LaunchKit · 2026
Back to Skills

Search and ingest knowledge from Lore, a research repository with citations.

0
1.0k downloads
by @mishkinf

Setup & Installation

openclaw skills install @mishkinf/lore

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install lore

What This Skill Does

Lore is a research knowledge repository that stores documents, meeting notes, interviews, and decisions with full citations linking back to original sources. It provides MCP tools for ingesting external content and searching stored knowledge across a project. Content is deduplicated on ingest and retrievable with its original source URL.

Unlike ad-hoc note storage, Lore preserves original source URLs alongside content so answers can always be traced back to the primary document rather than a paraphrase.

When to use it

  • Saving sprint planning notes so they're searchable in future sprints
  • Looking up why a technical decision was made before changing it
  • Ingesting a Slack thread of user feedback into a project's knowledge base
  • Checking what was discussed in past user interviews before writing a spec
  • Retaining a synthesized insight like a recurring user complaint for later reference

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Why did we choose OAuth over session-based auth?

AGENT
  1. 1Search Lore with query 'authentication approach decisions' using hybrid mode
  2. 2Review results for relevant documents or retained decisions
  3. 3Fetch full source text with get_source if more detail is needed
  4. 4Present findings with title, date, and source URL citation
OUTPUT

A cited answer referencing the original decision document, with a link to the source (e.g., GitHub issue or meeting notes)