Claude Skill

visant-copy

Writes and reviews public-facing Brazilian Portuguese copy in Visant's spoken voice, in any repo, and runs copy-lint, which catches AI tics in PT and English copy. Use on "copy", "headline", "landing copy", "remove the AI feel", "texto da landing", "reescrever a dobra", "essa cop

LLM Mart · 0 points · 3 views 0 listing impressions 0 install-command copies
Download pedrojaques99-visant-skills-public-visant-copy-0806a35.zip · 32 KB

Install

skills CLI npx skills add https://github.com/pedrojaques99/visant-skills-public/tree/main/visant-copy
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install pedrojaques99-visant-skills-public@llmmart
Git git clone https://github.com/pedrojaques99/visant-skills-public.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole pedrojaques99/visant-skills-public collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Visant Copy

Two things live here: how Visant copy sounds (valid in any repo) and how it is operated, which depends on where the text lives. The voice below is for Brazilian Portuguese; for English copy read english.md. The linter runs a PT and an English rule set on every input.

  • The repo uses Visant's pipeline (copy*.json at the root and copy:build/copy:check scripts in package.json): the JSON is the SSoT and the HTML is a generated view, so never edit text directly in the .html. See "If the repo uses Visant's pipeline".
  • Any other repo (copy inside the component, .md, exported CMS): the component is the SSoT, and the risk is echo, the same sentence in four files.

Find out which one before touching text:

ls copy*.json 2>/dev/null; grep -nE '"copy:(lint|build|check)"' package.json

Either way, never write Visant copy without going through the prohibitions below.

Rule zero: propose, never apply

Only the tic fixes the linter points out go into the file. A headline, lead or sentence that passes clean stays untouched, even if you think it sounds flat.

Style improvements go as a proposal table in the report (key, before, after), and the user picks row by row. Rewriting what was already good burns trust and makes the user review the reviewer.

The exception is an explicit request. "Essa copy tá confusa, tem que ser na pegada X" is a work order, not an invitation to debate: apply it, show the before/after table, and leave one or two ONE-line alternatives at the end, so a swap costs one Edit and not a new round. Returning only options when the user already gave the direction pushes the work back to them.

The prohibitions

Absolute. They apply to headline, body, CTA, FAQ, email, caption, alt text, error message, meta description. No "but here it worked" exception.

  1. Dash (— or –) never. Period, comma, colon or parentheses.
  2. Separator dot (·, alt+7) never. Not in metadata lists, not in a CTA with a price, not in a phase label, not on the social card. In a list it becomes period and comma ("34 páginas. 9 etapas, 1 case inteiro"), in a label a colon ("Fase 1: A Estratégia"), in a CTA a preposition ("Quero o e-book por R$ 47").
  3. "Não é X, é Y" never. Not split in two sentences ("Não é uma lista. É uma cascata."). Not the sentence that defines by negation ("Não é slogan.").
  4. "É sobre X" never. It asserts nothing. Swap it for the verb of what the thing does.
  5. "Não é apenas X, é X e Y" never. Nor "mais que apenas", "menos X e mais Y", "não se trata de".
  6. Negation dangling at the end never. "Feito pra ler, não pra arquivar." Delete the tail and the sentence gets stronger.
  7. Emoji never. Semicolon never. (©, ®, ™ are trademarks and stay.)
  8. Guru openings never. "Imagine que", "E se eu te dissesse", "Prepare-se pra", "Chegou a hora de". Start with the fact or the scene.
  9. Cliché urgency never. "Últimas vagas", "corre que acaba", "por tempo limitado". Scarcity must be countable: say the number ("este lote tem 30 vagas", "a cota sobe a cada compra").
  10. Credibility seal at most once per page. "real", "de verdade", "na prática", "de fato", "genuíno", "autêntico". One passes. With two, the reader counts and posts a screenshot ("trajetória real, projeto real, técnica real, processo real"). An adjective does not prove; numbers and scenes do. Sete anos de projeto real → Sete anos entregando marca.

The rule that solves 3 to 6: cut the negative half. The sentence that remains is almost always the right one. If the contrast really is the argument, show the consequence instead of negating: instead of "não é falta de talento, é falta de ordem", write "Talento você já tem. O que falta é ordem."

