Cindy Zhu.
Free guides
Marketing Claude

Train Claude to write your content

Hey, it's Cindy ๐ŸŒฑ You commented TRAINED, so here is the whole setup from the reel: the memory file itself and the prompts that write the hard sections for you.
btw the waitlist for AI System Club is now open! If you're keen on using AI to automate your content, video editing, job search, business or build AI agents, feel free to sign up (only if you want to hehe). Ps. the waitlist gets first dibs:)
The idea in one sentence. Stop describing your brand at the top of every chat. Write it down once in a file Claude reads automatically, then add one line to that file every time you correct a draft. The corrections compound, so after a few weeks the first draft comes back sounding like you instead of sounding like an AI wrote a caption about your industry.
step one

Pick your door

There are two ways to give Claude a permanent memory, and they are the same idea with different plumbing. Pick the one that matches where you already work. You do not need both, and neither one requires you to write code.

The Claude app: a project A project is a container with its own custom instructions and its own uploaded files. Every chat you start inside it loads that context automatically. This is the right door for almost everyone, and it works on the free plan. Your content brain goes in the custom instructions box.
Claude Code: a CLAUDE.md file If you already work in the terminal, a plain markdown file called CLAUDE.md in your project folder is read at the start of every session. Anthropic's memory docs list the exact locations: ./CLAUDE.md for one project, ~/.claude/CLAUDE.md for everything you do on that machine.
๐Ÿ’ก Same content either way. If you start in the app and move to Claude Code later, the file copies straight across with no edits.

step two

Paste the content brain

This is the file. Paste it into your project's custom instructions (or save it as CLAUDE.md), then fill in every bracket. Do not skip the "banned" section, because negative rules are the ones that visibly change the output. Twenty minutes of honest filling-in here saves you months of vague drafts.

๐Ÿ“„ the content brain, paste and fill in
# My content brain

## Who I am
I make content about [topic] for [platform]. I am [name], and the way I want to come across is [three adjectives, for example: warm, direct, a bit funny]. My handle is [@handle] and I post [how often].

## Who I am talking to
My audience is [age range, job or life stage, income bracket if relevant]. They already know [what you never need to explain to them], so never re-explain it. They do not yet know [the gap you fill]. The thing that keeps them stuck is [their real problem in their words, not marketing words]. They want [outcome], and they are afraid of [fear].

## What I believe
These are my actual positions, and my content should sound like someone who holds them:
- [opinion 1, stated strongly]
- [opinion 2, stated strongly]
- [opinion 3, stated strongly]
I disagree with the common advice that [the thing everyone in my niche says], because [reason].

## How I sound
- Sentence length: [short and punchy / longer and conversational].
- Formality: [I write like I talk / I write cleanly].
- Words I actually use: [list eight or ten of your real habits].
- I open on [a scenario / a question / a claim], never on [whatever you hate].

## Banned, non-negotiable
- No em dashes. Use commas, full stops, brackets or colons.
- No buzzwords: delve, unlock, elevate, game-changer, leverage, seamless, robust, "in today's fast-paced world".
- No "it's not X, it's Y" construction.
- No fake urgency, no fear-mongering, no promises about money I have not personally seen.
- Never accuse the viewer of being lazy, behind, or doing it wrong.
- [your own three pet peeves]

## The script template, follow this order every time
1. Hook: one line, under twelve words, second person, earns the next three seconds.
2. Value: the actual teaching. One idea, gone deep. Name real tools, never a vague category.
3. Proof: a number, a source, a screenshot, or a thing I personally did. If I have no proof, cut the claim.
4. Call to action: one ask, never two.

## Formats I post
- [format 1, for example: 45 second talking head, numbered series]
- [format 2, for example: carousel, 7 slides, cover is the promise]
- [format 3]

## My posts that worked, and why
[Paste three to five of your best-performing posts in full. Under each one, write two lines: what the hook did, and why you think it landed. The "why" is what Claude learns from, so write it even if you are guessing.]

## Lessons, append only
[Leave this empty for now. Every correction you make to a draft becomes one line here. This section is the training.]
โš ๏ธ Paste real posts, not summaries of them. "I write casual and relatable" teaches Claude nothing, because every creator believes that about themselves. Three full transcripts of things you actually published teach it your rhythm, your filler words and where you break sentences. This one difference is most of the quality gap between a setup that works and one that does not.

step three

Let your own posts write the voice section

Describing your own voice is genuinely hard, and most people get it wrong in the same direction: they describe who they want to be. Skip that and have Claude reverse-engineer it from evidence. Paste your five best posts into a fresh chat and run this.

โœ๏ธ extract my voice from my own posts
Below are [five] pieces of content I have actually published, and the ones that performed best for me. Read all of them before you answer anything.

Work out how I write, from the evidence only. I want my average sentence length, whether I use contractions, how I open, how I close, my punctuation habits, the words and phrases I return to, how formal I am on a scale of one to ten, and how I handle transitions between ideas. Quote a real line from my posts as the example for every single observation you make, so I can check you are describing me and not a generic creator.

Then tell me what my hooks have in common. Look at structure, not topic: are they questions, claims, numbers, scenarios, or second-person statements, and how many words do they run before the first pause.

Then tell me three habits I have that are actually weaknesses, with the line that shows each one. Be blunt about this, I am not looking for encouragement.

