convez.ai
MCP ServerDevOps & InfraestruturaIntermediário
existential-birds

Beagle - Marketplace de Code Review com IA

existential-birds/beagle

131 skills de code review, detecção IA, docs e testes para 8+ linguagens

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que fornece 131 skills de revisão de código, detecção de artefatos IA, geração de documentação, planos de teste e análise arquitetural. Suporta Python, Go, Rust, Elixir, React, Remix, Swift e frameworks de IA, integrável com Claude Code e outros agentes.

Instalação

$npx convez-ai existential-birds/beagle

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
88
Forks
9
Acompanhando
3
Saúde
62%
Último commit
há 2 meses
Versão
v4.4.0
Issues abertas
6
Contribuidores
2

Casos de uso

  • Revisar código antes de fazer push e detectar artefatos gerados por IA
  • Gerar planos de teste e documentação automaticamente
  • Análise arquitetural e workflows git otimizados
  • Integração com agentes (Amelia) e loops de review-fix-test automatizados

Veredito

Beagle é um marketplace robusto e abrangente de skills de code review com suporte multi-linguagem. Ideal para times que querem automatizar revisão, detecção de IA e testes, mas requer familiaridade com Claude Code e configuração inicial de plugins.

README

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

beagle

Ask DeepWiki

Apollo 10 astronaut Thomas P. Stafford pats the nose of a stuffed Snoopy

Image: NASA, Public Domain. Source

Beagle is a Claude Code plugin marketplace with 131 skills across code review, documentation, testing, architectural analysis, and git workflows. Use it to review before you push, detect AI-generated artifacts, draft and improve docs, generate test plans, and analyze codebases — across Python, Go, Rust, Elixir, React, Remix v2, iOS/Swift, and AI frameworks.

Used with Amelia for agent-based workflows and Daydream for automated review-fix-test loops.

Installation

Prerequisites:

# Add the marketplace
claude plugin marketplace add https://github.com/existential-birds/beagle

# Install the plugins you need
claude plugin install beagle-core@existential-birds
claude plugin install beagle-python@existential-birds
claude plugin install beagle-react@existential-birds

Verify installation by opening a new Claude Code session and running /beagle-core:commit-push — if the skill loads, the plugin is active.

To update:

claude plugin marketplace update existential-birds && claude plugin update <plugin-name>

Troubleshooting:

  • "Marketplace file not found": Remove stale entries from ~/.claude/plugins/known_marketplaces.json and restart Claude Code.
  • Plugin not updating: Run claude plugin marketplace update existential-birds to refresh the marketplace.

Other Agents

Use the skills CLI to install beagle skills for other AI agents:

npx skills add existential-birds/beagle

This downloads the skills and configures them for your agent.

Codex users: Link each plugin into ~/.agents/skills/ — see .codex/INSTALL.md for setup instructions.

Plugins

PluginSkillsCategory
beagle-core19Shared workflows, verification, git, skill tooling
beagle-python7Python, FastAPI, SQLAlchemy, pytest
beagle-go13Go, BubbleTea, Wish SSH, Prometheus
beagle-elixir11Elixir, Phoenix, LiveView, ExUnit, ExDoc
beagle-ios16Swift, SwiftUI, SwiftData, iOS frameworks
beagle-react28React, React Flow, shadcn/ui, Tailwind, Remix v2
beagle-rust12Rust, tokio, axum, sqlx, serde
beagle-docs10Documentation quality, AI writing detection (Diataxis)
beagle-analysis13Brainstorming, ADRs, strategy, LLM-as-judge, spec gap resolution, TDD plan writing
beagle-testing2Test plan generation and execution
Total131—

Skills

These are the canonical skill entry points for Beagle.

beagle-core

SkillDescription
review-plan <path>Review implementation plans
review-llm-artifactsDetect LLM coding artifacts
verify-llm-artifactsConfirm or reject review findings before deletes
fix-llm-artifactsFix detected artifacts
commit-pushCommit and push changes
create-prCreate PR with template
gen-release-notes <tag>Generate release notes
receive-feedback <path>Process review feedback
fetch-pr-feedbackFetch bot comments from PR
respond-pr-feedbackReply to bot comments
subagent-promptHand off the current session as an orchestrator-plus-subagents prompt for a fresh session
prompt-improverOptimize prompts

Code Review Skills

SkillPluginDescription
review-pythonbeagle-pythonPython/FastAPI code review
review-frontendbeagle-reactReact/TypeScript code review
review-gobeagle-goGo code review
review-tuibeagle-goBubbleTea TUI code review
review-iosbeagle-iosiOS/SwiftUI code review
review-elixirbeagle-elixirElixir/Phoenix code review
review-rustbeagle-rustRust/tokio/axum code review
review-remix-v2beagle-reactRemix v2 code review (loaders, actions, forms, sessions)

Documentation & Analysis Skills

SkillPluginDescription
draft-docs <prompt>beagle-docsGenerate documentation drafts
improve-doc <path>beagle-docsImprove docs using Diataxis
ensure-docsbeagle-docsDocumentation coverage check
review-ai-writingbeagle-docsDetect AI writing patterns
humanize-beaglebeagle-docsFix AI writing with safe/risky classification
llm-judgebeagle-analysisCompare implementations
write-adrbeagle-analysisGenerate ADRs from decisions
brainstorm-beaglebeagle-analysisTurn fuzzy ideas into structured project specs
resolve-beaglebeagle-analysisClose Open Questions and latent gaps in a brainstorm-beagle spec
strategy-interviewbeagle-analysisBuild strategy through guided conversation
strategy-reviewbeagle-analysisPressure-test existing strategy documents
prfaq-beaglebeagle-analysisWorking Backwards PRFAQ filter — pass/fail concepts before brainstorming
web-researchbeagle-analysisParallel-subagent web research with cited synthesis report
artifact-analysisbeagle-analysisParallel-subagent scan of local docs with cited extraction
write-planbeagle-analysisTurn a finalized brainstorm-beagle spec into a TDD-driven implementation plan

Skill Tooling

SkillPluginDescription
skill-builderbeagle-coreCreate new Claude Code skills with best practices
review-skillbeagle-coreAutomated skill PR review for structural validity, design quality, and marketplace consistency

Testing Skills

SkillPluginDescription
gen-test-planbeagle-testingGenerate YAML test plan
run-test-planbeagle-testingExecute test plan
Ver o original no GitHub

Bom para

Relacionados