The linter

Running it before delivering copy is mandatory. Plain node, no dependencies, runs in any repo:

L=<skill-dir>/scripts/copy-lint.mjs
node $L copy.json                       # copy JSON
node $L hero.tsx page.tsx og.tsx        # components, passed TOGETHER
node $L README.md docs/landing.md       # markdown or plain text
npm run copy:lint                       # if the repo uses Visant's pipeline

What it accepts, exactly:

input how it reads where it reports
.json (any structure, must be valid JSON) every string value, at any depth the dotted key (hero.title)
code (.js .jsx .ts .tsx .mjs .cjs .vue .svelte .astro) line by line, comments masked L<n>
any other text (.md, .html, .txt) line by line, no masking L<n>
  • Files or folders, one or many. A folder is walked for the types above, skipping node_modules, .git, .next, dist, build, out, coverage and dot-folders.
  • Invalid JSON or a missing path stops with a one-line error and exit 1.
  • Emoji runs on every file. Semicolon and pipe separator run only on .json (in .md the pipe is a table, in code ; is syntax).
  • Flags: --quiet (exit code only, for CI), --include-comments (lint code comments too), --self-test (every PT and EN rule fires, clean sentences pass).
  • Ids are English, pt-/en- when language-specific (pt-not-x-but-y, en-hype), bare for punctuation (em-dash, bullet-separator, semicolon). Old PT ids (travessao, bolinha) still work in config. EN hype needs a marketing object: "Unlock account" passes, "unlock your potential" fails.

Exit 1 with the key, the excerpt and the fix. Two warnings come outside the exit code, because good copy cannot fail on a detail:

  • length per line type (headline 60, CTA 28, lead 180, body 280, SEO title 60, meta description 160), inferred from the key suffix, so .json only; it flags the headline that breaks into three lines on mobile;
  • echo, when the same sentence lives in two of the files passed in the same call. That is why you pass the files together, never one at a time.

In code files comments are not linted on purpose: a JSDoc is not copy.

Repetition budget is per PIECE, and the file is not always the piece

credibility-seal (limit 1, PT and EN words share it) counts per piece: in JSON the first key segment (onboarding.*), in a component the file. Money (R$ 47) is not a seal; the rest is semantic, so confirm at file:line. Why.

The voice

Pattern taken from Visant's e-book landing. In order of importance:

  1. Spoken Brazilian, medium dose. "pra", "a gente", "tá". No "cê", "mano", "tá ligado". Short imperative: "Lê e julga", "Observa uma coisa".
  2. Short sentence after short sentence. Average 12 words. A verbless fragment is a device, always as a punch after the long sentence: "…e a marca se comporta de outro jeito três meses depois. Toda vez."
  3. Scene instead of adjective. Never "inconsistência de marca". Write what is seen: "Um post fala uma coisa, o atendimento fala outra, o site parece de outra empresa."
  4. Blame starts with the author. Confess before charging: "A gente começava pelo logo também. Perdeu semanas assim, até inverter a ordem." Accusing the reader directly ("você começa pelo logo porque é a parte divertida") only after the confession, if at all.
  5. Raw numbers, not rounded to impress. R$450k, 160+ lives, 34 páginas, 7 dias.
  6. Admit limits. "Se algo não funcionou pra gente, tá escrito que não funcionou." It is what most separates the voice from AI text.
  7. Humor by mocking the market, dry and unsignposted: "Sem aula de 40 horas ensinando a centralizar retângulo." It targets the practice, never the person.
  8. Mild swearing, at most one per page, and only where the argument hurts: "porcaria", "cagada". Never in the CTA or the main headline.
  9. Objections in the reader's voice. The FAQ is what the person thinks, in their words: "Já faço branding há anos. Vou ver algo novo?". The answer opens by answering ("Serve.", "É."), never with "Ótima pergunta".

Line-by-line detail, vocabulary, anglicisms, money, CTA, and the before/after table: references/voice.md. Read it before writing a new piece or rewriting a whole section.

The fold names the TASK, not the state

Applies to the H1, the <title> and the social card, and it is the most expensive mistake because it passes every linter.

State copy describes the reader's world and leaves them to work out what they gain: "Você tem centenas de mockups parados no disco." It is correct, real pain, and asks for nothing. Task copy names the verb the person came to do: "Ache o mockup certo sem abrir um PSD."

The test is one question: which verb would the reader type into Google? If the headline lacks that verb, it talks about the state. And beware the wrong task: before writing, check which step really hurts (example in references/cases.md).

