meirlabs

The meirlabs writing-voice skill — hard rules, tone, and never-use lists so drafts sound like one person instead of a model. npx installs it into .claude/skills.

The meirlabs new-project orchestration skill — discovery, an approval-gated PLAN.md, then the full scaffold/design/analytics/docs pipeline. npx installs it into .claude/skills.

How a one-person studio takes an idea to market — positioning, channels, and operating cadence, as a Claude Code skill. npx installs it into .claude/skills.

The meirlabs loop-engineering skill — drive a big goal end-to-end as a multi-agent orchestrator. Fan out as many haiku/sonnet/opus subagents as the goal needs, pick the model tier per task, plan first and get the plan approved before any large fan-out, ad

The meirlabs design rules for a product's visual layer — brand tokens, fixed structure, and the rules everything defers to. A Claude Code skill; npx installs it into .claude/skills.

Verify any UI change end-to-end before declaring it done — drive it in a real browser, check console and mobile, screenshot before/after. A Claude Code skill; npx installs it into .claude/skills.

The meirlabs security-audit skill — find real, exploitable issues and turn each into a ranked finding with an implementation plan: a threat model, a multi-lens static sweep, live-config checks, then a 3-skeptic adversarial verification pass so the report

The meirlabs AEO skill — make a site quotable by AI answer engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews). Encodes the per-page Findable/Quotable/Understandable/Trustworthy checklist with exact pass thresholds, the site-wide Content/Te

The meirlabs bookmark-triage skill — turn saved X/Twitter bookmarks into Linear tickets automatically: a daily agent loop that reads new bookmarks via the shiori.sh CLI, classifies each against your idea taxonomy, auto-files the actionable ones, and tags

The five-step ship checklist as a Claude Code skill — typecheck, build, env check, deploy to Vercel, report the URL. npx installs it into .claude/skills.

The meirlabs loops skill — design, pilot, and run standing agent loops: scheduled watcher-scribe agents that check a system against written thresholds between sessions, keep the state of record honest, and escalate to a human instead of acting. npx instal

A Claude Code skill that files a SaaS idea into a standard project structure — plan-first, confirm-before-move. npx installs it into .claude/skills.

The usage skill for @meir-labs/ui-kit — when tables, pagination, status pills, tags, or metrics come up, reach for the kit instead of rebuilding. npx installs it into .claude/skills.

The meirlabs tool-picking skill — a multi-agent evaluation harness: verified pricing research, adversarial fact-checking, a judge panel on the buyer's real priorities, and a decision memo with switch triggers. npx installs it into .claude/skills.

The house method for writing SEO/AEO articles as a Claude Code skill — answer-engine structure, tiered numbers with concrete examples, a stats convention, and the editorial rules. npx installs it into .claude/skills.

The meirlabs automated-testing standard: Vitest + Testing Library for unit/integration, Playwright for E2E, a CI workflow, and plain-language reporting for a non-coder owner. npx installs it into .claude/skills.

A motion-review Claude Code skill with ten non-negotiable standards derived from Emil Kowalski's design engineering philosophy — default to flagging, approval is earned. npx installs it into .claude/skills.