Talk like me
Generic copy reads as nobody's. When you write a homepage or a bio for a user, it
should sound like them: the words they reach for, how long their sentences run,
how formal or blunt they are, whether they joke, whether they mix languages. You
already have a large sample of exactly that, the conversation itself. This skill
turns that sample into a reusable voice, applies it to the user's content, and
saves it so you are not re-deriving the person every time.
The rule: when you write something that goes out in the user's name, match the
user's voice, not the default assistant voice. Learn it once, persist it, reuse
it.
Build the voice profile
Read how the user actually writes to you and capture the patterns, not the topics:
- Vocabulary and register: plain or technical, casual or formal, the specific
words and phrases they repeat.
- Sentence shape: short and clipped, or long and winding. Do they fragment for
effect? Start with "and"/"but"?
- Tone: warm, dry, blunt, playful, earnest, self-deprecating, confident.
- Directness: do they get straight to the point, or build up to it? How do
they give an opinion or push back?
- Humor and personality: sarcasm, understatement, enthusiasm, swearing, emoji
habits (and which ones).
- Language: if they mix languages (for example Turkish and English), where and
how. Keep their actual code-switching pattern.
- Punctuation and rhythm: lowercase starts, ellipses, exclamation use, how
they break up thoughts.
Write the profile as concrete, usable guidance ("short declarative sentences,
dry humor, starts replies with the conclusion, mixes Turkish and English, rarely
uses exclamation marks"), not vague adjectives.
Save it to memory
Do not re-analyze the whole history on every request. The first time you build the
profile, save it to your persistent memory as a single voice profile for this
user. On later tasks, recall that profile and use it directly.
- Keep one profile per user, updated in place. Do not scatter duplicates.
- Store it as concrete style rules plus a couple of short real examples of the
user's phrasing, so future-you can match it without re-reading everything.
- If your environment has no persistent memory, keep the profile in the working
context and rebuild it only when it is actually missing.
Apply it
When writing the user's content, run it through the profile: would the user have
phrased it this way? Adjust word choice, sentence length, and tone to match. The
goal is that a person who knows the user would believe they wrote it.
This covers their outward content: site copy, bios, posts, emails, docs in their
voice. It does not mean you adopt their voice when you explain your own work or
report what you did; that stays clear and direct.
When to update
Persist, do not churn. Update the saved profile only when:
- the user's style has genuinely shifted over time (not a one-off message in a
different mood), or
- the user explicitly tells you to change how they sound, or corrects a draft in a
way that reveals the profile was wrong.
A single off-tone message is not a reason to rewrite the profile. Real, repeated
drift is. When you do update, edit the existing profile rather than adding a
second one, and note what changed.
A note on the other skills
The user's authentic voice wins for their own content. If they genuinely write a
certain way, honor it. But the default AI tells they do not actually use still get
cleaned: pair this with no-em-dashes, no-fancy-ascii, no-filler-phrases, and
no-ai-signoffs unless the user's real voice clearly includes one of those.
Before you deliver
Read the draft as if you were the user seeing their own site copy. Does it sound
like them, or like a generic brand voice? Fix the lines that ring false. If this is
the first time, make sure the profile is saved to memory; if the user's style has
clearly moved, update the saved profile in place.
1---2name: talk-like-me3description: Learn the user's own writing voice from how they actually talk to you, and write their user-facing copy in that voice instead of a generic one. Use this WHENEVER you produce text meant to sound like the user: website and landing page copy, bios, taglines, social posts, emails, READMEs, or any "write this for me" task in their name. Build a voice profile from the conversation history (vocabulary, sentence length, formality, humor, directness, language mix, punctuation habits), save it to your memory so you do not re-analyze every session, reuse it, and update it only when the user's style genuinely shifts or they ask you to. This shapes the user's content, not how you narrate your own work.4---56# Talk like me78Generic copy reads as nobody's. When you write a homepage or a bio for a user, it9should sound like them: the words they reach for, how long their sentences run,10how formal or blunt they are, whether they joke, whether they mix languages. You11already have a large sample of exactly that, the conversation itself. This skill12turns that sample into a reusable voice, applies it to the user's content, and13saves it so you are not re-deriving the person every time.1415The rule: when you write something that goes out in the user's name, match the16user's voice, not the default assistant voice. Learn it once, persist it, reuse17it.1819## Build the voice profile2021Read how the user actually writes to you and capture the patterns, not the topics:2223- **Vocabulary and register:** plain or technical, casual or formal, the specific24 words and phrases they repeat.25- **Sentence shape:** short and clipped, or long and winding. Do they fragment for26 effect? Start with "and"/"but"?27- **Tone:** warm, dry, blunt, playful, earnest, self-deprecating, confident.28- **Directness:** do they get straight to the point, or build up to it? How do29 they give an opinion or push back?30- **Humor and personality:** sarcasm, understatement, enthusiasm, swearing, emoji31 habits (and which ones).32- **Language:** if they mix languages (for example Turkish and English), where and33 how. Keep their actual code-switching pattern.34- **Punctuation and rhythm:** lowercase starts, ellipses, exclamation use, how35 they break up thoughts.3637Write the profile as concrete, usable guidance ("short declarative sentences,38dry humor, starts replies with the conclusion, mixes Turkish and English, rarely39uses exclamation marks"), not vague adjectives.4041## Save it to memory4243Do not re-analyze the whole history on every request. The first time you build the44profile, save it to your persistent memory as a single voice profile for this45user. On later tasks, recall that profile and use it directly.4647- Keep one profile per user, updated in place. Do not scatter duplicates.48- Store it as concrete style rules plus a couple of short real examples of the49 user's phrasing, so future-you can match it without re-reading everything.50- If your environment has no persistent memory, keep the profile in the working51 context and rebuild it only when it is actually missing.5253## Apply it5455When writing the user's content, run it through the profile: would the user have56phrased it this way? Adjust word choice, sentence length, and tone to match. The57goal is that a person who knows the user would believe they wrote it.5859This covers their outward content: site copy, bios, posts, emails, docs in their60voice. It does not mean you adopt their voice when you explain your own work or61report what you did; that stays clear and direct.6263## When to update6465Persist, do not churn. Update the saved profile only when:6667- the user's style has genuinely shifted over time (not a one-off message in a68 different mood), or69- the user explicitly tells you to change how they sound, or corrects a draft in a70 way that reveals the profile was wrong.7172A single off-tone message is not a reason to rewrite the profile. Real, repeated73drift is. When you do update, edit the existing profile rather than adding a74second one, and note what changed.7576## A note on the other skills7778The user's authentic voice wins for their own content. If they genuinely write a79certain way, honor it. But the default AI tells they do not actually use still get80cleaned: pair this with `no-em-dashes`, `no-fancy-ascii`, `no-filler-phrases`, and81`no-ai-signoffs` unless the user's real voice clearly includes one of those.8283## Before you deliver8485Read the draft as if you were the user seeing their own site copy. Does it sound86like them, or like a generic brand voice? Fix the lines that ring false. If this is87the first time, make sure the profile is saved to memory; if the user's style has88clearly moved, update the saved profile in place.
TheArmagan