n8n Multi-Instance Targeting
czlonkowski/n8n-skills
Keeps an n8n MCP session pointed at the right n8n instance, with rules for discovering, switching and verifying the target before credential writes and for recovering from misroutes.
Conduz a jornada de onboarding 'do zero ao agente de atendimento' do fazer.ai agents num VPS, escolhendo o orquestrador de deploy (Tier A Coolify, B Portainer, C compose genérico para VM crua ou…
$ npx skills add fazer-ai/agents --skill agents-onboarding -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install fazer-ai/agents agents-onboarding --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/agents-onboarding .claude/skills/agents-onboarding && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agents-onboarding" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-onboarding into .claude/skills/agents-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-onboarding", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-onboardingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add fazer-ai/agents --skill agents-onboarding -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install fazer-ai/agents agents-onboarding --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/agents-onboarding .agents/skills/agents-onboarding && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agents-onboarding" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-onboarding into .agents/skills/agents-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-onboarding", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add fazer-ai/agents --skill agents-onboarding -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install fazer-ai/agents agents-onboarding --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/agents-onboarding .cursor/skills/agents-onboarding && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agents-onboarding" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-onboarding into .cursor/skills/agents-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-onboarding", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/fazer-ai/agents.git --path .claude/skills/agents-onboarding--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add fazer-ai/agents --skill agents-onboarding -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install fazer-ai/agents agents-onboarding --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/agents-onboarding .gemini/skills/agents-onboarding && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agents-onboarding" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-onboarding into .gemini/skills/agents-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-onboarding", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install fazer-ai/agents agents-onboardingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add fazer-ai/agents --skill agents-onboarding -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/agents-onboarding .github/skills/agents-onboarding && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agents-onboarding" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-onboarding into .github/skills/agents-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-onboarding", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add fazer-ai/agents --skill agents-onboarding -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install fazer-ai/agents agents-onboarding --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/agents-onboarding .opencode/skills/agents-onboarding && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agents-onboarding" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-onboarding into .opencode/skills/agents-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-onboarding", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
agents-onboardingConduz a jornada de onboarding 'do zero ao agente de atendimento' do fazer.ai agents num VPS, escolhendo o orquestrador de deploy (Tier A Coolify, B Portainer, C compose genérico para VM crua ou…
Agents Onboarding is an agent skill from fazer-ai/agents. Conduz a jornada de onboarding 'do zero ao agente de atendimento' do fazer.ai agents num VPS, escolhendo o orquestrador de deploy (Tier A Coolify, B Portainer, C compose genérico para VM crua ou qualquer painel). Provisiona DNS/SSH pelo MCP Hostinger, faz deploy de Chatwoot + fazer.ai agents + Langfuse com TLS, roda o /setup e importa o agente via MCP, pluga o Agent Bot do Chatwoot e valida ponta a ponta (playground + WhatsApp + traces no Langfuse). Também conduz a migração de uma Secretária v3 (n8n) para a V4…
Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 46 other files, including scripts and reference files (for example `gotchas.md`, `guardrails.md` and `references/00-prereqs-and-access.md`).
It sits in Productivity & Automation, covering LLM observability, Workflow automation and MCP servers. It works with Model Context Protocol, Langfuse, n8n and WhatsApp. The repository describes itself as: fazer.ai agents. Apache 2.0. The licence is Apache-2.0.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 246c664. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
sshbunxpythonbashFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use ssh and bunx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Agents Onboarding loads about 4.4k tokens when it runs, and up to ~48k if it reads all its reference files. Until then it costs about 209 tokens; SKILL.md has 2,231 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from fazer-ai/agents at commit 246c664, republished under its Apache-2.0 licence (© fazer-ai). 2,231 words, ~4,378 tokens.
.claude/skills/agents-onboarding/SKILL.md (or your agent's skills folder). This skill also uses 45 other files; get the full folder from GitHub.Leva uma VPS de "nada" até "agente de atendimento de IA rodando, testado e plugado numa caixa de entrada real". Esta skill é o bundle executado pelo agente (você): opera o VPS via SSH + a API do orquestrador escolhido (Coolify / Portainer / compose genérico), e controla o fazer.ai agents via MCP (OAuth, dry-run + audit).
