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 GitHubMCP 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/beagle1 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
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

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:
- Claude Code CLI installed
- agent-browser for the
run-test-planskill (optional)
# 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.jsonand restart Claude Code. - Plugin not updating: Run
claude plugin marketplace update existential-birdsto 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
| Plugin | Skills | Category |
|---|---|---|
| beagle-core | 19 | Shared workflows, verification, git, skill tooling |
| beagle-python | 7 | Python, FastAPI, SQLAlchemy, pytest |
| beagle-go | 13 | Go, BubbleTea, Wish SSH, Prometheus |
| beagle-elixir | 11 | Elixir, Phoenix, LiveView, ExUnit, ExDoc |
| beagle-ios | 16 | Swift, SwiftUI, SwiftData, iOS frameworks |
| beagle-react | 28 | React, React Flow, shadcn/ui, Tailwind, Remix v2 |
| beagle-rust | 12 | Rust, tokio, axum, sqlx, serde |
| beagle-docs | 10 | Documentation quality, AI writing detection (Diataxis) |
| beagle-analysis | 13 | Brainstorming, ADRs, strategy, LLM-as-judge, spec gap resolution, TDD plan writing |
| beagle-testing | 2 | Test plan generation and execution |
| Total | 131 | — |
Skills
These are the canonical skill entry points for Beagle.
beagle-core
| Skill | Description |
|---|---|
review-plan <path> | Review implementation plans |
review-llm-artifacts | Detect LLM coding artifacts |
verify-llm-artifacts | Confirm or reject review findings before deletes |
fix-llm-artifacts | Fix detected artifacts |
commit-push | Commit and push changes |
create-pr | Create PR with template |
gen-release-notes <tag> | Generate release notes |
receive-feedback <path> | Process review feedback |
fetch-pr-feedback | Fetch bot comments from PR |
respond-pr-feedback | Reply to bot comments |
subagent-prompt | Hand off the current session as an orchestrator-plus-subagents prompt for a fresh session |
prompt-improver | Optimize prompts |
Code Review Skills
| Skill | Plugin | Description |
|---|---|---|
review-python | beagle-python | Python/FastAPI code review |
review-frontend | beagle-react | React/TypeScript code review |
review-go | beagle-go | Go code review |
review-tui | beagle-go | BubbleTea TUI code review |
review-ios | beagle-ios | iOS/SwiftUI code review |
review-elixir | beagle-elixir | Elixir/Phoenix code review |
review-rust | beagle-rust | Rust/tokio/axum code review |
review-remix-v2 | beagle-react | Remix v2 code review (loaders, actions, forms, sessions) |
Documentation & Analysis Skills
| Skill | Plugin | Description |
|---|---|---|
draft-docs <prompt> | beagle-docs | Generate documentation drafts |
improve-doc <path> | beagle-docs | Improve docs using Diataxis |
ensure-docs | beagle-docs | Documentation coverage check |
review-ai-writing | beagle-docs | Detect AI writing patterns |
humanize-beagle | beagle-docs | Fix AI writing with safe/risky classification |
llm-judge | beagle-analysis | Compare implementations |
write-adr | beagle-analysis | Generate ADRs from decisions |
brainstorm-beagle | beagle-analysis | Turn fuzzy ideas into structured project specs |
resolve-beagle | beagle-analysis | Close Open Questions and latent gaps in a brainstorm-beagle spec |
strategy-interview | beagle-analysis | Build strategy through guided conversation |
strategy-review | beagle-analysis | Pressure-test existing strategy documents |
prfaq-beagle | beagle-analysis | Working Backwards PRFAQ filter — pass/fail concepts before brainstorming |
web-research | beagle-analysis | Parallel-subagent web research with cited synthesis report |
artifact-analysis | beagle-analysis | Parallel-subagent scan of local docs with cited extraction |
write-plan | beagle-analysis | Turn a finalized brainstorm-beagle spec into a TDD-driven implementation plan |
Skill Tooling
| Skill | Plugin | Description |
|---|---|---|
skill-builder | beagle-core | Create new Claude Code skills with best practices |
review-skill | beagle-core | Automated skill PR review for structural validity, design quality, and marketplace consistency |
Testing Skills
| Skill | Plugin | Description |
|---|---|---|
gen-test-plan | beagle-testing | Generate YAML test plan |
run-test-plan | beagle-testing | Execute test plan |