@opendirectory.dev/skills 0.1.0

package/skills/newsletter-digest/references/digest-format.md

@@ -0,0 +1,123 @@
+# Digest Format Reference
+
+Rules for structuring newsletter digests. Read this before generating any content.
+
+---
+
+## Three Digest Formats
+
+### Format 1: Weekly Roundup
+
+Use for: General weekly digest covering top stories across all monitored feeds.
+
+Target length: 350-500 words.
+
+Structure:
+1. **This Week in [Topic/Industry]** — one sentence capturing the week's theme
+2. **Top Story** — 100-150 words on the single most significant story. Include one specific data point or quote from the source.
+3. **Also Worth Reading** — 3-5 stories, each 40-60 words with a source attribution link
+4. **Quick Takes** — 3-5 one-line bullets for minor stories
+5. **Until Next Week** — 1-2 sentence closing
+
+Example section structure:
+
+```
+This Week in Developer Tools
+
+The npm ecosystem had a rough week.
+
+Top Story
+[Title as H3]
+[100-150 word summary. Every stat from the source. Source attribution link at end.]
+
+Also Worth Reading
+[Title as H3, linked to article]
+[40-60 words. Key insight. [Source: Name](URL)]
+
+Quick Takes
+- [One-line summary. Source.](URL)
+- [One-line summary. Source.](URL)
+
+Until Next Week
+[Closing sentence. No CTA filler.]
+```
+
+---
+
+### Format 2: Topic Deep Dive
+
+Use for: A focused issue on a single topic (e.g., "AI agents this week", "security incidents this week").
+
+Target length: 450-650 words.
+
+Structure:
+1. **The Big Picture** — 80-100 words on why this topic matters this week
+2. **Key Developments** — 3-4 sections, each 80-100 words, covering one development each
+3. **What to Watch** — 2-3 bullet points on what happens next
+4. **Resources** — list of all source articles with URLs
+
+---
+
+### Format 3: Curated Picks
+
+Use for: "Editor's choice" digest with opinionated selection of the best reads.
+
+Target length: 250-350 words.
+
+Structure:
+1. **This Week's Picks** — one sentence framing the selection
+2. **5 picks** — each with title (linked), 30-40 word description, and a one-line "Why read it" note
+3. **One to skip** — optional: one overhyped story and why it did not make the cut
+
+---
+
+## Length Rules
+
+| Format | Min | Target | Max |
+|--------|-----|--------|-----|
+| Weekly Roundup | 300 | 400 | 500 |
+| Topic Deep Dive | 400 | 550 | 650 |
+| Curated Picks | 200 | 300 | 380 |
+
+If Gemini output is too long, cut the Quick Takes section first, then trim the Also Worth Reading summaries.
+
+---
+
+## Attribution Rules
+
+Every non-obvious claim needs a source link. Format:
+
+- Inline: `[Source: Publication Name](https://full-url)`
+- Section header links: `### [Story Title](https://full-url)`
+- Bullet links: `- [Headline](https://full-url) — one-line summary`
+
+Never write a data point, statistic, or quote without a linked attribution.
+
+---
+
+## Tone Rules
+
+- Write for a reader who is busy. They scan. Use short paragraphs.
+- No hype. No "this is huge." Let the facts speak.
+- No first-person plural ("we noticed"). Write as a neutral observer.
+- One idea per paragraph, maximum three sentences per paragraph.
+- Dates: use full dates (April 10, 2026) not relative dates (this Tuesday).
+
+---
+
+## HTML Output Rules
+
+When generating HTML for Ghost:
+- Use `<h2>` for section headings (e.g., "Top Story", "Also Worth Reading")
+- Use `<h3>` for individual story titles
+- Use `<p>` for body text
+- Use `<ul>` and `<li>` for Quick Takes and bullet lists
+- Use `<a href="URL">` for all source links
+- Do not use `<div>` with inline styles
+- Do not use markdown syntax in the HTML output
+
+When generating Markdown for Substack:
+- Use `##` for section headings
+- Use `###` for story titles
+- Use `[text](url)` for links
+- Use `-` for bullet points