No início, resuma pro usuário o caminho em 4 fases, pra ele saber onde está e o que vem. Use estas palavras (não os nomes técnicos das etapas):
É um mapa pro usuário, não o roteiro técnico: as etapas numeradas abaixo (0 a 10) são o seu passo a passo e detalham essas fases. Ao virar de fase, avise ("terminamos de preparar os acessos; agora vou escolher onde hospedar e subir a base") pra a jornada não parecer uma caixa-preta.
guardrails.md inteiro. Tem fronteiras duras (só a VPS e o domínio indicados, licença única do hub, MCP dry-run, nada de produção de terceiros, nada de segredo em log). Cruzar qualquer uma é parar e perguntar.gotchas.md. São as armadilhas conhecidas que, se ignoradas, fazem você redescobrir do jeito difícil (FQDN que não dirige o Traefik, embedding por-tenant, Langfuse sem blob storage, persistência de branding etc.).references/00-prereqs-and-access.md: MCPs ligados (Hostinger ×3; o hub app-fazer-ai não é MCP da sessão, suas ops saem pelo proxy bunx @fazer-ai/agents hub …), acesso SSH, e o contrato do ambiente.AskUserQuestion; Hermes: clarify, setas + opções), use-a, uma pergunta por mensagem. Sem ela (Codex/genérico), pergunte em texto, ainda 1-2 itens por vez (só junte 2 se correlatos, ex.: IP do VPS + caminho da chave SSH). Pergunte na ordem do fluxo, só quando a etapa precisar; espere a resposta antes de avançar. Despejar 5-6 campos numa mensagem é o anti-padrão.hostinger-dns/hostinger-vps/hostinger-domains estão presentes, o provider JÁ é Hostinger (escolhido no CLI); use-os, nunca pergunte "se for Hostinger"; (2) o marcador ~/.fazer-ai/onboarding.json (chatwootSource = Chatwoot novo vs. existente/BYO; quando novo, chatwootTier + chatwootLicenseId; já escolhidos, ver references/00-prereqs-and-access.md). Re-perguntar provider/origem/tier/licença já definidos é erro./setup → MCP → import → bind → E2E) é idêntica em qualquer tier. A etapa 1c escolhe o tier e fixa o contrato que o deploy entrega à espinha./mcp por fora do harness, leitura do código/bundle pra achar endpoints, nem API key pra contornar. Linha do tempo: o MCP do agents nasce na etapa 6 (OAuth depois do /setup); até lá a ausência das tools é o estado normal da jornada, não um bloqueio — as etapas 0-5 não usam o MCP do agents, siga-as normalmente. Depois de conectado: se as tools MCP não estão expostas na sessão, PARE e peça ao usuário pra completar a conexão (Claude: /mcp → Authenticate, com /reload-plugins e reinício só se o fazer-ai não aparecer; Codex/Hermes: reiniciar); não há "fallback REST". SSH/psql/Rails runner só para infra (orquestrador, Chatwoot internals), de forma transitória. Detalhe e o gate em references/06-setup-and-mcp.md.@'…'@ | (ssh|python|bash), de ssh <host> '…código…' com aspas aninhadas/{{…}}/$()/(, de \ no fim da linha (continuação no PowerShell é `, não \), de '{…json…}' | helper (pipe de payload), nem de echo/Set-Content/Out-File > arquivo. **SEMPRE** escreva o payload num **arquivo** (com a ferramenta de edição, zero shell, sem BOM) e rode apontando pro arquivo: bash/Python local → bash x.sh/python x.py; bash remoto → scripts/remote.py --script-file x.sh; psql/rails runner num container remoto → scripts/remote.py --in-container <c> --exec "<prog>" --script-file x.sql; JSON de API → coolify.py … --json-file x.json (nunca pipe); config do fazer.ai agents → MCP. O PowerShell pode ter variável/loop/Start-Sleep; só não pode **carregar o código**. Tabela completa e modos de falha em gotchas.md.references/01b-brownfield.md): reaproveite o que está saudável, nunca destrua dados do usuário.fazer.ai agents nos nomes internos: o projeto do orquestrador e a org/projeto do Langfuse, que ninguém vê. O companyName do /setup é a exceção e não leva o default: o campo é rotulado "Nome da empresa" no produto e é dele que nasce o tenant, então instrua o usuário a digitar o nome da empresa dele (ou do cliente dele, numa agência), com fazer.ai agents só como saída para quem não se importa. O que a regra evita é gastar uma pergunta de onboarding com o nome do projeto, não é padronizar o nome do tenant de quem instala.hub …) e write tools de MCP previewam por padrão e só aplicam com --apply/dry_run:false. As frases boas e ruins de cada ponto de aprovação estão em guardrails.md.Abra a referência da etapa antes de executá-la (carga sob demanda). O fluxo é 0 → 1 → 1b → 1c, então o deploy do tier escolhido em 1c (Tier A = etapas 2-5; B/C = o doc do tier), convergindo na espinha 6-10 (igual em todos). As trilhas A (Coolify) e B (Portainer) são as maduras; a C (compose genérico) é mais nova, então trate-a como primeira run guiada (ver references/01c-pick-tier.md).
