Skip to content

heymegabyte/agent-skills / 15-site-generation

site-generation

Unverified

End-to-end AI website generation pipeline. Claude Opus 4.8 emits Bolt-style <boltArtifact> envelopes (multi-file, plan-first) that customize Vite+React+Tailwind templates from pre-researched business data. Pre-research via APIs, media acquisition, brand extraction, visual inspection via GPT Image 2 vision, R2 upload (per-file content-type by extension), D1 status updates. Supports all business types: SaaS, portfolio, non-profit, restaurant, salon, medical, legal, retail, tech.

FileKindSize
SKILL.mdskill md11.7 KB
_real-ua.mjsscript1.4 KB
blog-import.mjsscript10.5 KB
bolt-artifact-protocol.mdmarkdown8.4 KB
build-breaking-rules.mdmarkdown86.0 KB
build-image-redirects.mjsscript3.4 KB
build-prompts.mdmarkdown86.3 KB
check-routes.shexecutablescript904 B
domain-features.mdmarkdown17.1 KB
enhance-blog-posts.mjsscript12.9 KB
homepage-block-library.mdmarkdown12.6 KB
local-seo.mdmarkdown7.6 KB
media-acquisition.mdmarkdown39.2 KB
non-technical-owner-onboarding.mdmarkdown8.3 KB
page-set-expansion.mdmarkdown19.1 KB
pseo-templates.mdmarkdown13.3 KB
quality-gates.mdmarkdown46.6 KB
research-pipeline.mdmarkdown20.5 KB
scan-assets.mjsscript3.0 KB
small-business-mode.mdmarkdown9.6 KB
source-fidelity-loop.mdmarkdown10.0 KB
squarespace-full-crawl.mjsscript2.8 KB
template-improvements-100.mdmarkdown15.0 KB
template-system.mdmarkdown39.7 KB
validate-assets.mjsscript5.0 KB
validate-banned-slop.mjsscript4.6 KB
validate-brand-colors.mjsexecutablescript6.1 KB
validate-citations.mjsscript6.0 KB
validate-color-contrast.mjsscript5.2 KB
validate-favicon-set.mjsscript4.9 KB
validate-html-entities.mjsscript3.4 KB
validate-image-relevance.mjsscript6.1 KB
validate-internal-links.mjsscript4.3 KB
validate-jsonld-schema.mjsscript5.1 KB
validate-nap-consistency.mjsexecutablescript8.0 KB
validate-page-count.mjsscript4.1 KB
validate-page-set-completeness.mjsscript9.3 KB
validate-photo-authenticity.mjsexecutablescript10.0 KB
validate-pwa-kit.mjsscript7.0 KB
validate-route-metadata.mjsscript7.3 KB
validate-source-fidelity.mjsscript6.0 KB
validate-typography.mjsscript4.0 KB
verticals/local-business-site.mdmarkdown3.8 KB
verticals/nonprofit-site.mdmarkdown3.3 KB
verticals/restaurant-site.mdmarkdown2.6 KB

validate-image-relevance.mjs

View on GitHub
#!/usr/bin/env node
// validate-image-relevance.mjs — image topic-relevance + semantic-match gate (GPT-4o vision)
// Every page-rendered image must score ≥8/10 on topic relevance to the page subject AND
// pass business-type semantic match (rules/always.md "Every image business-type semantic
// mismatch gate"). Skips logo/icon/favicon. Caches results in .image-relevance-cache.json
// keyed by sha256(image bytes + page slug) so re-runs only re-score new images.
// When OPENAI_API_KEY is unset, validator no-ops with warning. When set, scores every
// image and fails on any <8/10 with the page slug + image src + reason.
// Usage: node validate-image-relevance.mjs <build-dir>
// Exit 0 = pass (or skipped), exit 1 = fail.

import { readdirSync, readFileSync, statSync, existsSync, writeFileSync } from 'node:fs';
import { join, relative, resolve, basename } from 'node:path';
import { createHash } from 'node:crypto';

const BUILD = resolve(process.argv[2] || '.');
const DIST = existsSync(join(BUILD, 'dist')) ? join(BUILD, 'dist') : BUILD;
const CACHE_PATH = join(BUILD, '.image-relevance-cache.json');
const OPENAI_KEY = process.env.OPENAI_API_KEY;

if (!existsSync(DIST)) {
  console.error(`[validate-image-relevance] dist dir not found: ${DIST}`);
  process.exit(1);
}
if (!OPENAI_KEY) {
  console.warn('[validate-image-relevance] OPENAI_API_KEY unset — skipping (set to enable vision scoring)');
  process.exit(0);
}

const cache = existsSync(CACHE_PATH) ? JSON.parse(readFileSync(CACHE_PATH, 'utf8')) : {};

function walkHtml(dir) {
  const out = [];
  for (const e of readdirSync(dir)) {
    if (e === 'node_modules' || e === '.git') continue;
    const p = join(dir, e);
    if (statSync(p).isDirectory()) out.push(...walkHtml(p));
    else if (e.toLowerCase().endsWith('.html')) out.push(p);
  }
  return out;
}