When the pain needs to show (and sometimes it does), it goes in the next section, opening the mechanism. On the fold you have 5 seconds, and spending all five describing the problem is wasting your turn.

Visant's own brand terms: glossary. In client copy, the glossary is the client's.

If the repo uses Visant's pipeline (copy.json)

Copy lives in the JSON. HTML and Markdown are generated views. Editing text in the .html is always wrong: the next build overwrites it and the check breaks the deploy. Flow: edit the JSON, npm run copy:lint, npm run copy:build, commit json + html + md together (copy:check in the gate catches drift). SEO (meta.title, meta.description, meta.og_*) lives in the JSON too, injected via data-copy-attr="content".

Full mechanics (new key, new page, data-copy-attr, \n becoming <br>, orphan key error, setting it up in a new repo): references/pipeline.md.

When there is no copy.json (any other repo)

Outside that pipeline, the component is the SSoT. Do not set up a copy.json in the middle of a text task: the user asked for copy, not a new architecture.

The risk changes shape. There is no build to sync views, so the same sentence exists copied in three or four places, and changing only the <h1> leaves the rest selling last month's promise. After changing the headline, hunt the echoes (social card and <title> are the ones most often left behind):

rg -n "trecho da frase antiga" src   # and repeat with 4 or 5 words from the middle

Where they hide, in order of being forgotten:

place typical file
<h1> and lead components/**/hero.tsx
link card app/**/opengraph-image.tsx, and the alt exported there
<title> and description app/**/page.tsx (and the twitter/openGraph of the same object)
screenshot alt and figcaption the same hero
section that repeats the argument components/**/ in the same folder

Close with npx tsc --noEmit in TS repos: a lost comma in JSX breaks the build. The <title> is the only one that changes voice: it answers search, so it carries the noun people search for ("mockups"), while the <h1> carries the verb.

Work order on "review/write the copy"

  1. Read the page's whole JSON (or the whole component) before touching any key. Including comments: they hold the WHY of the current line, and copy that contradicts the decision documented there is rework.
  2. Run copy-lint to get the map of tics.
  3. Apply only the tic fixes, and the rewrite the user asked for with a direction. Everything else becomes a proposal in a table.
  4. Check every number against the source of truth (server-side price, client count, member count). The skill does not store those values on purpose: they age. When in doubt, ask before publishing.
  5. Hunt the echo of the old sentence (rg, or the linter's echo warning with the files passed together) and update the social card, <title>, description and alt.
  6. If you touched a code comment, update what it explains: a comment defending the old copy lies to the next dev.
  7. Run copy-lint again. With Visant's pipeline, also copy:build and copy:check. In a React/TS repo, tsc --noEmit.
  8. Report the before/after of the changed lines. The user approves text by reading text, never by reading a summary of the text.

Neighbors

  • [[visant-design]]: the layout around the words
  • [[visant-killer]]: a screen that looks AI-made; this skill handles text that reads AI-made
  • [[visant-headlines]] (Visant internal): a client brand's voice; this skill is Visant's voice
  • [[visant-new-site]] (Visant internal): the copy of a whole client site
  • [[revenue-centric-design]]: the lever behind the message; this skill writes the sentence
Files (visant-skills-public)
  • references
    • cases.md 1.9 KB
      Loading…
    • english.md 3.8 KB
      Loading…
    • pipeline.md 6.1 KB
      Loading…
    • voice.md 12.7 KB
      Loading…
  • scripts
    • fixtures
      • clean-code.tsx 336 B · in bundle
      • clean-docs.md 201 B
        Loading…
      • dirty.tsx 98 B · in bundle
    • copy-lint.mjs 34 KB · in bundle
  • SKILL.md 13.1 KB
    ---
    name: visant-copy
    description: 'Writes and reviews public-facing Brazilian Portuguese copy in Visant''s spoken voice, in any repo, and runs copy-lint, which catches AI tics in PT and English copy. Use on "copy", "headline", "landing copy", "remove the AI feel", "texto da landing", "reescrever a dobra", "essa copy tá confusa", "tirar cara de IA", "burilar a copy".'
    metadata:
      family: texto
      routes: visant-headlines
    ---
    
    # Visant Copy
    
    Two things live here: **how Visant copy sounds** (valid in any repo) and **how it
    is operated**, which depends on where the text lives. The voice below is for
    Brazilian Portuguese; **for English copy read [english.md](references/english.md)**.
    The linter runs a PT and an English rule set on every input.
    
