link-whatsapp
Skill4 starsChanged 3 days agoApache-2.0View on GitHub
Liga o repositório atual a um grupo ou DM de WhatsApp (cria .claude/whatsapp.json + linha no CLAUDE.md/AGENTS.md + indexa no painel). Use quando o operador pedir pra "linkar", "vincular" ou "conectar" um repo/projeto a uma conversa de WhatsApp.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- autonomoSkill
- comunicacao-clienteSkill
- plantaoSkill
- run-whatsapp-automationSkill
- agenda-radarSkill
- autonomoSkill
- comunicacao-clienteSkill
- plantaoSkill
- run-whatsapp-automationSkill
- voz-do-operadorSkill
- watchSkill
The file
Files
Link projeto ↔ WhatsApp
Siga exatamente o passo a passo canônico em .claude/commands/link-whatsapp.md na raiz
deste repositório (whatsapp-automation) — ele é a fonte única do fluxo: descobrir o painel
(local → Railway), listar os chats, confirmar os campos com o operador e gravar o link.
Duas adaptações quando rodando fora do Claude Code (ex.: Codex):
- Onde o fluxo manda escrever a linha marcada no
CLAUDE.mddo repo de destino, faça o MESMO upsert também noAGENTS.md(crie se não existir) — mesmo bloco, mesmos marcadores<!-- wa-link:start -->/<!-- wa-link:end -->— pra qualquer agente enxergar o vínculo. - Ignore instruções específicas do harness do Claude (ex.: armar a tool Monitor); o vínculo
em si (
.claude/whatsapp.json+ linha no arquivo de instruções + índice do painel) é agnóstico de agente.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