package/skills/newsletter-digest/references/output-template.md

@@ -0,0 +1,136 @@
+# Output Templates
+
+Three templates — one per digest format. Replace every [BRACKETED FIELD] with content from the fetched articles. Never leave bracket text in the final output. Skip sections that have no source material rather than inventing content.
+
+---
+
+## Template 1: Weekly Roundup
+
+```html
+<h2>This Week in [INDUSTRY/TOPIC]</h2>
+<p>[ONE SENTENCE capturing the week's theme or dominant story. Specific, not generic.]</p>
+
+<h2>Top Story</h2>
+<h3><a href="[ARTICLE_URL]">[ARTICLE_TITLE]</a></h3>
+<p>[100-150 word summary of the most significant story this week. Include one specific data point or quote directly from the article. No invented statistics.] <a href="[ARTICLE_URL]">[SOURCE_NAME]</a></p>
+
+<h2>Also Worth Reading</h2>
+
+<h3><a href="[ARTICLE_2_URL]">[ARTICLE_2_TITLE]</a></h3>
+<p>[40-60 word summary. Key insight from the article.] <a href="[ARTICLE_2_URL]">[SOURCE_2_NAME]</a></p>
+
+<h3><a href="[ARTICLE_3_URL]">[ARTICLE_3_TITLE]</a></h3>
+<p>[40-60 word summary. Key insight from the article.] <a href="[ARTICLE_3_URL]">[SOURCE_3_NAME]</a></p>
+
+<h3><a href="[ARTICLE_4_URL]">[ARTICLE_4_TITLE]</a></h3>
+<p>[40-60 word summary. Key insight from the article.] <a href="[ARTICLE_4_URL]">[SOURCE_4_NAME]</a></p>
+
+<h2>Quick Takes</h2>
+<ul>
+  <li><a href="[ARTICLE_5_URL]">[ARTICLE_5_TITLE]</a> — [One-line summary.]</li>
+  <li><a href="[ARTICLE_6_URL]">[ARTICLE_6_TITLE]</a> — [One-line summary.]</li>
+  <li><a href="[ARTICLE_7_URL]">[ARTICLE_7_TITLE]</a> — [One-line summary.]</li>
+</ul>
+
+<p>[1-2 sentence closing. No CTA filler. No "see you next week".]</p>
+```
+
+Worked example:
+
+```html
+<h2>This Week in Developer Tools</h2>
+<p>A major npm supply chain incident and two new runtime releases dominated developer news.</p>
+
+<h2>Top Story</h2>
+<h3><a href="https://blog.npmjs.org/post/supply-chain">npm Detects Malicious Package Injecting Crypto Miner</a></h3>
+<p>The npm security team removed 47 packages after discovering a supply chain attack targeting Node.js build environments. The packages had been downloaded 2.3 million times before detection. The attack injected a crypto miner into postinstall scripts. npm is rolling out mandatory provenance attestation for all new package versions by June 2026. <a href="https://blog.npmjs.org/post/supply-chain">npm Blog</a></p>
+
+<h2>Also Worth Reading</h2>
+
+<h3><a href="https://bun.sh/blog/bun-1.2">Bun 1.2 Ships with Built-In S3 and SQL Support</a></h3>
+<p>Bun 1.2 adds first-party APIs for S3 storage and SQL databases without any npm packages. The release also brings a 20% startup time improvement. <a href="https://bun.sh/blog/bun-1.2">Bun Blog</a></p>
+
+<h2>Quick Takes</h2>
+<ul>
+  <li><a href="https://nodejs.org/en/blog/release/v22.14.0">Node.js 22.14.0 Released</a> — Minor patch with V8 12.4 backports and a fix for the http2 memory leak.</li>
+  <li><a href="https://deno.com/blog/deno-2.2">Deno 2.2 Adds WebGPU Compute Shaders</a> — First runtime to support GPU compute from server-side JavaScript.</li>