    - **The repo uses Visant's pipeline** (`copy*.json` at the root and
      `copy:build`/`copy:check` scripts in `package.json`): the JSON is the SSoT and
      the HTML is a generated view, so never edit text directly in the `.html`. See
      "If the repo uses Visant's pipeline".
    - **Any other repo** (copy inside the component, `.md`, exported CMS): the
      component is the SSoT, and the risk is echo, the same sentence in four files.
    
    Find out which one before touching text:
    
    ```bash
    ls copy*.json 2>/dev/null; grep -nE '"copy:(lint|build|check)"' package.json
    ```
    
    Either way, never write Visant copy without going through the prohibitions
    below.
    
    ## Rule zero: propose, never apply
    
    **Only the tic fixes the linter points out go into the file.** A headline, lead
    or sentence that passes clean stays untouched, even if you think it sounds flat.
    
    Style improvements go as a **proposal table in the report** (key, before, after),
    and the user picks row by row. Rewriting what was already good burns trust and
    makes the user review the reviewer.
    
    **The exception is an explicit request.** "Essa copy tá confusa, tem que ser na
    pegada X" is a work order, not an invitation to debate: apply it, show the
    before/after table, and leave **one or two ONE-line alternatives** at the end, so
    a swap costs one Edit and not a new round. Returning only options when the user
    already gave the direction pushes the work back to them.
    
    ## The prohibitions
    
    Absolute. They apply to headline, body, CTA, FAQ, email, caption, alt text,
    error message, meta description. No "but here it worked" exception.
    
    1. **Dash (— or –) never.** Period, comma, colon or parentheses.
    2. **Separator dot (`·`, alt+7) never.** Not in metadata lists, not in a CTA with
       a price, not in a phase label, not on the social card. In a list it becomes
       period and comma ("34 páginas. 9 etapas, 1 case inteiro"), in a label a colon
       ("Fase 1: A Estratégia"), in a CTA a preposition ("Quero o e-book por R$ 47").
    3. **"Não é X, é Y" never.** Not split in two sentences ("Não é uma lista. É uma
       cascata."). Not the sentence that defines by negation ("Não é slogan.").
    4. **"É sobre X" never.** It asserts nothing. Swap it for the verb of what the
       thing does.
    5. **"Não é apenas X, é X e Y" never.** Nor "mais que apenas", "menos X e mais
       Y", "não se trata de".
    6. **Negation dangling at the end never.** "Feito pra ler, não pra arquivar."
       Delete the tail and the sentence gets stronger.
    7. **Emoji never. Semicolon never.** (`©`, `®`, `™` are trademarks and stay.)
    8. **Guru openings never.** "Imagine que", "E se eu te dissesse", "Prepare-se
       pra", "Chegou a hora de". Start with the fact or the scene.
    9. **Cliché urgency never.** "Últimas vagas", "corre que acaba", "por tempo
       limitado". Scarcity must be countable: say the number ("este lote tem 30
       vagas", "a cota sobe a cada compra").
    10. **Credibility seal at most once per page.** "real", "de verdade", "na
        prática", "de fato", "genuíno", "autêntico". One passes. With two, the reader
        counts and posts a screenshot ("trajetória real, projeto real, técnica real,
        processo real"). An adjective does not prove; numbers and scenes do.
        `Sete anos de projeto real` → `Sete anos entregando marca`.
    
    **The rule that solves 3 to 6: cut the negative half.** The sentence that remains
    is almost always the right one. If the contrast really is the argument, show the
    **consequence** instead of negating: instead of "não é falta de talento, é falta
    de ordem", write "Talento você já tem. O que falta é ordem."
    
