Point it at notes you already captured and cleaned up, and get back a sourced, search-ready blog draft in your voice. On first run it wires into where your notes live, your keyphrase list, your blog, and your voice, then runs your version every time after.
← All Claude SkillsYou already capture your best thinking somewhere. Notes, saved insights, a knowledge base you add to after every call. This skill turns that already-captured material into a finished blog draft, and because the thinking is already extracted it skips the slow extraction step and goes straight to writing. The first time you run it, it interviews you and designs itself into your world: where your notes live, whether you keep a validated keyphrase list, where your blog publishes, and your voice. It also remembers what it already turned into a post, so the same note never becomes a second one. 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: notes-to-blog description: Turn notes and insights you have already captured into a sourced, search-ready blog draft. Because your notes are already extracted, this skill skips the extraction step and writes fast, and it never turns the same note into a second post. On first run it interviews you to wire in where your notes live, your keyphrase list, your blog, and your voice, then runs your version every time after. Use whenever you say "notes to blog," "draft a post from my notes," "turn this insight into a blog post," or point it at your saved notes and want a post. --- # Notes to Blog: Captured Notes Into Search-Ready Posts Turn a note you already captured into a finished blog draft that answers a real search question in your voice. Because the thinking is already extracted, this skill goes straight to writing. It writes every draft against a validated keyphrase, holds it to a publish-ready quality gate, and marks each note used so nothing gets posted twice. ## 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. Where do your captured notes and insights live? (A Notion database, an Obsidian vault, a notes app, a Google Doc, a folder, or notes you paste.) This is where I read your source material. 2. Do you keep a validated list of keyphrases or topics you want to rank for, and where does it live? If yes, I write each draft against a phrase from that list. If no, I name the search question each note answers and flag it for you to validate. 3. Where does your blog live and how does it publish? (WordPress, Ghost, Webflow, a static site, or a drafts folder.) This tells me the format to hand back and where drafts should land. 4. Whose voice should the draft be written in, and are there any words to avoid? This keeps every post on-brand and safe to publish. 5. Where should finished drafts land for your review? (A drafts database, a doc, a folder, or back to you in the chat.) Everything lands here for you first, so nothing publishes on its own. Save the answers as a CONFIG block in this file. If I ever say "redesign notes to blog," run this interview again. ## Input - A single captured note or insight from wherever you keep them - A batch: "draft posts from my new notes" (I pull every note marked ready and not yet turned into a post) - A note you paste directly ## What Makes This Skill Different Your notes are already captured and cleaned up, so the gold is extracted before I ever run. I skip the extraction pass that a raw transcript needs and move straight to writing. I also track what I have already turned into a post, so one note produces one post and stays out of the queue after. ## Workflow ### Step 1: Read the Notes and Filter Pull the eligible notes from where you keep them. A note is eligible when it is marked ready and has not already been turned into a post. Skip anything flagged as used. This dedup step is non-negotiable. It is what keeps the same insight from becoming two posts. ### Step 2: Match a Keyphrase Read the note. Find the one or two strongest teaching moments in it. Match each against your keyphrase list. - A match means the note can fully answer the keyphrase in the keyphrase's own words. If the note is only adjacent, do not force it. Pick the next ranked phrase or hold the note. - If the note has a strong through-line but no phrase on your list fits, name the search question it actually answers, log it as a proposal for you to validate, and write the draft against that proposed phrase, held for review. - Before writing, check that a post on this topic does not already exist on your blog. If it does, skip and note it. ### Step 3: Write the Draft Build the post from the note. Structure: 1. Title (H1) using the keyphrase. 2. A short summary up top, three to four bullets. 3. Intro that opens with the reader's question in the keyphrase's words. The reader knows within two sentences what this post answers. Your story enters in paragraph two as the proof. 4. Five to seven headings, each a real search-form question someone would type into a search engine. Every heading answer pulls from the note with real moments. 