| # | Etapa | Referência |
|---|---|---|
| 0 | Pré-requisitos, MCPs, acesso | references/00-prereqs-and-access.md |
| 1 | VPS + DNS (A-records agents./chatwoot./langfuse. + painel do tier) + SSH | references/01-vps-dns-ssh.md |
| 1b | Inventário brownfield: sondar (read-only) e decidir por-serviço (reusar/instalar/sinalizar). Detecta também a Secretária v3 e, achando, oferece a migração. Havendo v3, a VPS está atendendo cliente: antes do deploy, confira a folga de memória e faça o snapshot com prova de rollback | references/01b-brownfield.md + references/migracao-v3.md seção 1b |
| 1c | Selecionar o tier de deploy + fixar o contrato (o que o deploy entrega à espinha) | references/01c-pick-tier.md |
| 2 | Tier A · Coolify: reusar/instalar, API Access, Instance Domain (coolify.<root>) | references/02-coolify.md |
| 3 | Deploy Chatwoot (Pro ou OSS pelo marcador; Pro: API do Coolify, login Harbor). chatwootSource: existing PULA este passo e usa o Chatwoot que já existe | references/03-chatwoot-pro.md |
| 4 | Deploy fazer.ai agents (edição Free/Pro pelo marcador, templates/docker-compose.coolify.yml, bootstrap 2-roles + migrate) | references/04-agents-image.md |
| 5 | Deploy Langfuse (+ MinIO S3 obrigatório) | references/05-langfuse.md |
| 6 | fazer.ai agents /setup (cria admin SUPER_ADMIN) → conectar MCP (OAuth) → alvo de tenant (tenant_list; passar tenant nas tools) | references/06-setup-and-mcp.md |
| 8 | Import do agente (agent_import; padrão Maria/Clínica Moreira, vendorado em samples/agents/maria-clinica-moreira.json) + embedding por-tenant + reindex/retry da KB. Havendo v3, o agente sai dela e não da Maria | references/08-agent-import.md + references/migracao-v3.md |
| 8b | Pós-import (gate): resolver avisos (KB→READY + grounding; STT/TTS/visão) + features opcionais (voz, Google OAuth); com resposta em áudio ligada, oferecer a checagem do áudio (memória + sim do usuário) | references/agent-features.md |
| 9 | Plugar Chatwoot no fazer.ai agents (deployment_connect → set_accounts → inbox_bind). Havendo v3, isto é o cutover e a ordem é obrigatória | references/09-chatwoot-bind.md + references/migracao-v3.md |
| 9b | Licenciar Chatwoot no hub (Kanban/Pro): com licença disponível (CLI/hub licenses) é happy-path (hub create-instance pelo UUID de instalação, NÃO o host → hub attach-license → Refresh → enable-kanban na conta). O sinal autoritativo é enable-kanban retornar kanban_feature_enabled: true (liga a feature na conta E só passa se a assinatura casar); Refresh verde sozinho não basta: imagem + assinatura + feature na conta, os três. Sem licença → OSS sem Kanban | references/chatwoot-hub-register.md |
| 10 | Validar E2E (playground + grounding → integração via Inbox API → traces; Kanban ativo no tier Pro; WhatsApp real opcional). Havendo v3, o agente já está em produção depois do cutover, e a validação é a da migração, não o /teste em caixa descartável | references/10-validate-e2e.md + references/migracao-v3.md |
O deploy (etapa 2) ramifica por tier. As linhas 2-5 acima são a trilha do Tier A (Coolify). Para os outros, escolha em 1c, substitua 2-5 pelo doc único do tier e convirja direto no 6 (todos entregam o mesmo contrato):
references/deploy-b-portainer.mdreferences/deploy-c-compose.mdRevalidar uma instância que já está no ar (o usuário quer conferir a instalação, ou algo de infraestrutura quebrou depois dela) não é outra jornada: rode só a sondagem da 1b, a checagem do Coolify no próprio host da etapa 2 (Tier A) e a 10. A instância atende clientes: qualquer conserto, inclusive o heal-localhost, só com OK do usuário.
O usuário cria o 1º admin no browser do orquestrador (Coolify/Portainer), do Chatwoot e do fazer.ai agents (/setup). Você entrega o link + a instrução e espera (no Coolify, coolify.py wait-admin; no fazer.ai agents, a URL /setup, que não pede token: o onboarding sobe com SETUP_TOKEN_REQUIRED=false), nunca cria essas contas por conta própria. Depois do admin criado, o token e o resto da config são com você. Exceção: o Langfuse é headless (LANGFUSE_INIT_*, etapa 5): você semeia a conta (usuário OWNER) e o operador só faz login (/auth/sign-in); como ele não vê o seed acontecer, faça um handoff explícito (anuncie o painel no ar, entregue URL + e-mail + senha temporária) e espere ele confirmar que entrou antes de seguir. Detalhes em guardrails.md.
migracao-v3.md): ela não é infraestrutura para atualizar, é a configuração do agente morando em outra ferramenta, e vira fonte de leitura para a etapa 8.Os três tiers de deploy (A/B/C) estão dentro do escopo (a etapa 1c roteia).