+</ul>
+
+<p>Four feeds, 34 articles, one interesting week.</p>
+```
+
+---
+
+## Template 2: Topic Deep Dive
+
+```html
+<h2>The Big Picture</h2>
+<p>[80-100 words on why this topic is significant this week. Ground in specific events, not general claims. One data point from a source.]</p>
+
+<h2>[DEVELOPMENT_1_HEADING]</h2>
+<h3><a href="[ARTICLE_URL]">[ARTICLE_TITLE]</a></h3>
+<p>[80-100 word summary. Specific facts, no invented details.] <a href="[ARTICLE_URL]">[SOURCE_NAME]</a></p>
+
+<h2>[DEVELOPMENT_2_HEADING]</h2>
+<h3><a href="[ARTICLE_URL]">[ARTICLE_TITLE]</a></h3>
+<p>[80-100 word summary.] <a href="[ARTICLE_URL]">[SOURCE_NAME]</a></p>
+
+<h2>[DEVELOPMENT_3_HEADING]</h2>
+<h3><a href="[ARTICLE_URL]">[ARTICLE_TITLE]</a></h3>
+<p>[80-100 word summary.] <a href="[ARTICLE_URL]">[SOURCE_NAME]</a></p>
+
+<h2>What to Watch</h2>
+<ul>
+  <li>[Next development to follow, grounded in current events.]</li>
+  <li>[Second thing to watch.]</li>
+  <li>[Third thing to watch.]</li>
+</ul>
+
+<h2>This Week's Sources</h2>
+<ul>
+  <li><a href="[URL_1]">[TITLE_1]</a> — [SOURCE_NAME_1]</li>
+  <li><a href="[URL_2]">[TITLE_2]</a> — [SOURCE_NAME_2]</li>
+</ul>
+```
+
+---
+
+## Template 3: Curated Picks
+
+```html
+<h2>This Week's Picks</h2>
+<p>[One sentence framing the selection — what connects these picks or what made them stand out.]</p>
+
+<h3>1. <a href="[ARTICLE_1_URL]">[ARTICLE_1_TITLE]</a></h3>
+<p>[30-40 word description. Key takeaway.]</p>
+<p><strong>Why read it:</strong> [One sentence. Specific reason.] <a href="[ARTICLE_1_URL]">[SOURCE_1_NAME]</a></p>
+
+<h3>2. <a href="[ARTICLE_2_URL]">[ARTICLE_2_TITLE]</a></h3>
+<p>[30-40 word description. Key takeaway.]</p>
+<p><strong>Why read it:</strong> [One sentence. Specific reason.] <a href="[ARTICLE_2_URL]">[SOURCE_2_NAME]</a></p>
+
+<h3>3. <a href="[ARTICLE_3_URL]">[ARTICLE_3_TITLE]</a></h3>
+<p>[30-40 word description.]</p>
+<p><strong>Why read it:</strong> [One sentence.] <a href="[ARTICLE_3_URL]">[SOURCE_3_NAME]</a></p>
+
+<h3>4. <a href="[ARTICLE_4_URL]">[ARTICLE_4_TITLE]</a></h3>
+<p>[30-40 word description.]</p>
+<p><strong>Why read it:</strong> [One sentence.] <a href="[ARTICLE_4_URL]">[SOURCE_4_NAME]</a></p>
+
+<h3>5. <a href="[ARTICLE_5_URL]">[ARTICLE_5_TITLE]</a></h3>
+<p>[30-40 word description.]</p>
+<p><strong>Why read it:</strong> [One sentence.] <a href="[ARTICLE_5_URL]">[SOURCE_5_NAME]</a></p>
+```
+
+---
+
+## Fill-in Rules
+
+1. Replace every [BRACKETED FIELD] with content from the fetched articles
+2. Never leave bracket text in the output
+3. Every URL must be an absolute URL (starts with `https://`)
+4. Every non-obvious claim needs a linked source attribution
+5. Skip a section if there is no source material for it
+6. Check word count before presenting — see references/digest-format.md for targets
+7. Do not use markdown in HTML output; do not use HTML tags in Markdown output
+8. Write the Markdown version after the HTML version by converting heading tags and links