    ## The linter
    
    Running it before delivering copy is mandatory. Plain node, no dependencies, runs
    in any repo:
    
    ```bash
    L=<skill-dir>/scripts/copy-lint.mjs
    node $L copy.json                       # copy JSON
    node $L hero.tsx page.tsx og.tsx        # components, passed TOGETHER
    node $L README.md docs/landing.md       # markdown or plain text
    npm run copy:lint                       # if the repo uses Visant's pipeline
    ```
    
    What it accepts, exactly:
    
    | input | how it reads | where it reports |
    |---|---|---|
    | `.json` (any structure, must be valid JSON) | every string value, at any depth | the dotted key (`hero.title`) |
    | code (`.js .jsx .ts .tsx .mjs .cjs .vue .svelte .astro`) | line by line, comments masked | `L<n>` |
    | any other text (`.md`, `.html`, `.txt`) | line by line, no masking | `L<n>` |
    
    - **Files or folders**, one or many. A folder is walked for the types above,
      skipping `node_modules`, `.git`, `.next`, `dist`, `build`, `out`, `coverage`
      and dot-folders.
    - Invalid JSON or a missing path stops with a one-line error and exit 1.
    - Emoji runs on every file. Semicolon and pipe separator run **only on
      `.json`** (in `.md` the pipe is a table, in code `;` is syntax).
    - Flags: `--quiet` (exit code only, for CI), `--include-comments` (lint code
      comments too), `--self-test` (every PT and EN rule fires, clean sentences pass).
    - **Ids are English**, `pt-`/`en-` when language-specific (`pt-not-x-but-y`,
      `en-hype`), bare for punctuation (`em-dash`, `bullet-separator`, `semicolon`).
      Old PT ids (`travessao`, `bolinha`) still work in config. EN hype needs a
      marketing object: "Unlock account" passes, "unlock your potential" fails.
    
    Exit 1 with the key, the excerpt and the fix. Two warnings come **outside the
    exit code**, because good copy cannot fail on a detail:
    
    - **length per line type** (headline 60, CTA 28, lead 180, body 280, SEO title
      60, meta description 160), inferred from the key suffix, so `.json` only; it
      flags the headline that breaks into three lines on mobile;
    - **echo**, when the same sentence lives in two of the files passed in the same
      call. That is why you **pass the files together**, never one at a time.
    
    In code files **comments are not linted** on purpose: a JSDoc is not copy.
    
    ### Repetition budget is per PIECE, and the file is not always the piece
    
    `credibility-seal` (limit 1, PT and EN words share it) counts per piece: in JSON
    the first key segment (`onboarding.*`), in a component the file. Money (`R$ 47`)
    is not a seal; the rest is semantic, so confirm at `file:line`. [Why](references/cases.md).
    
    ## The voice
    
    Pattern taken from Visant's e-book landing. In order of importance:
    
    1. **Spoken Brazilian, medium dose.** "pra", "a gente", "tá". No "cê", "mano",
       "tá ligado". Short imperative: "Lê e julga", "Observa uma coisa".
    2. **Short sentence after short sentence.** Average 12 words. **A verbless
       fragment is a device**, always as a punch after the long sentence: "…e a marca
       se comporta de outro jeito três meses depois. Toda vez."
    3. **Scene instead of adjective.** Never "inconsistência de marca". Write what is
       seen: "Um post fala uma coisa, o atendimento fala outra, o site parece de
       outra empresa."
    4. **Blame starts with the author.** Confess before charging: "A gente começava
       pelo logo também. Perdeu semanas assim, até inverter a ordem." Accusing the
       reader directly ("você começa pelo logo porque é a parte divertida") only
       after the confession, if at all.
    5. **Raw numbers, not rounded to impress.** `R$450k`, `160+ lives`,
       `34 páginas`, `7 dias`.
    6. **Admit limits.** "Se algo não funcionou pra gente, tá escrito que não
       funcionou." It is what most separates the voice from AI text.
    7. **Humor by mocking the market**, dry and unsignposted: "Sem aula de 40 horas
       ensinando a centralizar retângulo." It targets the practice, never the person.
    8. **Mild swearing, at most one per page**, and only where the argument hurts:
       "porcaria", "cagada". Never in the CTA or the main headline.
    9. **Objections in the reader's voice.** The FAQ is what the person thinks, in
       their words: "Já faço branding há anos. Vou ver algo novo?". The answer opens
       by answering ("Serve.", "É."), never with "Ótima pergunta".
    
    Line-by-line detail, vocabulary, anglicisms, money, CTA, and the before/after
    table: [references/voice.md](references/voice.md). Read it before writing a new
    piece or rewriting a whole section.
    
    ### The fold names the TASK, not the state
    
    Applies to the H1, the `<title>` and the social card, and it is the most
    expensive mistake because it passes every linter.
    
