etalab-ia/dragster

etalab-ia のプロフィール

記録された最新のソース活動: 2026年3月31日 14:36

SkillsMP カタログ更新: 2026年10月17日 00:09

収集済み skills: 4

GitHub スター: 1
GitHub フォーク: 0

リポジトリの README

README の元ファイル：README.md

README の元ファイルを読む

README 全文を表示

# Dragster [![Release](https://img.shields.io/github/v/release/etalab-ia/dragster?sort=date&style=flat-square)](https://github.com/etalab-ia/dragster/releases) [![License](https://img.shields.io/github/license/etalab-ia/dragster?style=flat-square)](LICENSE) [![Status](https://img.shields.io/badge/status-beta-orange?style=flat-square)](https://github.com/etalab-ia/dragster) ``` ██████╗ ██████╗ █████╗ ██████╗ ███████╗████████╗███████╗██████╗ ██╔══██╗██╔══██╗██╔══██╗██╔════╝ ██╔════╝╚══██╔══╝██╔════╝██╔══██╗ ██║ ██║██████╔╝███████║██║ ███╗███████╗ ██║ █████╗ ██████╔╝ ██║ ██║██╔══██╗██╔══██║██║ ██║╚════██║ ██║ ██╔══╝ ██╔══██╗ ██████╔╝██║ ██║██║ ██║╚██████╔╝███████║ ██║ ███████╗██║ ██║ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚═╝ ╚═════╝ ╚══════╝ ╚═╝ ╚══════╝╚═╝ ╚═╝ ``` Skills for local document ingestion and semantic search. Built for AI coding agents (Letta Code, Claude Code, OpenCode, etc.). ## Quick Start ```bash # Install tools npm install -g @tobilu/qmd npm install -g @llamaindex/liteparse # Install all skills npx skills add etalab-ia/dragster # Or install individual skills npx skills add etalab-ia/dragster --skill rag-parse npx skills add etalab-ia/dragster --skill rag-index npx skills add etalab-ia/dragster --skill rag-search npx skills add etalab-ia/dragster --skill rag-tracking ``` ## Skills | Skill | Purpose | Provider | |-------|---------|----------| | `rag-parse` | PDF/DOCX/PPTX/XLSX/Images → Markdown/JSON | [liteparse](https://github.com/run-llama/liteparse) | | `rag-index` | Index documents for semantic search | [qmd](https://github.com/tobi/qmd) | | `rag-search` | Search indexed documents | [qmd](https://github.com/tobi/qmd) | | `rag-tracking` | Track ingestion state & issues | ctx (optional) | > **Note**: `rag-tracking` is designed for agents without built-in memory (Claude Code, Codex, OpenCode). Not needed for Letta Code which has native persistent memory. ## Workflow ``` Documents ──[/rag-parse]──> Markdown ──[/rag-index]──> Index ──[/rag-search]──> Results ``` 1. **Parse**: Convert documents to markdown or JSON (PDF, DOCX, PPTX, XLSX, images) 2. **Index**: Create searchable embeddings with qmd 3. **Search**: Query your knowledge base ## Provider System Skills support multiple providers via metadata in each SKILL.md: ```yaml --- name: search provider: qmd available-providers: - qmd - pinecone - weaviate --- ``` - **provider**: Current active provider (editable by agents) - **available-providers**: Providers this skill can support To switch providers, ask your agent to update the `provider` field in the skill file. ## Integration Works with: - Letta Code - Claude Code - OpenCode - Pi - Cursor - Any agent that supports skills See [docs/integration-guide.md](docs/integration-guide.md) for detailed setup instructions. ## Documentation - [Integration Guide](docs/integration-guide.md) — How to use with various AI agents - [qmd Setup](docs/qmd-setup.md) — Detailed qmd installation and configuration ## Requirements - Node.js 18+ or Bun - liteparse: `npm install -g @llamaindex/liteparse` - qmd: `npm install -g @tobilu/qmd` ## License MIT

リポジトリの README を読み込んでいます…

このリポジトリの skills

ソフトウェア開発者

1 件の職業カテゴリ · 100% 分類済み

skill

職業分類

説明

更新

rag-index

ソフトウェア開発者

Index a document corpus for semantic search. Use when the user wants to set up a knowledge base, create a searchable index from markdown documents, or enable semantic search. Triggers on keywords like "index documents", "create knowledge base", "setup…

原文の言語: 英語

2026-03-31

rag-parse

ソフトウェア開発者

Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally without cloud dependencies.

原文の言語: 英語

2026-03-31

rag-search

ソフトウェア開発者

Search the knowledge base for relevant documents. Use when the user wants to find documents in their indexed corpus, has questions that could be answered by their documents, or needs context from their knowledge base. Triggers on keywords like "search…

原文の言語: 英語

2026-03-31

rag-tracking

ソフトウェア開発者

External persistent memory for document ingestion and issues, designed for agents without built-in memory (Claude Code, Codex, OpenCode). Use when ingesting documents, tracking parsing problems, or recalling collection state. Works with ctx for cross-session…

原文の言語: 英語

2026-03-31

収集済み skill 4 件中 4 件を表示しています。

AI アシスタントでインストール

このプロンプトをコピーして、使用中の AI アシスタントに送ってください。

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/etalab-ia/dragster.