本文へスキップ
TakoAPI
スキル一覧に戻る
—まだ評価がありません
あなたの評価

概要

High-velocity research orchestration engine.

説明

このスキルでできること

ResearchVault manages persistent state for agentic research using a local SQLite database. It stores artifacts, findings, and links across sessions, and supports parallel research paths through branches and hypotheses. A built-in synthesis engine discovers connections between findings using local embeddings.

Persistent local state and embedded synthesis mean research context survives across agent runs without relying on external memory services.

使いどころ

  • Tracking findings across a multi-session research project
  • Running parallel hypotheses on the same research topic
  • Monitoring URLs and queries continuously for new developments
  • Coordinating multiple AI agents working on the same research vault
  • Flagging low-confidence data for automated verification

ワークフロー例

入力

User asks: research rising underground metal bands in Finland

エージェント
  1. 1

    Initialize a new vault project with an objective using vault.py init

  2. 2

    Ingest sources by running scuttle against relevant URLs

  3. 3

    Run synthesize to discover and link related findings

  4. 4

    Run verify plan to identify and queue low-confidence findings for follow-up

  5. 5

    Start the MCP server to share vault state with other agents

出力

A structured SQLite vault with linked findings, verified facts, and hypothesis branches ready for further agent consumption

インストール

clawhub install lraivisto/vault-research

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク