New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Human and Agent Kanban Orchestration

by Hermes-brasil in Hermes-brasil/hermes-brasil

Runs a project on one Kanban board shared by people and AI agents, where a dispatcher splits goals into tasks and any task can go to either a human or an agent.

MITAuto-check passedProductivity & Automation

SKILL.md written in Portuguese; this summary is our English description.

Install Human and Agent Kanban Orchestration

skills CLI
$ npx skills add Hermes-brasil/hermes-brasil --skill orquestracao-kanban-humano-agente -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Hermes-brasil/hermes-brasil orquestracao-kanban-humano-agente --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Hermes-brasil/hermes-brasil.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/orquestracao-kanban-humano-agente .claude/skills/orquestracao-kanban-humano-agente && rm -rf skills-src

Use ~/.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/

Facts

Skill name
orquestracao-kanban-humano-agente
GitHub stars
154
Token cost
~738 tokens
SKILL.md length
161 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Runs a project on one Kanban board shared by people and AI agents, where a dispatcher splits goals into tasks and any task can go to either a human or an agent.

  • Projects that need a sequence of tasks with human review points
  • SKILL.md covers Princípio central, Colunas padrão do board, Mecânica de orquestração and Orquestração em qualquer direção, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Coordinating people and AI agents in one shared workflow

What it does

The core idea is a single board rather than separate systems for people and for agents: the same columns and tasks, with positions that either a human or an AI can fill. A human project manager can set up tasks by hand while agents handle the pieces assigned to them, and instructions can run in either direction. The board has six columns from Triage, where raw ideas enter, through To-do for tasks waiting on a dependency, to Done.

A dispatcher role breaks a large goal into smaller tasks and assigns them to human or specialist-agent executors. Typical uses include long content such as an ebook or course written chapter by chapter with review points. Practices include marking a task Blocked explicitly, saving progress durably instead of trusting session memory, stating on each task whether a human or an AI executes it, and treating the board as the source of truth. The skill text is written in Portuguese.

When your agent uses it

  • Projects that need a sequence of tasks with human review points
  • Coordinating people and AI agents in one shared workflow
  • Long work that should not be lost between sessions
  • Multi-step automation that includes a human decision point

Example prompts

  • “Set up a Kanban board for my course launch where you write the chapters and I review each one.”
  • “Break this ebook project into tasks and assign each to me or to an agent.”
  • “Mark the pricing page task as Blocked and note what it is waiting on.”

Requirements

  • A Kanban board that both people and agents can update

What it can do on your machine

Read from SKILL.md and the folder at commit 8f94818. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Human and Agent Kanban Orchestration loads about 738 tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 161 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~738

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.

Safety

Auto-check passed

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Hermes-brasil/hermes-brasil at commit 8f94818, republished under its MIT licence (© Hermes-brasil). 161 words, ~738 tokens.

Download SKILL.mdSave it as .claude/skills/orquestracao-kanban-humano-agente/SKILL.md (or your agent's skills folder).
name
orquestracao-kanban-humano-agente
description
Orquestrar projetos com Kanban humano + agentes de IA.

Orquestração Kanban — Humanos + Agentes de IA

Padrão validado pelo co-fundador da Nous Research (Hermes Agent) no podcast com Peter Yang (02/08/2026). Usado para orquestrar trabalho onde humanos e agentes de IA colaboram no MESMO board.

Princípio central

UM só Kanban para humanos E agentes de IA. Não são dois sistemas separados — são as mesmas colunas, mesmas tarefas, mas as posições são intercambiáveis (humano ou IA em qualquer ponto).

"Posso ter um gerente de projeto humano no board manualmente
enquanto agentes preenchem as peças que ele pediu."
— Karan Malhotra (Nous Research)

Colunas padrão do board

📊 6 COLUNAS:
├── Triage       → ideias cruas entram
├── To-do        → tarefa aguardando (dependência)
├── Ready        → tarefa designada, pronta pra pegar
├── In Progress  → executor (humano ou IA) trabalhando
├── Blocked      → TRAVOU, precisa de humano/intervenção
└── Done         → concluído

Mecânica de orquestração

⚙️ ORQUESTRADOR/DISPATCHER:
├── Quebra meta grande em tarefas menores
├── Atribui a executores (humanos ou agentes especialistas)
├── Checa o board periodicamente (ex: a cada 60s)
├── Roda tarefas na ordem certa
└── Detecta "Blocked" e escalona pra humano

