Hermes Brasil skill
Portuguese skills and guides for Hermes Agent: text editing, VPS operations, kanban, RAG and injection defense
- 158 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Operations skills change Hermes settings on the server, including gateway and cron
- The external content triage skill and MCP guides extend the agent reach to the network and tools
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/hermes-brasilDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Operations skills change Hermes settings on the server, including gateway and cron
- The external content triage skill and MCP guides extend the agent reach to the network and tools
This is third-party code. Review the repository files before installing.
What it does
Hermes Brasil is a Brazilian community repository for the Nous Research Hermes agent with a set of `SKILL.md` skills and guides in Portuguese. The `skills/` folder holds nine skills: `anti-ai-slop` (editorial cleanup of PT-BR and English text), `hermes-ops-producao` (update, gateway, health check), `orquestracao-kanban-humano-agente`, `prospeccao-b2b-comercio-local`, `rag-assistente-conhecimento`, `sabi-routing`, `think-tank-research`, `triagem-conteudo-externo` and `hermes-philosophy-podcast`. `guides/` collects step-by-step instructions: basic install, production on a VPS, cron jobs, profiles and kanban, MCP servers, writing and testing skills locally, backup and recovery, and running Chrome on Windows through CDP from WSL. `integrations/` covers a link with n8n. Skills can be added with `hermes skills tap add Hermes-brasil/hermes-brasil` or installed one by one from a direct `SKILL.md` link. Copying folders by hand into `~/.hermes/skills/` works too. The format follows the agentskills.io standard.
Who it is for. Brazilian Hermes users and anyone who wants Hermes skill examples and notes on running the agent on a server.
Good fit when
- Hermes runs on a VPS and you need an order for updates, gateway, cron jobs and backups
- Agent text in Portuguese has to be proofread and stripped of AI tells before publishing
- You need a task queue where people and agents share one kanban
- The agent reads external content and needs protection against injections through it
Not a fit when
- You need a ready plugin with code: the repository is made of text skills and guides
- The reader does not know Portuguese: skills and guides are written in it
- You work with an agent other than Hermes: the skills target Hermes even though the format is shared
Example request
Install the anti-ai-slop skill and proofread this Portuguese post before publishingLimitations
The skills and guides are written in Portuguese and target Hermes Agent, with no focus on Claude Code or Codex, though the `SKILL.md` format is shared. Some scenarios such as `prospeccao-b2b-comercio-local` call external sources, and you should use them within data-protection and marketing laws. The n8n integration and Chrome through CDP need separate setup following the guides.
The repository is community-maintained, not by the Hermes vendor. Some skills such as `sabi-routing` depend on a third-party routing service and its terms.
How to disable. Delete the relevant skill folders from `~/.hermes/skills/` or reverse the tap through `hermes skills` commands. Guide files live only in the repository.
FAQ
How do I connect the skills to Hermes?
With `hermes skills tap add Hermes-brasil/hermes-brasil`. You can install a single skill from its `SKILL.md` link or copy folders into `~/.hermes/skills/`.
What is anti-ai-slop?
A skill for editorial review of PT-BR and English text: it edits wording, structure, tone and meaning and gives variants per publishing channel.
Do I need a separate server for Hermes?
The guides describe a cheap VPS, but a local install works too. The production guide covers updates, gateway and cron.
Is there a guide on MCP?
Yes, `guides/mcp-no-hermes.md` explains how to connect MCP servers to Hermes and extend the toolset.
Can I contribute?
Yes, the repository has `CONTRIBUTING.md` and a pull request template. The `autoria-de-skills.md` guide explains how to write new skills.
Discussion
No questions or reviews yet.
Related
SkillsA pack of practical skills for Hermes Agent: notes, trips, code security, browser automation and interface themes.
Agent Skills by moonlight-lupin
agent-skills
A library of skills and plugins for Hermes Agent covering research, media, scraping, documents, DevOps and agent upkeep.
Thirteen stable and six experimental skills for Hermes Agent: stack diagnosis, migration, token and skill audits
Custom skills bundle for Hermes Agent
hermes-custom-skills
A monorepo of five skills for Hermes Agent: agent security hardening, skill auto-updates, skill search, cross-border expansion and Tencent Yuanbao chat
A self-improving agent from Nous Research with a TUI, messaging gateway, cron jobs and skills it writes itself
Official Hermes Agent plugins: Home Assistant, Spotify, Blender, Snyk, Langfuse, sandboxes and importers for other agents
README in short
The repository collects Portuguese skills, guides and integrations for Hermes Agent: installation, VPS operations, cron, profiles, kanban and MCP. Hermes is described as an open agent with memory across sessions and channels such as Telegram, Discord, Slack, WhatsApp, Signal and Teams.
README badge
Original SKILL.md
---
name: anti-ai-slop
description: Protocolo de revisão editorial para eliminar AI slop em textos PT-BR e EN. Use em toda peça escrita antes da entrega final — léxico, estrutura, tom, semântica, self-check e variações por canal.
version: 1.0.0
license: MIT
metadata:
hermes:
tags: [writing, editorial, revision, anti-slop, humanization, pt-br]
---
# Anti AI-Slop — Skill de Revisão Editorial
> Carregue esta skill na fase de revisão de toda peça escrita. Aplique com disciplina. Não é sugestão, é protocolo.
## Quando usar
- Sempre, em toda peça antes de declarar pronto
- Especialmente quando o draft inicial foi produzido por modelo auxiliar (Kimi, Qwen, DeepSeek, etc.)
- Quando o texto soa "certinho demais" — slop adora se disfarçar de prosa competente
## O que é AI slop
AI slop é uma textura específica de prosa gerada por LLM, reconhecível pela combinação de quatro vícios:
1. **Léxico genérico** — palavras que não comprometem com nada
2. **Estrutura previsível** — formas repetidas que traem o gerador
3. **Tom artificial** — entusiasmo performático, calor sintético, otimismo forçado
4. **Semântica oca** — truísmos vestidos de insight, abstração quando o concreto serve
Não é "texto ruim". É uma textura que cumula. Um sintoma isolado pode ser inocente; três ou quatro juntos é diagnóstico.
---
## 1. Camada Léxica
### 1.1 Verbos-muleta — EN
`delve` · `navigate` (uso abstrato) · `explore` (uso abstrato) · `foster` · `leverage` · `unlock` · `harness` · `embrace` · `embark` · `journey` · `transform` (uso vago) · `elevate` · `empower` · `unleash` · `craft` (quando "make" basta) · `cultivate` (em contextos não-agrícolas) · `streamline` · `optimize` (uso vago)
### 1.2 Verbos-muleta — PT-BR
`navegar` (uso abstrato) · `explorar` (idem) · `desbloquear` · `alavancar` · `fomentar` · `potencializar` · `transformar` (uso vago) · `elevar` · `empoderar` · `mergulhar` (uso metafórico) · `trazer à tona` · `lançar luz sobre` · `desvendar` · `abraçar` (uso metafórico) · `cultivar` (em contextos não-agrícolas) · `entregar valor` · `agregar valor`
### 1.3 Adjetivos vazios — EN