package/skills/newsletter-digest/scripts/fetch-feeds.js

@@ -0,0 +1,141 @@
+#!/usr/bin/env node
+/**
+ * fetch-feeds.js
+ * Fetches RSS/Atom feeds, filters by date window, deduplicates, and saves to JSON.
+ *
+ * Usage:
+ *   node fetch-feeds.js              # Default: last 7 days
+ *   node fetch-feeds.js --days=14    # Extend window to 14 days
+ *
+ * Output: /tmp/newsletter-digest-articles.json
+ */
+
+import Parser from 'rss-parser';
+import { readFileSync, writeFileSync } from 'fs';
+import { fileURLToPath } from 'url';
+import { dirname, join } from 'path';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+
+// Parse CLI args
+const args = process.argv.slice(2);
+const daysArg = args.find(a => a.startsWith('--days='));
+const DAYS = daysArg ? parseInt(daysArg.split('=')[1], 10) : 7;
+const OUTPUT_PATH = '/tmp/newsletter-digest-articles.json';
+const FEEDS_PATH = join(__dirname, '..', 'feeds.json');
+
+async function main() {
+  // Load feeds config
+  let feeds;
+  try {
+    feeds = JSON.parse(readFileSync(FEEDS_PATH, 'utf8'));
+  } catch (err) {
+    console.error(`ERROR: Could not read feeds.json at ${FEEDS_PATH}`);
+    console.error('Create feeds.json with this format:');
+    console.error('[{"url": "https://example.com/feed", "name": "Source Name"}]');
+    process.exit(1);
+  }
+
+  if (!Array.isArray(feeds) || feeds.length === 0) {
+    console.error('ERROR: feeds.json is empty or not an array.');
+    process.exit(1);
+  }
+
+  const cutoffDate = new Date();
+  cutoffDate.setDate(cutoffDate.getDate() - DAYS);
+
+  const parser = new Parser({
+    timeout: 10000,
+    headers: { 'User-Agent': 'newsletter-digest-skill/1.0' },
+    customFields: {
+      item: ['summary', 'description', 'content:encoded', 'media:content'],
+    },
+  });
+
+  const allArticles = [];
+  const seenUrls = new Set();
+  const feedsSummary = [];
+
+  for (const feed of feeds) {
+    if (!feed.url || !feed.name) {
+      console.warn(`WARN: Skipping malformed feed entry: ${JSON.stringify(feed)}`);
+      continue;
+    }
+
+    let parsed;
+    try {
+      console.log(`Fetching: ${feed.name} (${feed.url})`);
+      parsed = await parser.parseURL(feed.url);
+    } catch (err) {
+      console.warn(`WARN: Failed to fetch ${feed.name}: ${err.message}`);
+      feedsSummary.push({ name: feed.name, count: 0, error: err.message });
+      continue;
+    }
+
+    let feedCount = 0;
+    for (const item of parsed.items) {
+      const pubDate = item.pubDate || item.isoDate;
+      if (!pubDate) continue;
+
+      const publishedAt = new Date(pubDate);
+      if (isNaN(publishedAt.getTime())) continue;
+      if (publishedAt < cutoffDate) continue;
+
+      const url = item.link || item.guid;
+      if (!url || seenUrls.has(url)) continue;
+      seenUrls.add(url);
+
+      // Extract the best available summary
+      const content =
+        item['content:encoded'] ||
+        item.content ||
+        item.summary ||
+        item.description ||
+        '';
+
+      // Strip HTML tags for plain text excerpt
+      const plainText = content.replace(/<[^>]*>/g, ' ').replace(/\s+/g, ' ').trim();
+      const excerpt = plainText.slice(0, 400) + (plainText.length > 400 ? '...' : '');
+
+      allArticles.push({
+        title: item.title || 'Untitled',
+        url,
+        source: feed.name,
+        publishedAt: publishedAt.toISOString(),
+        author: item.author || item.creator || '',
+        excerpt,
+      });
+      feedCount++;
+    }
+
+    feedsSummary.push({ name: feed.name, count: feedCount });
+    console.log(`  Found ${feedCount} articles in the last ${DAYS} days`);
+  }
+
+  // Sort newest first
+  allArticles.sort((a, b) => new Date(b.publishedAt) - new Date(a.publishedAt));
+
+  const output = {
+    fetchedAt: new Date().toISOString(),
+    daysWindow: DAYS,
+    dateRange: {
+      from: cutoffDate.toISOString(),
+      to: new Date().toISOString(),
+    },
+    articles: allArticles,
+    feedsSummary,
+  };
+
+  writeFileSync(OUTPUT_PATH, JSON.stringify(output, null, 2));
+
+  console.log(`\nDone. ${allArticles.length} articles saved to ${OUTPUT_PATH}`);
+  feedsSummary.forEach(f => {
+    const status = f.error ? `ERROR: ${f.error}` : `${f.count} articles`;
+    console.log(`  ${f.name}: ${status}`);
+  });
+}
+
+main().catch(err => {
+  console.error('Unexpected error:', err);
+  process.exit(1);
+});

