agents/skills/smart-brevity/SKILL.md
Rewrite text using Smart Brevity principles — shorter, sharper, audience-first communication. Use this skill whenever the user wants to: rewrite or edit text to be more concise, apply Smart Brevity formatting, improve emails/newsletters/presentations/speeches/social posts/meeting agendas, audit a codebase or website for copy improvements, make writing punchier or clearer, reduce word count while preserving meaning, or mentions "Smart Brevity" in any context. Also trigger when the user pastes a block of text and asks to "tighten," "shorten," "clean up," "make it punchy," "cut the fluff," or similar brevity-related requests. Even if the user doesn't say "Smart Brevity" explicitly, use this skill for any request to improve the clarity, brevity, or impact of written communication.
npx skillsauth add carterdea/dots smart-brevityInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Rewrite and audit text using the Smart Brevity system — a framework for saying more with less, developed by the founders of Axios and Politico.
Smart Brevity is a system for thinking more sharply, communicating more crisply, and saving everyone time. The core idea: adapt to how people actually consume content. People spend 26 seconds on average reading a piece of content. Most scan, not read. So every word must earn its place.
The motto: "Brevity is confidence. Length is fear."
The user provides text. You rewrite it and present numbered changes for approval.
The user points you at a codebase, website, document, or app. You scan the copy, identify text that violates Smart Brevity principles, and present numbered recommendations for approval.
Determine what kind of content the user is working with. If unclear, ask. The medium
determines which specific guidance applies. Read mediums.md for medium-specific rules.
Common mediums:
Read principles.md for the full rule set. Apply these checks:
This is critical. Do NOT just rewrite everything silently. Present each change as a numbered item so the user can approve or deny individually.
Format each change like this:
1. [CATEGORY] Brief description of the change
BEFORE: "the original text"
AFTER: "the rewritten text"
WHY: one-sentence rationale
2. [CATEGORY] Brief description of the change
BEFORE: "the original text"
AFTER: "the rewritten text"
WHY: one-sentence rationale
Categories to use:
[HEADLINE] — tease/subject line changes[LEDE] — first sentence rewrites[CONTEXT] — adding/improving "Why it matters" or Axioms[CUT] — removing unnecessary words, sentences, or sections[WORD] — replacing weak/foggy/fancy words with strong ones[STRUCTURE] — reformatting (adding bullets, bold, breaking up paragraphs)[VOICE] — passive → active, formal → conversational[LENGTH] — trimming to meet medium-specific targets[DEPTH] — adding "Go deeper" or restructuring supporting detailAfter presenting the numbered list, tell the user:
Reply with the numbers you want to apply (e.g.,
1,3,5or1-4orall), ornoneto skip.
Once the user replies:
all — apply every change and output the final rewritten text.1,3,6) — apply only those changes and output the result.none — do nothing.When applying changes to a codebase or file, make the edits directly in the files. When applying changes to pasted text, output the final rewritten version.
Always show a word count comparison: BEFORE: X words → AFTER: Y words (Z% reduction)
When the user asks you to audit copy across files:
For code audits, focus on:
Before presenting any rewrite, verify:
principles.md — Full Smart Brevity rule set (word choice, structure, formatting, anti-patterns). Read this before any rewrite.examples.md — Before/after examples from the book for calibration. Read when you need to calibrate tone and degree of change.mediums.md — Medium-specific guidance (email, newsletter, presentation, speech, social, meetings, visuals, inclusive writing). Read when the user specifies a medium.When presenting changes, be direct. No preamble. No "Great question!" No throat-clearing. Model the principles you're teaching. Your own output should exemplify Smart Brevity.
development
Add net-new product, workflow, platform, or developer-experience features as small vertical slices. Use this skill whenever the user asks to build a new feature, add a new page/route/API/workflow/job/eval/operator path, enrich an existing feature with a new user-visible capability, or plan feature architecture before coding. This skill maps the files to change or create, defines the authoritative contract, specifies tests, and gives a QA plan before treating the feature as done.
development
Verify a developer's finished Trello ticket on a non-Shopify web app and render a verdict. Dogfood the posted preview (desktop + mobile) against the card's acceptance criteria, then PASS it (approve the PR, move to Ready for Release) or FAIL it (request changes, attach repro, reassign the dev, move to Development). Read-only: never implements, commits, or opens a PR. Use when asked to 'QA this card', 'test before release', or 'sign off on this ticket'. Shopify themes use shopify-trello-qa; building a ticket uses trello-delivery.
development
Verify a developer's finished Shopify theme ticket and render a verdict. Dogfood the posted preview theme and Customizer (desktop + mobile) against the card's acceptance criteria and Figma, then PASS it (approve the PR, move to Ready for Release) or FAIL it (request changes, attach repro, reassign the dev, move to Development). Read-only: never implements, commits, deploys, or opens a PR. Use when asked to 'QA this Shopify card', 'verify the Ready for Testing card', or 'sign off on this theme ticket'. Non-Shopify apps use trello-qa; building a ticket uses shopify-trello-delivery.
development
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.