A run está provada quando: o agente responde no playground E na integração via Inbox API do Chatwoot (mensagem incoming injetada na conversa → webhook → debounce → turn → modelo real → resposta outgoing observada na conversa); a KB está grounding (docs READY, resposta usa o conteúdo indexado); e os traces aparecem no Langfuse (ingestion 207). O WhatsApp físico é opcional (a integração já foi provada via Inbox API). Detalhe e checklist em references/10-validate-e2e.md.
© fazer-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 45 other files (scripts, references) in .claude/skills/agents-onboarding of fazer-ai/agents.
Open the folder on GitHubat commit 246c664
Agents Onboarding next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agents Onboarding this skillfazer-ai/agents | 118 | — | ~4.4k | Automated safety check: Pass | Apache-2.0 | |
| n8n Multi-Instance Targetingczlonkowski/n8n-skills | 6.4k | — | ~3.2k | Automated safety check: Pass | MIT | |
| N8n MCP Tools Expertdavila7/claude-code-templates | 32k | 8 repos | ~3.2k | Automated safety check: Pass | MIT | |
| n8n MCP Tools Expertczlonkowski/n8n-skills | 6.4k | — | ~7.6k | Automated safety check: Pass | MIT | |
| Using N8n MCP Skillsczlonkowski/n8n-skills | 6.4k | — | ~4.3k | Automated safety check: Pass | MIT | |
| Using N8n MCP Skillssickn33/agentic-awesome-skills | 47k | 1 repos | ~3.4k | Automated safety check: Pass | MIT |
czlonkowski/n8n-skills
Keeps an n8n MCP session pointed at the right n8n instance, with rules for discovering, switching and verifying the target before credential writes and for recovering from misroutes.
davila7/claude-code-templates
Expert guide for using n8n-mcp MCP tools effectively. An agent skill from davila7/claude-code-templates.
czlonkowski/n8n-skills
Guides the agent in choosing and calling n8n-mcp tools: finding nodes, validating configurations, deploying templates, managing workflows, folders and credentials, and auditing an instance.
czlonkowski/n8n-skills
A skill your agent uses when building, editing, validating, testing, or debugging an n8n workflow through the n8n-mcp MCP server — designing a flow, configuring a node, writing an expression or Code…
sickn33/agentic-awesome-skills
Route n8n MCP workflow design, editing, validation, testing, deployment, credential, execution, and debugging tasks to specialist guidance.
ericrisco/rsc-harness
A skill your agent uses when operating Make.com (formerly Integromat) programmatically — driving its REST API v2 or the Make MCP server from code or an agent to create, read, update, activate, run…
fazer-ai/agents
Modo operação do fazer.ai agents: debugar conversas em produção e corrigir comportamentos inesperados do agente.
fazer-ai/agents
Modo desenvolvedor do fazer.ai agents: trabalhar no código-fonte.
Conduz a jornada de onboarding 'do zero ao agente de atendimento' do fazer.ai agents num VPS, escolhendo o orquestrador de deploy (Tier A Coolify, B Portainer, C compose genérico para VM crua ou…. Agents Onboarding is an agent skill from fazer-ai/agents.ai agents num VPS, escolhendo o orquestrador de deploy (Tier A Coolify, B Portainer, C compose genérico para VM crua ou qualquer painel).
Agents Onboarding fits situations like: tasks that involve LLM observability; tasks that involve Workflow automation; tasks that involve MCP servers.
Run `npx skills add fazer-ai/agents --skill agents-onboarding -a claude-code`. Or copy the skill folder (.claude/skills/agents-onboarding in fazer-ai/agents) into .claude/skills/agents-onboarding in your project. Claude Code loads it when a task matches its description.
Run `npx skills add fazer-ai/agents --skill agents-onboarding -a codex`. Or copy the skill folder (.claude/skills/agents-onboarding in fazer-ai/agents) into .agents/skills/agents-onboarding in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fazer-ai/agents --skill agents-onboarding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agents-onboarding, .gemini/skills/agents-onboarding, .github/skills/agents-onboarding and .opencode/skills/agents-onboarding in your project.
Going by SKILL.md and its folder, Agents Onboarding needs the command-line tools its instructions call (ssh, bunx, python and bash). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use ssh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Agents Onboarding is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 44k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Agents Onboarding: n8n Multi-Instance Targeting (czlonkowski/n8n-skills, 6.4k stars), N8n MCP Tools Expert (davila7/claude-code-templates, 32k stars), n8n MCP Tools Expert (czlonkowski/n8n-skills, 6.4k stars) and Using N8n MCP Skills (czlonkowski/n8n-skills, 6.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
fazer-ai (a GitHub organization) maintains it in fazer-ai/agents, which has 118 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.
Source: fazer-ai/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.