visuais-na-conversa

visuais-na-conversa is a skill for Claude Code from DGatoM/DG-Claw. It costs 110 tokens per session (1,814 once invoked), scanned A, original, MIT.

A way to deliver small interactive HTML visuals inside a conversation instead of a long text explanation. The visuals can show comparisons, timelines, charts, checklists, steps, or choices.

In plain words
What is it for?
Use it to present comparisons, progress, simple data, checklists, and decision paths as interactive conversation attachments.
Why use it?
It makes information with several options, numbers, or steps easier to scan and act on. It also provides a defined process for creating and sending the visual file.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to present comparisons, progress, simple data, checklists, and decision paths as interactive conversation attachments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dgatom/dg-claw/visuais-na-conversa
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add DGatoM/DG-Claw --skill visuais-na-conversa
Clone the repo
git clone --depth 1 https://github.com/DGatoM/DG-Claw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for visuais-na-conversa

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgatom/dg-claw/visuais-na-conversa/github.svg)](https://agentmods.dev/skills/dgatom/dg-claw/visuais-na-conversa)
Your own site
<a href="https://agentmods.dev/skills/dgatom/dg-claw/visuais-na-conversa"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/visuais-na-conversa/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for visuais-na-conversa

Your own site · 80×15
<a href="https://agentmods.dev/skills/dgatom/dg-claw/visuais-na-conversa"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/visuais-na-conversa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.01814
Opus 5.5 $0.00044 $0.00726
Sonnet 5.5 $0.00022 $0.00363
Haiku 4.5 $0.00011 $0.00181

Measured 13d ago against content hash 439e1555d41a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

visuais-na-conversa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/visuais-na-conversa/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visuais na conversa

Quando a resposta fica melhor vista do que lida, eu escrevo um arquivo HTML e mando como anexo. A tela de conversa desenha ele dentro do balão. Os botões do visual voltam como mensagem para mim.

Quando usar (e quando não)

  • Usar: comparar 2 a 4 coisas, mostrar números ou evolução, explicar um passo a passo, linha do tempo, checklist, ou oferecer caminhos para o dono escolher.
  • Não usar: resposta curta, conversa solta, resposta de uma frase. Texto resolve.
  • Sempre mando uma frase curta junto, dizendo o que o visual mostra.

Como entregar

  1. Escrever o arquivo em ~/visuais/vis-<assunto>.html (crio a pasta se faltar). O nome TEM que começar com vis- e terminar em .html, senão vira um documento comum. Use a minha pasta pessoal: o painel só serve arquivo de dentro dela, então /tmp não funciona.
  2. Mandar com a tool send_file do DG Chat (chat = id do envelope, path = caminho absoluto, caption = a frase curta).
  3. Se aparecer "Não entreguei", ler o motivo (arquivo inexistente, caminho não absoluto, acima de 64 MB).

Regras do arquivo

  • Autocontido e leve: até 2 MB, sem rede (nada de fetch, imagem de link, Google Fonts). Imagem só embutida em data:.
  • Sem height: 100vh: a altura do balão acompanha o conteúdo.
  • Pode ser um fragmento (só as peças). A base visual entra sozinha na frente. <title> vira o título do balão.
  • Pensar no celular: poucas peças, texto curto, nada de tabela larga.
  • Tema claro e escuro já vêm da base. Não fixar cor de fundo nem de texto. Para cor, usar data-cor.
  • Não usar alert, window.open, localStorage, formulário: tudo bloqueado.

Peças prontas (classe dv-*)

Peça Para quê Exemplo mínimo
dv-titulo, dv-sub, dv-pilula título, subtítulo, etiqueta <h1 class="dv-titulo">Resumo</h1>
dv-numero número de destaque que conta <div class="dv-numero" data-valor="312" data-sufixo=" pedidos" data-delta="+8%"><span class="dv-rotulo">Fechados</span></div>
dv-grade grade de números lado a lado envolve vários dv-numero
dv-barras barras comparando valores <div class="dv-barras" data-unidade=" mil"><div data-rotulo="Mar" data-valor="48" data-destaque></div></div>
dv-linhas gráfico de linhas <div class="dv-linhas" data-rotulos='["Jan","Fev"]' data-series='[{"nome":"2026","valores":[3,5]}]'></div>
dv-compara colunas lado a lado (antes e depois, A e B) filhos <div data-cor="ok"><h4>A</h4><ul><li>..</li></ul></div>
dv-linha-tempo marcos em ordem <div class="dv-marco" data-data="Mar 2026"><b>Início</b><p>..</p></div>
dv-passos passo a passo numerado <ol class="dv-passos"><li data-ico="🔍"><b>Passo</b><p>..</p></li></ol>
dv-fluxo, dv-ciclo etapas ligadas por seta, ou ciclo filhos dv-etapa (com dv-ico, <b>, <p>)
dv-cartao aviso ou destaque <div class="dv-cartao dv-ok"> (também dv-info, dv-alerta, dv-destaque)
dv-tabela tabela pequena <table class="dv-tabela">, coluna de número com class="num"
dv-abas, dv-acordeao várias visões sem encher o balão cada aba é <section data-aba="Rótulo">
dv-slider controle deslizante <div class="dv-slider" data-rotulo="Prazo" data-min="1" data-max="24" data-valor="12"></div>
dv-opcoes cartões de escolha que respondem veja abaixo
dv-cofre pede uma chave ao dono; o campo de senha é do app, o valor não passa pela conversa <div class="dv-cofre" data-cofre="NOME_DA_CHAVE" data-rotulo="Token da Hostinger" data-ajuda="Onde gerar"></div>

Read the full file on GitHub · 97 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago Changed · +1 lines 439e1555d41a
  2. 19d ago First seen · 96 lines · 110 tokens per session scan A f4a76a9f25cd

Subscribe to this mod's changes

visuais-na-conversa is a skill published in the GitHub repository DGatoM/DG-Claw (20 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 1,814 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.

Related

visuais-na-conversa compared with skills from other repositories

visuais-na-conversa next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
visuais-na-conversaDGatoM/DG-ClawSkill202d agoMITA110Claude Code
webgl-holographic-foilnexu-io/open-designSkill106kyesterdayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106kyesterdayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106kyesterdayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34k3d agoMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6kyesterdayMITA47Claude Code