💾 DURABILIDADE (crítico):
├── Board persistente (ex: SQLite local)
├── Cada handoff/tarefa fica SALVO
├── Cada executor é um processo com identidade própria
└── Trabalho NÃO se perde entre sessões

Orquestração em qualquer direção

🔄 QUEM INSTRUI QUEM (intercambiável):
├── Humano (gerente) → instrui agentes
│   Ex: "crie as 5 tasks, agente executa"
├── Agente → instrui humanos
│   Ex: agente orienta equipe de call center
└── A mesma tarefa pode ser feita por humano OU IA

Exemplos de uso

✅ EXEMPLOS PRÁTICOS:
├── Criação de conteúdo longo (ebook, curso):
│   ├── Agente escreve capítulo por capítulo
│   ├── Humano (gerente) dirige o ritmo e revisa
│   └── Mesmo board, papéis trocáveis
├── Prospecção/operações multi-etapa
├── Projetos que precisam de sequência + revisão humana
└── Qualquer fluxo com ponto de decisão humana

💡 COMO APLICAR:
├── Usar coluna "Blocked" explicitamente
│   (agente trava → marca e pede decisão humana)
├── Quebrar metas grandes em tasks no board
└── Manter progresso durável entre sessões

Quando usar esta skill

  • Projetos que precisam de sequência de tarefas + revisão humana
  • Orquestrar agentes + humanos no mesmo fluxo
  • Trabalho longo que não deve se perder entre sessões
  • Automação multi-etapa com ponto de decisão humana

Boas práticas

  • Definir colunas claras (Triage → Done)
  • Marcar explicitamente quando tarefa fica "Blocked"
  • Salvar progresso duravelmente (não confiar só em memória de sessão)
  • Deixar claro em cada tarefa se é humano ou IA que executa
  • Usar o board como fonte de verdade do progresso

© Hermes-brasil, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/orquestracao-kanban-humano-agente of Hermes-brasil/hermes-brasil.

Open the folder on GitHubat commit 8f94818

Compare with similar skills

Human and Agent Kanban Orchestration 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.

Human and Agent Kanban Orchestration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Human and Agent Kanban Orchestration this skillHermes-brasil/hermes-brasil154—~738Automated safety check: PassMIT
Superset Agent Standupsuperset-sh/superset15k—~712Automated safety check: PassCustom licence
Pi Messenger Crewnicobailon/pi-messenger719—~3.7kAutomated safety check: PassNone
AgentRQ Supervisoragentrq/agentrq1.1k—~3.1kAutomated safety check: PassAGPL-3.0
Agent Kanban Tasksaltbo/agent-kanban488—~844Automated safety check: PassCustom licence
Kanban Mdantopolskiy/kanban-md223—~4kAutomated safety check: PassMIT

Similar skills

  • Superset Agent Standup

    superset-sh/superset

    Sweeps every Superset workspace, task and agent terminal to report what finished, what needs review and what is blocked, read-only, and can publish the digest as a page.

    15k GitHub stars~712 tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Pi Messenger Crew

    nicobailon/pi-messenger

    Orchestrator reference for pi-messenger Crew planning, task management, configuration, and agent coordination.

    719 GitHub stars~3.7k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

  • AgentRQ Supervisor

    agentrq/agentrq

    Orchestrates work across specialized AgentRQ workspaces, breaking goals into tasks, assigning them to the right workspace agent, and tracking shared learning notes.

    1.1k GitHub stars~3.1k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Agent Kanban Task

    saltbo/agent-kanban

    Creates, assigns, monitors and reviews one Agent Kanban task through the realmroot toolbox command line, only when you ask for an AK task.

    488 GitHub stars~844 tokensUpdated 9 days ago
    Productivity & AutomationAuto-check passed

  • Kanban Md

    antopolskiy/kanban-md

    Manage project tasks using kanban-md, a file-based kanban board CLI.

    223 GitHub stars~4k tokensUpdated 5 days ago
    Productivity & AutomationAuto-check passed

  • Agent Kanban Task Worker

    saltbo/agent-kanban

    Lets an agent read, claim, update and submit an assigned Agent Kanban task through the Realmroot Toolbox CLI, with progress notes and a review handoff.

    488 GitHub stars~855 tokensUpdated 9 days ago
    Productivity & AutomationAuto-check passed

More from Hermes-brasil/hermes-brasil

All 8 skills in this repo

  • Hermes Agent Production Ops

    Hermes-brasil/hermes-brasil

    A runbook, written in Portuguese, for keeping Hermes Agent healthy on a VPS: updates, gateway restarts, health checks and hosts without a systemd user bus.

