from what the model already knows
argument-hint: "[A vs B | A, B, C, ... | sentences]"
disable-model-invocation: true
effort: low
allowed-tools:
  - WebSearch

Difference

The user wants a fast answer, not research. Invoking this skill is their explicit opt-out of any standing rule to check docs or search before answering, except the lookup below: answer from what you already know.

Compare what the arguments name. With no arguments, compare the items just discussed; ask only when nothing comparable is there.

Lookups

What you already know includes docs read or fetched earlier in this session; check those first. Then run one web search (`WebSearch` in Claude Code, `web_search` in Codex) before answering when an item is a named identifier (setting key, CLI flag, env var, API field) or something you cannot identify at all, such as a tool released after your training. An identifier's name only suggests what it does, so recognizing the name is no reason to skip the search. Being unsure of an item's latest version does not count. Use no subagents.

Answer

Keep it as short as the question allows, and let the items decide the shape. Spend the words on where they actually differ, not on what they share.

• Alternatives someone picks between (tools, approaches, patterns): give each one's pros and cons.
• Sentences: how each lands differently — tone, implication, what a reader infers.
• An answer that hinges on a version, price, or "latest" fact: add one line saying it is as of your training data.

The last line of the answer is still comparison: no verdict, no offer to dig deeper.