From pagekit
Run the heuristic AI-slop regression check on PageKit drafts. Wraps scripts/slop-check.sh. Use before and after the claim-check step, and any time you want to sanity-check a draft for the mechanically detectable slop patterns.
npx claudepluginhub hnshah/pagekit --plugin pagekitThis skill uses the workspace's default tool permissions.
Wraps `scripts/slop-check.sh`. Heuristic regression check covering the mechanically detectable subset of `../pagekit/references/anti-slop.md`: Not-X-Not-Y headings and sentences, em-dash stacking, "actually" intensifier, copula avoidance, signposting, filler, significance inflation, anaphora, rule-of-three short-sentence clustering, intensifier vocabulary, quoted antithesis.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Builds 3-5 year financial models for startups with cohort revenue projections, cost structures, cash flow, headcount plans, burn rate, runway, and scenario analysis.
Wraps scripts/slop-check.sh. Heuristic regression check covering the mechanically detectable subset of ../pagekit/references/anti-slop.md: Not-X-Not-Y headings and sentences, em-dash stacking, "actually" intensifier, copula avoidance, signposting, filler, significance inflation, anaphora, rule-of-three short-sentence clustering, intensifier vocabulary, quoted antithesis.
../pagekit/references/anti-slop.md — the authoritative pattern catalogbash scripts/slop-check.sh [paths...]. With no args, scans every homepage-draft.md / first-page-draft.md / first-page-draft-corrected.md under runs/.pagekit-first-page-draft produces a draft, before invoking pagekit-claim-check.Do not advance to the claim-check step until slop-check is clean on the draft. The claim-check should focus on semantic issues; the slop-check should have already cleared the obvious cadence problems.
The script is heuristic. It will flag false positives (some rule-of-three clusters carry real content; some uses of "actually" are correct). Use judgement; do not blindly rewrite. The script's job is to surface lines worth looking at.