package/skills/newsletter-digest/scripts/ghost-publish.js

@@ -0,0 +1,147 @@
+#!/usr/bin/env node
+/**
+ * ghost-publish.js
+ * Publishes the newsletter digest to Ghost CMS via Admin API.
+ *
+ * Usage:
+ *   node ghost-publish.js --title "Weekly Digest: Apr 7-14" --status draft
+ *   node ghost-publish.js --title "Weekly Digest: Apr 7-14" --status published
+ *
+ * Reads digest content from: /tmp/newsletter-digest-output.json
+ * Required env vars: GHOST_URL, GHOST_ADMIN_KEY
+ *
+ * GHOST_ADMIN_KEY format: "key_id:secret" (from Ghost Admin > Settings > Integrations)
+ */
+
+import jwt from 'jsonwebtoken';
+import { readFileSync } from 'fs';
+
+const OUTPUT_PATH = '/tmp/newsletter-digest-output.json';
+
+function generateToken(adminKey) {
+  const [id, secret] = adminKey.split(':');
+  if (!id || !secret) {
+    throw new Error('GHOST_ADMIN_KEY must be in format "key_id:secret"');
+  }
+  // Ghost requires the secret as binary (hex-decoded), signed with HS256
+  return jwt.sign({}, Buffer.from(secret, 'hex'), {
+    keyid: id,
+    algorithm: 'HS256',
+    expiresIn: '5m',
+    audience: '/admin/',
+  });
+}
+
+async function main() {
+  const args = process.argv.slice(2);
+  const titleArg = args.find(a => a.startsWith('--title='));
+  const statusArg = args.find(a => a.startsWith('--status='));
+
+  const title = titleArg ? titleArg.split('=').slice(1).join('=') : null;
+  const status = statusArg ? statusArg.split('=')[1] : 'draft';
+
+  if (!title) {
+    console.error('ERROR: --title is required');
+    process.exit(1);
+  }
+
+  if (!['draft', 'published'].includes(status)) {
+    console.error('ERROR: --status must be "draft" or "published"');
+    process.exit(1);
+  }
+
+  const ghostUrl = process.env.GHOST_URL;
+  const adminKey = process.env.GHOST_ADMIN_KEY;
+
+  if (!ghostUrl) {
+    console.error('ERROR: GHOST_URL is not set');
+    process.exit(1);
+  }
+  if (!adminKey) {
+    console.error('ERROR: GHOST_ADMIN_KEY is not set');
+    process.exit(1);
+  }
+
+  // Read digest content
+  let digestOutput;
+  try {
+    digestOutput = JSON.parse(readFileSync(OUTPUT_PATH, 'utf8'));
+  } catch (err) {
+    console.error(`ERROR: Could not read digest output at ${OUTPUT_PATH}`);
+    console.error('The agent must write the digest to this file before running ghost-publish.js');
+    process.exit(1);
+  }
+
+  const html = digestOutput.html;
+  if (!html) {
+    console.error('ERROR: digest output JSON does not contain an "html" field');
+    process.exit(1);
+  }
+
+  // Generate JWT token
+  let token;
+  try {
+    token = generateToken(adminKey);
+  } catch (err) {
+    console.error(`ERROR: Failed to generate Ghost JWT: ${err.message}`);
+    process.exit(1);
+  }
+
+  // Build Ghost API URL (strip trailing slash)
+  const baseUrl = ghostUrl.replace(/\/$/, '');
+  const apiUrl = `${baseUrl}/ghost/api/admin/posts/?source=html`;
+
+  const payload = {
+    posts: [
+      {
+        title,
+        html,
+        status,
+      },
+    ],
+  };
+
+  // POST to Ghost Admin API
+  let response;
+  try {
+    const res = await fetch(apiUrl, {
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+        Authorization: `Ghost ${token}`,
+      },
+      body: JSON.stringify(payload),
+    });
+
+    response = await res.json();
+
+    if (!res.ok) {
+      console.error('Ghost API error:', JSON.stringify(response, null, 2));
+      process.exit(1);
+    }
+  } catch (err) {
+    console.error(`ERROR: Network request to Ghost failed: ${err.message}`);
+    process.exit(1);
+  }
+
+  const post = response.posts?.[0];
+  if (!post) {
+    console.error('ERROR: Ghost did not return a post object');
+    console.error(JSON.stringify(response, null, 2));
+    process.exit(1);
+  }
+
+  console.log(`\nPost created successfully.`);
+  console.log(`  Status:   ${post.status}`);
+  console.log(`  Title:    ${post.title}`);
+  console.log(`  Slug:     ${post.slug}`);
+  console.log(`  Admin URL: ${baseUrl}/ghost/#/editor/post/${post.id}`);
+  if (post.status === 'published') {
+    console.log(`  Public URL: ${post.url}`);
+  }
+}
+
+main().catch(err => {
+  console.error('Unexpected error:', err);
+  process.exit(1);
+});