    State copy describes the reader's world and leaves them to work out what they
    gain: "Você tem centenas de mockups parados no disco." It is correct, real pain,
    and asks for nothing. Task copy names the verb the person came to do: "Ache o
    mockup certo sem abrir um PSD."
    
    The test is one question: **which verb would the reader type into Google?** If
    the headline lacks that verb, it talks about the state. And beware the wrong
    task: before writing, check which step really hurts (example in
    [references/cases.md](references/cases.md)).
    
    When the pain needs to show (and sometimes it does), it goes in the **next
    section**, opening the mechanism. On the fold you have 5 seconds, and spending
    all five describing the problem is wasting your turn.
    
    Visant's own brand terms: [glossary](references/voice.md#brand-glossary-visants-own-copy-only). In client copy, the glossary is the client's.
    
    ## If the repo uses Visant's pipeline (`copy.json`)
    
    **Copy lives in the JSON. HTML and Markdown are generated views.** Editing text
    in the `.html` is always wrong: the next build overwrites it and the check breaks
    the deploy. Flow: edit the JSON, `npm run copy:lint`, `npm run copy:build`,
    commit json + html + md together (`copy:check` in the gate catches drift). SEO
    (`meta.title`, `meta.description`, `meta.og_*`) lives in the JSON too, injected
    via `data-copy-attr="content"`.
    
    Full mechanics (new key, new page, `data-copy-attr`, `\n` becoming `<br>`, orphan
    key error, setting it up in a new repo): [references/pipeline.md](references/pipeline.md).
    
    ## When there is no `copy.json` (any other repo)
    
    Outside that pipeline, **the component is the SSoT**. Do not set up a
    `copy.json` in the middle of a text task: the user asked for copy, not a new
    architecture.
    
    The risk changes shape. There is no build to sync views, so the same sentence
    exists copied in three or four places, and changing only the `<h1>` leaves the
    rest selling last month's promise. **After changing the headline, hunt the
    echoes** (social card and `<title>` are the ones most often left behind):
    
    ```bash
    rg -n "trecho da frase antiga" src   # and repeat with 4 or 5 words from the middle
    ```
    
    Where they hide, in order of being forgotten:
    
    | place | typical file |
    |---|---|
    | `<h1>` and lead | `components/**/hero.tsx` |
    | link card | `app/**/opengraph-image.tsx`, and the `alt` exported there |
    | `<title>` and description | `app/**/page.tsx` (and the `twitter`/`openGraph` of the same object) |
    | screenshot `alt` and `figcaption` | the same hero |
    | section that repeats the argument | `components/**/` in the same folder |
    
    Close with `npx tsc --noEmit` in TS repos: a lost comma in JSX breaks the build.
    The `<title>` is the only one that changes voice: it answers search, so it
    carries the noun people search for ("mockups"), while the `<h1>` carries the verb.
    
    ## Work order on "review/write the copy"
    
    1. Read the page's whole JSON (or the whole component) before touching any key.
       Including comments: they hold the WHY of the current line, and copy that
       contradicts the decision documented there is rework.
    2. Run `copy-lint` to get the map of tics.
    3. **Apply only the tic fixes**, and the rewrite the user asked for with a
       direction. Everything else becomes a proposal in a table.
    4. Check every number against the source of truth (server-side price, client
       count, member count). The skill does not store those values on purpose: they
       age. When in doubt, ask before publishing.
    5. **Hunt the echo** of the old sentence (`rg`, or the linter's echo warning with
       the files passed together) and update the social card, `<title>`, description
       and `alt`.
    6. If you touched a code comment, update what it explains: a comment defending
       the old copy lies to the next dev.
    7. Run `copy-lint` again. With Visant's pipeline, also `copy:build` and
       `copy:check`. In a React/TS repo, `tsc --noEmit`.
    8. Report the before/after of the changed lines. The user approves text by
       reading text, never by reading a summary of the text.
    
    ## Neighbors
    
    - **[[visant-design]]**: the layout around the words
    - **[[visant-killer]]**: a screen that looks AI-made; this skill handles text that reads AI-made
    - **[[visant-headlines]]** (Visant internal): a client brand's voice; this skill is Visant's voice
    - **[[visant-new-site]]** (Visant internal): the copy of a whole client site
    - **[[revenue-centric-design]]**: the lever behind the message; this skill writes the sentence
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.