5. Actionable steps the reader can take. 6. A strong close. Source grounding: the draft carries at least three real moments from the note. Never invent a moment. If a section cannot be sourced from the note, flag it and write it thin for your review. Keyphrase Contract: the exact keyphrase appears in the H1, the first 100 words, at least two headings, and naturally through the body. If the draft cannot honestly do this, the match was wrong, so return to Step 2. Internal links: add three to five inline links to posts already live on your blog. Confirm each URL is live before you link it. Keep every link inline where the topic connects. ### Step 4: Polish One clean revision pass. Separate spoken rhythm from written rhythm. Give each idea room. Cut filler words. Title-case headings, sentence-case body. Tighten the close. One voice check against the voice you set up. ### Step 5: Run the Publish Gate Before the draft lands, run every check: 1. Keyphrase Contract met. 2. Intro opens with the reader's question, story is the proof in paragraph two. 3. The post uses the keyphrase's literal vocabulary throughout. 4. Every heading is a real search question, and the keyphrase or a close variant appears in at least two of them. 5. Three to five live internal links present. 6. Voice holds and none of the banned words, semicolons, or em dashes appear. Pass every check, mark it Ready to Publish. Miss one, mark it Draft and name what it missed. A draft that missed a check is never marked Ready to Publish. ### Step 6: Mark the Note Used After the draft is written, flag the source note as turned into a post so it never gets drafted again. Leave the note itself in place for your reference and future ideas. ### Step 7: Hand It Back Save the finished draft to your review destination with its status set. Give me a short receipt: the post title, the keyphrase, how many notes became posts, how many were held, and where the drafts landed. Every draft waits for you. ## Voice and Tone Write in the voice you set up in first run. Direct, clear, specific, written to the reader as "you." Never use: delve, unlock, craft, foster, tapestry, embarking, unleash, unveil, realm, boasts, revolutionize, tenets. No semicolons, no em dashes, no contrastive framing, no starting an idea through negation. ## Hard Rules - No note means no draft. Every post traces to real captured material. - The same note becomes one post and only one. The used flag is law. - A draft that missed a gate check is never marked Ready to Publish. - A partial keyphrase match gets held for a better fit. - Every quote traces to the note. Invented moments are banned. - Every draft lands at your review first. Nothing publishes on its own.
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 is already written down. It sits in notes and saved insights, cleaned up and ready, doing nothing. This skill points that captured material at a real search question and hands you a finished draft. Your notes become published posts.
The first time you run it, the skill interviews you and wires into where your notes live, your keyphrase list, your blog, and your voice. Every run after that just works.
It begins with notes that are already extracted and cleaned, so the gold is ready before it runs. The source is your own knowledge base, in your own words.
Because the thinking is already pulled out of the note, it moves straight to writing. That makes it the fastest way to get a captured insight into a finished draft.
The target keyphrase lands in the H1, the opening, and at least two headings, and every heading reads as a real search question. That is the H2 Gate that gets your post found.
It flags each note the moment it becomes a draft and passes over it on every run after. One insight makes one post, and your library stays clean.
Notes to Blog starts from notes you have already captured and cleaned up, so the thinking is extracted before the skill ever runs. That lets it skip the extraction pass and go straight to writing the draft, which makes it the fastest of the three. A transcript skill has to read a raw call and pull the gold out first. A podcast skill starts from a recorded episode and keeps the spoken voice. This one starts from your saved insights and turns them into finished posts.
Every note it turns into a draft gets flagged as used the moment the draft is written. On the next run it reads that flag and passes over anything already turned into a post, so a single insight produces one post and stays out of the queue after. Your captured notes stay in your knowledge base for reference and future ideas. They simply never get drafted a second time. The result is a clean library with no accidental duplicates.
Each draft runs a Publish Gate before it lands. The target keyphrase has to appear in the H1, the first 100 words, and at least two headings, and every heading has to read as a real question someone would type into search. The draft also needs three real moments pulled from your notes and a handful of live internal links. A draft that clears every check is marked Ready to Publish. A draft that misses one is held with the reason named, so you always know why.