    154 GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check: notes

  • Hermes Podcast Insights

    Hermes-brasil/hermes-brasil

    Portuguese notes on a podcast interview with a Nous Research co-founder about Hermes Agent: memory over models, self-improvement, anti-sycophancy and open source.

    154 GitHub stars~802 tokensUpdated 6 days ago
    Auto-check passed

  • Local Business B2B Prospecting

    Hermes-brasil/hermes-brasil

    Runs a B2B prospecting pipeline for local shops in Brazil: Google Places lead collection, WhatsApp or Instagram filtering, messaging and SQLite logging.

    154 GitHub stars~1.1k tokensUpdated 6 days ago
    Auto-check passed

  • RAG Company Knowledge Assistant

    Hermes-brasil/hermes-brasil

    Portuguese guide to building a retrieval-augmented generation assistant over a company's documents, with embeddings, section-based chunking, retrieval and a client workflow.

    154 GitHub stars~1.1k tokensUpdated 6 days ago
    Auto-check passed

  • Think Tank Research

    Hermes-brasil/hermes-brasil

    Use quando precisar de pesquisa multi-persona com síntese protegida por evidências.

    154 GitHub stars~3.1k tokensUpdated 6 days ago
    Auto-check passed

  • Triagem Conteudo Externo

    Hermes-brasil/hermes-brasil

    Tratar conteúdo externo não confiável antes de agir. An agent skill from Hermes-brasil/hermes-brasil.

    154 GitHub stars~1.1k tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Human and Agent Kanban Orchestration

What does Human and Agent Kanban Orchestration do?

Runs a project on one Kanban board shared by people and AI agents, where a dispatcher splits goals into tasks and any task can go to either a human or an agent. The core idea is a single board rather than separate systems for people and for agents: the same columns and tasks, with positions that either a human or an AI can fill. A human project manager can set up tasks by hand while agents handle the pieces assigned to them, and instructions can run in either direction.

When should I use Human and Agent Kanban Orchestration?

Human and Agent Kanban Orchestration fits situations like: projects that need a sequence of tasks with human review points; coordinating people and AI agents in one shared workflow; long work that should not be lost between sessions; multi-step automation that includes a human decision point.

How do I install Human and Agent Kanban Orchestration in Claude Code?

Run `npx skills add Hermes-brasil/hermes-brasil --skill orquestracao-kanban-humano-agente -a claude-code`. Or copy the skill folder (skills/orquestracao-kanban-humano-agente in Hermes-brasil/hermes-brasil) into .claude/skills/orquestracao-kanban-humano-agente in your project. Claude Code loads it when a task matches its description.

How do I install Human and Agent Kanban Orchestration in Codex?

Run `npx skills add Hermes-brasil/hermes-brasil --skill orquestracao-kanban-humano-agente -a codex`. Or copy the skill folder (skills/orquestracao-kanban-humano-agente in Hermes-brasil/hermes-brasil) into .agents/skills/orquestracao-kanban-humano-agente in your project. Codex loads it when a task matches its description.

Can I use Human and Agent Kanban Orchestration in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Hermes-brasil/hermes-brasil --skill orquestracao-kanban-humano-agente -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orquestracao-kanban-humano-agente, .gemini/skills/orquestracao-kanban-humano-agente, .github/skills/orquestracao-kanban-humano-agente and .opencode/skills/orquestracao-kanban-humano-agente in your project.

What does Human and Agent Kanban Orchestration need to run?

SKILL.md names no scripts, command-line tools or credentials: Human and Agent Kanban Orchestration is instructions for the agent only. Our summary lists: A Kanban board that both people and agents can update.

Does Human and Agent Kanban Orchestration access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Human and Agent Kanban Orchestration safe to install?

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. Review the folder before installing.

What licence does Human and Agent Kanban Orchestration use?

Human and Agent Kanban Orchestration is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Human and Agent Kanban Orchestration use?

About 738 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Human and Agent Kanban Orchestration?

Skills that share tags, products or a category with Human and Agent Kanban Orchestration: Superset Agent Standup (superset-sh/superset, 15k stars), Pi Messenger Crew (nicobailon/pi-messenger, 719 stars), AgentRQ Supervisor (agentrq/agentrq, 1.1k stars) and Agent Kanban Task (saltbo/agent-kanban, 488 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Human and Agent Kanban Orchestration?

Hermes-brasil (a GitHub organization) maintains it in Hermes-brasil/hermes-brasil, which has 154 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 5, 2026.

Source: Hermes-brasil/hermes-brasil on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.