function pageContext(html) {
  const titleM = html.match(/<title[^>]*>([^<]+)<\/title>/i);
  const descM = html.match(/<meta\s+name=["']description["']\s+content=["']([^"']+)["']/i);
  const h1M = html.match(/<h1[^>]*>([\s\S]*?)<\/h1>/i);
  const h2M = html.match(/<h2[^>]*>([\s\S]*?)<\/h2>/i);
  return [titleM?.[1] ?? '', descM?.[1] ?? '', (h1M?.[1] ?? '').replace(/<[^>]+>/g, '').trim(), (h2M?.[1] ?? '').replace(/<[^>]+>/g, '').trim()].filter(Boolean).join(' | ');
}

function imageRefs(html) {
  const out = [];
  const IMG_RE = /<img\s+[^>]*src=["']([^"']+)["'][^>]*(?:alt=["']([^"']*)["'])?/gi;
  let m;
  while ((m = IMG_RE.exec(html)) !== null) {
    out.push({ src: m[1], alt: m[2] ?? '' });
  }
  return out;
}

function isSkippableSrc(src) {
  return /(?:^|\/)(?:logo|icon|favicon|sprite|loader|spinner|placeholder)/i.test(src) || /\.(?:svg)(?:\?|$)/i.test(src);
}

async function scoreImage(absPath, pageCtx, alt) {
  const buf = readFileSync(absPath);
  const ext = basename(absPath).split('.').pop()?.toLowerCase() ?? 'png';
  const mime = { png: 'image/png', jpg: 'image/jpeg', jpeg: 'image/jpeg', webp: 'image/webp', gif: 'image/gif', avif: 'image/avif' }[ext] ?? 'image/png';
  const dataUrl = `data:${mime};base64,${buf.toString('base64')}`;
  const resp = await fetch('https://api.openai.com/v1/chat/completions', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json', Authorization: `Bearer ${OPENAI_KEY}` },
    body: JSON.stringify({
      model: 'gpt-4o',
      max_tokens: 200,
      messages: [
        {
          role: 'user',
          content: [
            { type: 'text', text: `Page context: "${pageCtx}". Image alt: "${alt}". Score this image 0-10 on topic relevance to the page subject AND business-type semantic match. Return ONLY JSON: {"score":<0-10>,"semantic_match":<bool>,"reason":"<≤120 chars>"}` },
            { type: 'image_url', image_url: { url: dataUrl } },
          ],
        },
      ],
    }),
  });
  if (!resp.ok) throw new Error(`OpenAI ${resp.status}: ${await resp.text()}`);
  const j = await resp.json();
  const txt = j.choices?.[0]?.message?.content ?? '';
  const jsonM = txt.match(/\{[\s\S]*\}/);
  if (!jsonM) throw new Error(`unparsable response: ${txt.slice(0, 100)}`);
  return JSON.parse(jsonM[0]);
}

const failures = [];
const warnings = [];
const htmlFiles = walkHtml(DIST);
let scored = 0;
let cached = 0;

for (const file of htmlFiles) {
  const rel = relative(DIST, file);
  const html = readFileSync(file, 'utf8');
  const ctx = pageContext(html);
  const imgs = imageRefs(html);
  for (const { src, alt } of imgs) {
    if (isSkippableSrc(src)) continue;
    if (src.startsWith('data:') || src.startsWith('http://') || src.startsWith('https://')) continue;
    const abs = src.startsWith('/') ? join(DIST, src) : join(DIST, src);
    if (!existsSync(abs)) {
      failures.push(`${rel}: image src "${src}" not found at ${abs}`);
      continue;
    }
    const buf = readFileSync(abs);
    const key = createHash('sha256').update(buf).update(rel).digest('hex');
    let score = cache[key];
    if (score) {
      cached++;
    } else {
      try {
        score = await scoreImage(abs, ctx, alt);
        cache[key] = score;
        scored++;
      } catch (err) {
        warnings.push(`${rel}: scoring "${src}" failed: ${err.message}`);
        continue;
      }
    }
    if (score.score < 8) {
      failures.push(`${rel}: image "${src}" scored ${score.score}/10 — ${score.reason}`);
    }
    if (score.semantic_match === false) {
      failures.push(`${rel}: image "${src}" failed business-type semantic match — ${score.reason}`);
    }
  }
}

writeFileSync(CACHE_PATH, JSON.stringify(cache, null, 2));

if (warnings.length) {
  console.warn(`\n[validate-image-relevance] ${warnings.length} warnings:`);
  warnings.slice(0, 20).forEach((w) => console.warn(`  ⚠ ${w}`));
}
if (failures.length) {
  console.error(`\n[validate-image-relevance] ${failures.length} failures (${scored} new + ${cached} cached scores):`);
  failures.slice(0, 30).forEach((f) => console.error(`  ✗ ${f}`));
  if (failures.length > 30) console.error(`  ...+${failures.length - 30} more`);
  console.error('\n[validate-image-relevance] BUILD GATE FAILED — re-generate offending images via skill 12');
  process.exit(1);
}
console.log(`[validate-image-relevance] ✓ ${scored + cached} images scored ≥8/10 (${scored} new, ${cached} cached) across ${htmlFiles.length} pages.`);
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall