Drop in a recorded podcast episode and get back an AEO-optimized blog post that keeps your spoken voice word for word. On first run it wires into your podcast host, your blog, and your language, then runs your version every time after.
← All Claude SkillsYou pour real thinking into every episode, and most of it stays locked in audio where search engines and answer engines cannot read it. This skill turns each episode into a blog post that reads like you talking and gets found. The first time you run it, it interviews you and designs itself into your world: your podcast host, where your blog lives, your voice and signature phrases, and where you track content. Every run after that, it just works. Copy the two blocks below and give them to your Claude.
Step 1. Copy the skill block below.
Step 2. Open Claude and paste this instruction first, then paste the block underneath it:
Turn the block below into a Claude skill and install it. Create the skill file exactly as written. Then personalize it with smart defaults from what you know about me: my business, my voice, my current priorities, and where I keep my work. Confirm when it is installed and tell me how to run it.
--- name: podcast-to-blog description: Turn any recorded podcast episode into an AEO-optimized, publish-ready blog post that keeps your spoken voice word for word. On first run the skill interviews you to wire in your podcast host, your blog, and your language, then runs your version every time after. Use whenever you say "podcast to blog," "turn this episode into a blog post," "publish episode [number] as a post," or drop an episode transcript and want it turned into a post. --- # Podcast to Blog: Episode Intelligence Publisher Turn a recorded podcast episode into an AEO-optimized blog post that reads like you talking, structured for how people ask AI. Every post keeps your spoken voice, answers one clear question better than anything else on the internet, and passes an AEO audit before it ships. This is your episode, structured to get found and cited. ## First Run: Design Your Version The first time you run this skill, set it up. Ask me these questions one at a time, save my answers into this skill file as a CONFIG block, and use them on every run after this. If the answers are already saved, skip straight to the workflow. 1. What do you use to host and record your podcast, and how do you get transcripts? (Zoom, Riverside, Descript, a transcription tool, or a transcript you paste.) This tells me how to get the episode text. 2. Where does your blog live, and how does it publish? (WordPress, Ghost, Webflow, a static site in a git repo, or a CMS.) This is where the finished post lands and how it goes live. 3. Whose voice should the post be written in, and which signature phrases should stay word for word? Name the host and list the phrases to preserve. This keeps the post in your own spoken voice. 4. Where do you track your episodes and content? (A Notion database, a spreadsheet, a content calendar, or a folder.) This is where I read the episode from and mark it published. 5. What is your podcast called? I use this in the episode attribution line at the bottom of every post. If I ever say "redesign podcast to blog," run this interview again. ## Input - An episode name or number from wherever you track content (I pull the transcript) - A pasted transcript - "Publish the next episode in my queue" (I find the next episode marked ready) ## Workflow ### Step 1: Get the Episode Pull the transcript from the host or tracker you set up, or use the one you paste. Grab the episode title, number, publish date, audio URL, description, and any keyphrases already mapped. If the transcript is empty or the episode is not marked ready, skip it and move to the next one. ### Step 2: Find the One Big Idea Read the full transcript. Identify the single most valuable idea by answering this question: "What is the single question this episode answers better than anything else on the internet?" That question becomes the angle for the whole post. Everything else in the transcript is supporting material. Pick the idea with the highest combination of specificity, actionability, and searchability. A named framework the host teaches wins first. A concrete, do-it-now insight wins next. A mindset shift that reframes the topic wins after that. A story carrying a clear lesson wins last. When several strong ideas compete, choose the one a listener would actually type into AI. ### Step 3: Preserve the EEAT Voice This is the part that makes the post impossible to fake. From the transcript, pull and keep: - Exact phrases and signature language the host uses, word for word - Specific stories and moments, with real names and identifiers removed - Real numbers and data points the host cites - Analogies the host uses to make hard ideas simple - Challenge language where the host speaks straight to the listener Use these as close to spoken as possible while they fit a written post. Do not paraphrase the host's raw language into polished prose. The spoken words are the content. The structure organizes the thinking. It never replaces the voice. ### Step 4: Write the Post Follow this template exactly. Every element is required. **Title (H1)** - Include the primary keyphrase naturally - Refine the episode title if a cleaner version reads better - Conversational. A question or a bold statement both work. - Skip colon-based titles **Key Takeaways Block** - 3-5 bullets summarizing the key takeaways, placed right after the title and date - These are the first 200 words AI reads, so make them count - Each bullet is a standalone insight that delivers value on its own **Opening (3 sentences max)** - Lead with what the reader gets: the framework, the insight, the actionable thing - Skip the backstory about the show or the episode - Within 3 sentences the reader knows exactly what this post delivers and why it matters to them - Open with a confident declaration that stakes a position **Question-Based H2 Sections (4-6)** - Each H2 is phrased as a question someone would ask AI - CRITICAL: a bold direct answer leads the first 1-2 sentences after every H2. This is what AI extracts for citations. Give the definitive answer in bold before any story or depth. - Then go deep with the host's stories, exact spoken language from the transcript, specific examples, and steps - Each section stands alone. If AI pulls only this section, it fully answers the H2 question. **H3 Sub-sections (where the framework needs them)** - If the episode teaches a framework with named parts, each part gets its own H3 with real depth - Use the host's transcript language for each one **Closing Section** - One H2 like "Where Do You Start?" with a bold direct answer - Specific actions the reader can take this week - Pull the host's exact challenge language from the transcript if they gave one **Episode Attribution Line** Always end the body with a line like: *This post is adapted from Episode [NUMBER] of [your podcast name]. [Listen to the full episode here.](AUDIO_URL)* ### Step 5: Score Against the AEO Audit Scorecard Score the draft against all 25 criteria. Total: 100 points. Target: 85+. **AEO Structure (25 points)** - Question-based H2 headings matching real search queries (5 pts) - Bold direct answer leading every H2, within the first 40 words (5 pts) - Key takeaways or summary at the top (5 pts) - Clear hierarchy with proper H1, H2, H3 tags (5 pts) - 1,500+ words of substantive content (5 pts) **EEAT Signals (30 points)** - First-person lived experience with real stories (6 pts) - Specific examples with real numbers and data (6 pts) - Original frameworks or methodology referenced (6 pts) - Real conversations, anonymized (6 pts) - Depth of expertise evident throughout (6 pts) **Answer Engine Extractability (20 points)** - Standalone sections that fully answer the H2 question (4 pts) - Actionable steps the reader can take right away (4 pts) - Natural keyphrase integration, never stuffed (4 pts) - Conversational tone matching how people ask AI (4 pts) - Primary question answered within the first 200 words (4 pts) **Content Differentiation (15 points)** - Original insight not available elsewhere (3 pts) - Specific data or receipts (3 pts) - Unique analogies or explanations (3 pts) - Clear actionable takeaway (3 pts) - Voice authenticity, sounds like the host and not like AI (3 pts) **Technical AEO Readiness (10 points)** - Title includes the primary keyphrase (2 pts) - Meta description under 160 characters (2 pts) - 3-5 internal links with descriptive anchor text (2 pts) - Evergreen angle that stays relevant (2 pts) - No filler paragraphs (2 pts) **Scoring thresholds:** - 85+ proceeds to publish - 65-84 upgrades the weakest categories and re-scores before publishing - Below 65 rewrites the weakest sections, then re-scores Do not publish below 85. Fix the weakest areas and re-score first. ### Step 6: Generate Meta Data - Slug: lowercase, hyphens, derived from the title - Meta description: under 160 characters, answering the core question of the post - Category: pick the one that fits the content ### Step 7: Publish Create the post in whatever format your blog uses, matching your existing post structure. Include: - Article schema markup (JSON-LD) with author, date, headline, description - FAQ schema built from the H2 question headers - Key takeaways styled as a summary callout box - Proper H1, H2, H3 hierarchy - Open Graph and Twitter Card tags with an image if a thumbnail exists Add the post to your blog listing as the newest entry. Use clean, lowercase, hyphenated slugs and publish it the way your platform ships posts live. ### Step 8: Internal Linking After the post is live, read your existing posts and add 3-5 natural inline links from the new post to relevant older ones, with conversational anchor text. Then find 2-3 older posts where a link back to this new post fits, and add one link each. Only link where the topic genuinely connects. Never duplicate a link already in the post. ### Step 9: Mark It Tracked Update the entry wherever you track content: set the status to published, save the live URL, and store the title, meta description, and primary keyphrase. ## Voice Rules Write in the voice you set up in first run. Warm, direct, action-oriented, spoken straight to the reader as "you." - Short to medium sentences. Break lines often. One-sentence paragraphs for emphasis. - Rhythm: short, short, then a longer sentence that lands the point, then short again. - Talk to the reader with "you" and turn every lesson toward them. - Skip jargon. Explain hard things through simple, punchy analogies. - Preserve the host's signature phrases word for word, straight from the transcript. - Never start a sentence with "And." - Never use "Here's the truth," "Here's the thing," or "Here's what I know." - Never smooth the host's raw language into generic prose. Their actual words are the content. - Never fabricate stories or details that were not in the transcript. - Never use these words: delve, unlock, craft, foster, tapestry, embarking, unleash, unveil, realm, boasts, revolutionize, tenets. - No semicolons, no em dashes, no contrastive framing. The EEAT principle: the transcript language is the gold. The host's exact phrases, analogies, stories, and explanations are what content farms cannot copy. Preserve them. The post structures the thinking. It never replaces the voice. ## Quality Gate Before any post goes live, verify: - AEO score is 85+ - A bold direct answer leads every H2 - The key takeaways block has 3-5 bullets - The opening tells the reader what they get within 3 sentences - The host's actual transcript language is preserved word for word - At least 2 specific stories or moments from the transcript are included - At least 3 internal links to existing posts - Meta description is under 160 characters - The episode attribution line sits at the bottom with the audio link - The slug is lowercase, hyphens only - Article schema and FAQ schema are in the post - The blog listing is updated - The tracked entry is marked published with the live URL
Claude reads the block, builds the skill file, and installs it. From then on, you just run the skill in any conversation. No folders to find, no code to write.
Every week you see what's working, build it live, and put it to work in your business.
Here's the shape of what this skill hands you when it runs. Copy it, use it, keep moving.
You don't need to hold any of this in your head. That's the skill's job. If you're curious what it's doing for you, here's the idea underneath it.
Your best thinking lives inside episodes, and audio is a place search engines and answer engines cannot read. The value was real. It just had nowhere findable to live. Podcast to Blog gives it a home built for how people ask AI, with your spoken voice kept word for word. An episode becomes a page that gets cited.
The first time you run it, the skill interviews you and wires into your podcast host, your blog, your voice, and where you track content. Every run after that just works.
It reads the full episode and answers one question: what this episode answers better than anything else online. That becomes the angle, and everything else supports it.
The EEAT pass pulls your exact phrases, stories, and analogies straight from the transcript and keeps them word for word. The post sounds like you talking.
Every section is a question a person would ask AI, led by a bold direct answer AI can lift and cite. Each section stands alone and fully answers its question.
A 100-point scorecard checks structure, EEAT signals, extractability, differentiation, and technical readiness. A post under 85 gets upgraded and re-scored first.
It reads the full transcript and answers one question: what is the single question this episode answers better than anything else on the internet. That question becomes the angle for the whole post, and everything else in the episode becomes supporting material. It ranks candidates by specificity, actionability, and searchability, so a named framework you teach wins over a broad idea, and a concrete do-it-now insight wins over a vague one. The winner is the idea a listener would actually type into AI.
This is the EEAT preservation pass, and it is the part that makes your post impossible for a content farm to copy. Before writing, the skill pulls your exact phrases, signature language, stories, real numbers, and analogies straight from the transcript and keeps them word for word. It never smooths your raw language into polished prose, so the post reads like you talking, in your own words. The structure organizes the thinking. Your spoken words stay the content.
The AEO audit scorecard is a 100-point check across five areas: AEO structure, EEAT signals, answer engine extractability, content differentiation, and technical readiness. The skill scores every draft against all 25 criteria and targets 85 or higher before anything ships. A draft under 85 gets its weakest categories upgraded and re-scored, and a draft under 65 gets its weakest sections rewritten. The scorecard is why a post reads well for a human and gets cited by an answer engine.