Anakin Claude Plugin
Anakin-Inc/anakin-claude-plugin
Web scraping, busca e pesquisa profunda integrados ao Claude Code
Ver no GitHubPlugin para Claude Code que integra web scraping, busca e pesquisa profunda via Anakin.io. Converte websites em dados limpos em escala, com suporte a batch scraping, buscas alimentadas por IA e pesquisa agentica multi-etapas.
Instalação
npx convez-ai Anakin-Inc/anakin-claude-plugin1 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
- Extrair dados de múltiplos websites em lote
- Realizar pesquisas web aprofundadas com análise automática
- Coletar e estruturar informações para análise competitiva
- Alimentar pipelines de IA com dados web limpos e organizados
Veredito

Plugin robusto que estende significativamente as capacidades de pesquisa do Claude. Excelente para tarefas de extração dados e análise web em escala, mas requer configuração prévia (CLI + autenticação API) e consumo de créditos.
README
A tradução para o português deste README ainda está na fila.
Anakin Claude Code Plugin
Convert websites into clean data at scale: scrape, batch-scrape, search, and deep research.
Requirements
This plugin requires anakin-cli (Python 3.10+):
pip install anakin-cli
anakin login --api-key "ak-your-key-here"
Get your API key from anakin.io/dashboard.
Installation
From marketplace
First, add the Anakin marketplace to Claude Code:
/plugin marketplace add Anakin-Inc/anakin-claude-plugin
Then install the plugin:
/plugin install anakin@anakin
From local directory (development)
claude --plugin-dir ./anakin-claude-plugin
Validate locally
claude plugin validate .
Once installed, Claude will automatically use Anakin for web scraping, search, and research tasks.
Development note: After modifying plugin files, restart Claude Code to pick up changes.
Components
Skills
| Skill | Invocation | Description |
|---|---|---|
scrape-website | /anakin:scrape-website [url] | Scrape a single URL to markdown, JSON, or raw |
scrape-batch | /anakin:scrape-batch [url1] [url2] | Scrape up to 10 URLs at once |
search-web | /anakin:search-web [query] | AI-powered web search with instant results |
deep-research | /anakin:deep-research [topic] | Deep agentic multi-step research (1-5 min) |
setup | /anakin:setup | Install CLI, configure API key, set up output directory |
anakin-cli | (auto) | Background knowledge: escalation workflow, CLI rules, output organization |
Agents
| Agent | Description |
|---|---|
data-extraction-architect | Plan which anakin-cli commands to use for complex extraction tasks |
Hooks
| Hook | Event | Description |
|---|---|---|
check-auth | PreToolUse (Bash) | Verify anakin-cli is installed and authenticated before running anakin commands |
Scripts
| Script | Used By | Description |
|---|---|---|
check-auth.sh | hooks.json | Shell script that checks CLI installation and auth status |
Usage Examples
Once the plugin is active, Claude will use Anakin automatically. You can also invoke skills directly:
/anakin:search-web latest React documentation
/anakin:scrape-website https://example.com
/anakin:deep-research pros and cons of microservices vs monolith
/anakin:scrape-batch https://a.com https://b.com https://c.com
All output is saved to the .anakin/ directory to keep your context window clean:
.anakin/
├── search-react-docs.json
├── example.com.md
├── batch-results.json
└── research-microservices.json
Architecture
anakin-claude-plugin/
├── .claude-plugin/
│ ├── plugin.json # Plugin manifest
│ └── marketplace.json # Marketplace catalog entry
├── skills/
│ ├── anakin-cli/
│ │ └── SKILL.md # Background knowledge (auto-loaded, not user-invocable)
│ ├── scrape-website/
│ │ └── SKILL.md # Single URL scraping
│ ├── scrape-batch/
│ │ └── SKILL.md # Batch URL scraping
│ ├── search-web/
│ │ └── SKILL.md # Web search
│ ├── deep-research/
│ │ └── SKILL.md # Deep agentic research
│ └── setup/
│ └── SKILL.md # CLI setup and authentication
├── agents/
│ └── data-extraction-architect.md # Extraction strategy planner
├── hooks/
│ └── hooks.json # PreToolUse auth verification
├── scripts/
│ └── check-auth.sh # Auth check script for hooks
├── LICENSE
├── CHANGELOG.md
├── README.md
└── .gitignore
The CLI source code lives in a separate repo: Anakin-Inc/anakin-cli
Configuration
| Variable | Description |
|---|---|
ANAKIN_API_KEY | API key (env var, takes precedence over config file) |
~/.anakin/config.json | Stored API key (set via anakin login) |
License
MIT