convez.ai
MCP ServerAutomaçãoAvançado
prgilabert

Agent Ecosystem Generator

prgilabert/agent-ecosystem-generator

Scaffolding de ecossistemas multi-agentes validados via brief em texto

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server que gera automaticamente ecossistemas multi-agentes validados (orquestrador + N sub-agentes + M skills/MCPs) a partir de uma descrição em linguagem natural. Vai além do skill-creator com validação semântica, avaliações trigger-fire e scaffolding customizado de MCPs em Python/TypeScript.

Instalação

$npx convez-ai prgilabert/agent-ecosystem-generator

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
9
Forks
1
Acompanhando
1
Saúde
42%
Último commit
há 7 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Gerar orquestradores com múltiplos agentes especializados (ex: trio de revisores de PR)
  • Criar pipelines sequenciais ou paralelos de agentes com MCPs customizados
  • Validar cobertura, overlaps e wiring entre agentes em um ecossistema

Veredito

Ferramenta robusta (alpha, bem testada end-to-end) para quem precisa orquestrar múltiplos agentes e MCPs em produção. Scaffolding em Python/FastMCP e TypeScript SDK prontos; validação semântica com até 3 loops de correção automática. Exige compreensão sólida de padrões de orquestração de agentes.

README

A tradução para o português deste README ainda está na fila.

agent-ecosystem-generator

Status: alpha. Core flow smoke-tested end-to-end on a synthetic brief. Project-mode and custom-MCP paths are present but less exercised. Issues and PRs welcome.

Claude Code plugin that scaffolds a validated orchestrator + N sub-agents + M skills/MCPs ecosystem from a brief — a step up from skill-creator, which only scaffolds a single skill.

What it does

  1. /generate-ecosystem spawns a requirements-interviewer sub-agent that talks to you in isolated context and produces a spec.json.
  2. The orchestrator picks an orchestration pattern (orchestrator-workers, sequential pipeline, routing, parallelization-voting, evaluator-optimizer), enumerates agents/skills/MCPs, and writes plan.md.
  3. You pick the output target: portable plugin or in-project .claude/ config.
  4. A ecosystem-builder sub-agent materializes the files (+ scaffolds custom stdio MCPs in Python/FastMCP or TS SDK when needed).
  5. A ecosystem-validator sub-agent runs semantic validation (overlap detection, pushy-ness scoring, coverage, MCP wiring) and trigger evals adapted from skill-creator. If anything fails, it loops back with fix hints up to 3 rounds.

Install

Inside a Claude Code session, register this repo as a marketplace and install the plugin:

/plugin marketplace add prgilabert/agent-ecosystem-generator
/plugin install agent-ecosystem-generator@prgilabert-plugins

Or, if you've cloned the repo locally:

/plugin marketplace add "/absolute/path/to/agent-ecosystem-generator"
/plugin install agent-ecosystem-generator@prgilabert-plugins

claude plugin install <path> (the CLI subcommand) resolves names through a registered marketplace — you can't point it at a local directory directly. The two-step flow above is the canonical path for local plugin repos until Claude Code ships first-class local installs.

Usage

/generate-ecosystem review PRs with three checkers: security, performance, tests

Or just describe what you want — the ecosystem-generator skill auto-triggers on phrases like "design a multi-agent system", "build an agent team", "scaffold an orchestrator".

Examples

See examples/ for real ecosystems produced by this plugin. Each one is an installable Claude Code plugin you can inspect or claude plugin install directly.

  • examples/pr-review-trio/ — orchestrator-workers pattern: /review-pr orchestrates 3 parallel reviewers (security, performance, tests), aggregates via the pr-comment-formatter skill, references the github MCP. Synthetic reference.
  • examples/space-dialogue-plugin/ — orchestrator-workers with parallel fan-out: /escribe-dialogo runs a plot writer first, then astronaut-voice + robot-voice in parallel, then a dialogue-reviewer that assembles and saves a Markdown file. Generated by a real /generate-ecosystem session (Spanish brief, 4 iterations, 0.95 validation).

Improvements over skill-creator

Featureskill-creatoragent-ecosystem-generator
Single skill vs ecosystemSingleOrchestrator + N agents + M skills + MCPs
Output targetsSkill dirPortable plugin or .claude/ project config
Custom MCP scaffoldingReferenced onlyFastMCP (Python) and @modelcontextprotocol/sdk (TS) templates
Validation depthYAML fields presentOverlap detection, pushy-ness scoring, coverage, MCP wiring, trigger evals
Orchestration pattern pickN/APattern library with justification (5 canonical patterns)
Context isolationN/AInterviewer + builder + validator all run in isolated sub-agent ctx

See stack_explanation.md §1–6 for the background, and ROADMAP.md for what's next and where to contribute.

Ver o original no GitHub

Bom para

Relacionados