← Back to Skills Marketplace
mishkinf

Lore

by mishkinf · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
1293
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install lore
Description
Search and ingest knowledge from Lore, a research repository with citations
README (SKILL.md)

Lore Knowledge Base

Lore is a research knowledge repository you have access to via MCP tools. It stores documents, meeting notes, interviews, and decisions with full citations — not just summaries, but the original content linked back to its source. Use it to ground your answers in evidence and to preserve important context from your conversations.

When to Ingest Content into Lore

Push content into Lore using the ingest tool whenever you encounter information worth preserving:

  • After conversations: When a user shares meeting notes, interview transcripts, or important documents, ingest them so they're searchable later.
  • External content: When you fetch content from Slack, Notion, GitHub, email, or other systems, ingest the relevant parts into Lore.
  • Decisions and context: When important decisions are made or context is shared that future conversations will need.

Always include:

  • source_url: The original URL (Slack permalink, Notion page URL, GitHub issue URL) for citation linking.
  • source_name: A human-readable label like "Slack #product-team" or "GitHub issue #42".
  • project: The project this content belongs to.

Ingestion is idempotent — calling ingest with the same content twice is safe and cheap (returns immediately with deduplicated: true).

When to Search Lore

Before answering questions about past decisions, user feedback, project history, or anything that might already be documented:

  1. Use search for quick lookups. Pick the right mode:

    • hybrid (default): Best for most queries
    • keyword: For exact terms, names, identifiers
    • semantic: For conceptual queries ("user frustrations", "pain points")
  2. Use research only when the question requires cross-referencing multiple sources or synthesizing findings. It costs 10x more than search — don't use it for simple lookups.

  3. Use get_source with include_content=true when you need the full original text of a specific document.

When to Retain Insights

Use retain (not ingest) for short, discrete pieces of knowledge:

  • Key decisions: "We chose X because Y"
  • Synthesized insights: "3/5 users mentioned Z as their top issue"
  • Requirements: "Must support SSO for enterprise"

Citation Best Practices

When presenting information from Lore, always cite your sources:

  • Reference the source title and date
  • Quote directly when possible
  • If a source_url is available, link to the original

Example Workflows

User asks about past decisions:

  1. search("authentication approach decisions", project: "my-app")
  2. Review results, get full source if needed: get_source(source_id, include_content: true)
  3. Present findings with citations

User shares meeting notes:

  1. ingest(content: "...", title: "Sprint Planning Jan 15", project: "my-app", source_type: "meeting", source_name: "Google Meet", participants: ["Alice", "Bob"])
  2. Confirm ingestion to user

User asks a broad research question:

  1. research(task: "What do users think about our onboarding flow?", project: "my-app")
  2. Present the synthesized findings with citations
Usage Guidance
This skill is coherent with its stated purpose and requests nothing unexpected, but be mindful of the following before installing: 1) It expects your agent to have connectors (Slack, Notion, GitHub, email) or MCP tooling to pull content — ensure those connectors have appropriate scopes and you trust them. 2) Ingesting can store sensitive content in the Lore repository; confirm retention and access policies and obtain consent before ingesting private data. 3) Although the skill itself requests no credentials or installs, review the permissions of any external integrations the agent will use.
Capability Analysis
Type: OpenClaw Skill Name: lore Version: 1.0.0 The skill bundle is benign. The `SKILL.md` file provides instructions for an AI agent on how to interact with a knowledge base system named 'Lore' using predefined tools like `ingest`, `search`, `research`, `get_source`, and `retain`. The instructions are clear, align with the stated purpose of knowledge management, and do not contain any evidence of prompt injection attempts, malicious execution, data exfiltration, persistence mechanisms, or obfuscation. The examples provided are standard usage patterns for a knowledge base interaction.
Capability Assessment
Purpose & Capability
The name/description (search and ingest knowledge from a research repository) matches the SKILL.md instructions which describe when/how to use ingest/search/research/get_source/retain. No unrelated binaries, env vars, or installs are requested.
Instruction Scope
Instructions stay within the repository use-case (ingest/search/retain/research). They explicitly recommend ingesting content from Slack, Notion, GitHub, email, etc.—which is appropriate for a knowledge base but means the agent will handle potentially sensitive content if those connectors exist. The SKILL.md does not instruct the agent to read arbitrary local files or undeclared environment variables.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes on-disk risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. The guidance to use external connectors is reasonable for the stated purpose; there are no unexplained secret requests.
Persistence & Privilege
always:false and user-invocable:false. disable-model-invocation:false (normal); the skill does not request permanent presence or to modify other skills or system settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install lore
  3. After installation, invoke the skill by name or use /lore
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Slug lore
Version 1.0.0
License
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Lore?

Search and ingest knowledge from Lore, a research repository with citations. It is an AI Agent Skill for Claude Code / OpenClaw, with 1293 downloads so far.

How do I install Lore?

Run "/install lore" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Lore free?

Yes, Lore is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Lore support?

Lore is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Lore?

It is built and maintained by mishkinf (@mishkinf); the current version is v1.0.0.

💬 Comments