package/skills/noise2blog/.env.example

@@ -0,0 +1,16 @@
+# noise2blog — Environment Variables
+# =====================================
+# The agent writes the blog post — no separate backend needed.
+# Only Gemini is required. Tavily is optional for research enrichment.
+
+# Required: Google Gemini API key
+# Get it: aistudio.google.com → Get API key → Create API key
+# Free tier available (rate-limited). Paid tier for higher volume.
+GEMINI_API_KEY=your_gemini_api_key_here
+
+# Optional: Tavily API key (for research enrichment)
+# When set, the agent searches for supporting data to verify claims in your raw content.
+# Without this, the blog post is based entirely on what you provide — which is fine for
+# personal stories, experience-based tutorials, and opinion posts.
+# Get it: app.tavily.com → API Keys
+TAVILY_API_KEY=your_tavily_api_key_here

package/skills/noise2blog/README.md

@@ -0,0 +1,107 @@
+# noise2blog
+
+<img width="1280" height="640" alt="noise2blog" src="https://github.com/user-attachments/assets/2359cff9-dfd4-4276-bb3e-4b6091ad6983" />
+
+
+Paste your rough notes, bullet points, voice transcript, or tweet dump and get a publication-ready blog post.
+
+## What It Does
+
+- Accepts any rough input: bullet points, rough notes, voice transcripts, tweet dumps, short drafts, or a URL
+- Detects the right blog post style automatically (Technical Tutorial, Case Study, Thought Leadership, Explainer)
+- Enriches claims with Tavily research when you set an API key (supporting data, verification)
+- Generates a Markdown post with no AI slop, no em dashes, no banned words
+- Formats frontmatter for Ghost, dev.to, Substack, or Hashnode on request
+
+## Requirements
+
+| Requirement | Purpose | How to Set Up |
+|------------|---------|--------------|
+| Google Gemini API key | Generates the blog post | aistudio.google.com, Get API key |
+| Tavily API key (optional) | Enriches claims with research | app.tavily.com, API Keys |
+
+No LLM backend to run. The agent calls the Gemini API directly.
+
+## Setup
+
+```bash
+cp .env.example .env
+```
+
+Edit `.env` and fill in:
+- `GEMINI_API_KEY` (required)
+- `TAVILY_API_KEY` (optional, enables research enrichment)
+
+## Blog Post Styles
+
+| Style | Use When | Signals in Your Input |
+|-------|----------|----------------------|
+| Technical Tutorial | Step-by-step guide, code walkthrough | Numbered steps, commands, "how to" |
+| Case Study | Build log, before/after story, lessons learned | Specific results, journey narrative |
+| Thought Leadership | Opinion piece, counterintuitive argument | Strong claim, debate framing |
+| Explainer | Explaining a concept or tool to newcomers | Definition-first, comparisons |
+
+The agent detects the style automatically. Override it with: "Use Thought Leadership style" or "Make this a tutorial".
+
+## How to Use
+
+From pasted notes:
+
+```
+"Write a blog post from these notes: [paste your content]"
+"Turn these bullet points into a blog post"
+"Expand this into an article"
+```
+
+From a voice transcript:
+
+```
+"Turn this transcript into a blog post: [paste transcript]"
+"Clean up this voice note and make it publishable"
+```
+
+From a tweet thread:
+
+```
+"Turn this tweet thread into a blog: [paste tweets]"
+"Expand this thread into a full article"
+```
+
+With style override:
+
+```
+"Write a thought leadership post from these notes"
+"Make this a technical tutorial"
+```
+
+With platform formatting:
+
+```
+"Write the post and format it for dev.to"
+"Give me Ghost frontmatter too"
+```
+
+## Output
+
+- Full blog post in Markdown (800-1,800 words)
+- Meta description (1-2 sentences)
+- Alternative title option
+- Platform-specific frontmatter on request
+
+## Project Structure
+
+```
+noise2blog/
+├── SKILL.md
+├── README.md
+├── .env.example
+├── evals/
+│   └── evals.json
+└── references/
+    ├── blog-format.md
+    └── output-template.md
+```
+
+## License
+
+MIT