Finish by writing a "how I sound" section, in bullet points, short enough to paste into a memory file. Write it as instructions to you, not as a description of me. So "open on a relatable scenario in second person", not "Cindy is relatable".
๐Ÿ“Œ Paste the output straight into the "how I sound" section of your content brain, then read it once and delete anything that describes a version of you that does not exist yet. Aspirational voice rules produce drafts you end up rewriting.

step four

Lock one script template

The template in the file is deliberately boring, and that is the point. A fixed order is what lets you judge a draft in ten seconds: you check each beat is present and doing its job, instead of reading the whole thing and feeling vaguely unhappy. These are the four beats and the test each one has to pass.

Hook Under twelve words, second person, no wind-up. Test: if you read only this line, do you want the next one? "Here's what most people get wrong about X" fails, because it could sit on any post in any niche.
Value One idea, taken deep, with real named tools and real steps. Test: could someone act on this today without opening another tab? Three shallow tips lose to one thing explained properly.
Proof A number with a source, a screenshot, or something you personally did. Test: would you be comfortable if someone asked "where's that from?" in the comments. No proof means cut the claim, not soften it.
Call to action One ask. Test: is there exactly one thing to do. Follow and comment and save and share is four asks, which reads as zero.
๐ŸŒฑ Once the template is in the file, you can stop restating it. "Draft me three scripts on [topic]" already means "in my four-beat structure, in my voice, for my audience", because all of that is loaded before you type.

step five, the actual training

The corrections loop

Here is the part most people miss. The file you paste today is a starting point, and it is worth maybe a third of the eventual quality. What makes your Claude better than everyone else's is the forty lines you add over the next three months, because those lines encode the specific things that annoy you, and nobody else's file has them.

  1. โœ๏ธ Notice the second time. The first time you fix something in a draft, fix it and move on. The second time you type the same correction, that is the signal. Anything you have corrected twice becomes a permanent line.
  2. ๐Ÿ” Turn the annoyance into a rule. Do not write it yourself if you cannot be bothered. Run the prompt below and it gives you a properly worded, checkable line.
  3. ๐Ÿ“„ Append it to "lessons". Paste the line at the bottom of the lessons section of your content brain and save. In the Claude app, edit the project's custom instructions. In Claude Code, edit the file and it loads next session.
  4. ๐Ÿงน Prune it monthly. Contradicting rules are the main reason a big memory file stops working, because when two lines disagree Claude picks one and you cannot predict which. Delete the stale ones as ruthlessly as you add new ones, and keep the whole file tight rather than complete.
๐Ÿ” turn a correction into a permanent rule
You did something in that draft that I have now had to fix twice, so let's make the fix permanent instead of me repeating myself. Here is what happened: [describe it plainly, for example "you opened on a question when I have told you I open on a scenario", or "you wrote three tips instead of one idea explained properly"].

Write me one line for the lessons section of my content brain that prevents it happening again. It has to be specific enough that it is obvious whether you followed it or not, so avoid vague words like clear, engaging, good or appropriate, because I cannot check those. Where a rule needs an example to be unambiguous, include a short one in the same line.

Then check my existing file for me. Tell me whether this new line contradicts anything already in there, and if it does, show me which line and rewrite the older one so the two agree.

Give me the final line on its own at the end, ready to copy.

daily use

The draft prompt you use forever

With the brain loaded, your everyday prompt gets short. This is the one I would keep, because it asks for options rather than one draft, and it makes Claude show its reasoning on the hook, which is where the whole post lives or dies.

๐Ÿ“‹ the daily draft prompt
Draft me three scripts on [topic], following my content brain: my four-beat structure, my voice rules, my audience, and everything in the lessons section.

Before the scripts, give me five hook options and rank them. For each hook, say in one line who it is speaking to and what makes them stop, and be honest when one of them is weak. I would rather you tell me two of the five are filler than pad the list.

Then write the three full scripts using your top three hooks. Each one goes to about [45] seconds when read out loud, so keep them to roughly [120] words. Mark the proof beat clearly in each script and name the actual source, and if you cannot find real proof for a claim, cut the claim and tell me you cut it rather than writing something that sounds plausible.

Finish with one line per script on why you think it would work for my audience specifically, not for creators in general.

honest bit

Four ways this quietly breaks

The file gets bloated A memory file that runs to thousands of words gets followed less reliably, not more, because it eats the context every chat starts with. Keep it tight, around 200 lines, and split anything project-specific into its own place.
The rules are moods "Write engagingly" cannot be checked, so it cannot be followed. Every line should be something you could mark right or wrong: "no em dashes", "under twelve words", "one call to action".
You never update it A file you paste once and never touch is a prompt with extra steps. The compounding only happens if corrections go back in, so the habit matters more than the template.
You outsource the taste This gets you a strong first draft, and the last ten percent is still yours. Read every script out loud before you film it, and change the lines that do not sound like your mouth said them.
โš ๏ธ On the results people quote. Follower numbers attached to setups like this one belong to the creator who posted them, and they came with that person's face, filming and posting cadence attached. Treat a memory file as something that removes the blank-page problem and keeps your voice consistent, which is real and worth having, rather than as a growth guarantee.

The docs behind this

Anthropic on projects: custom instructions and project knowledge
Anthropic on CLAUDE.md: file locations, load order and size guidance

the waitlist is now open

AI System Club is launching soon

Build AI systems with me through recorded lessons you can follow at your own pace. Join the waitlist for first access and the founding price.

btw this list gets first dibs
the moment doors open :)