LaunchKit · 2026
Back to Skills

brain-search

**You MUST actually execute every curl command using your shell/exec tool.** Read the real HTTP response.

0
481 downloads
by @ryandeangraves

Setup & Installation

openclaw skills install @ryandeangraves/brain-search

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

npx clawhub install brain-search

Version History

v1.1.0Feb 19, 2026 - Version note by skill developer:

**Major update emphasizing strict execution and new capabilities:** - Added a critical rule: All curl commands must be executed for real—no simulated or fabricated responses. - Introduced Kanban board/task management features: create, update, and list tasks. - Expanded file storage/handling documentation: upload, list, and delete file attachments. - Added explicit instructions for error handling and reporting actual API responses. - Clarified multi-step job delegation and sub-agent routing. - Updated rules to reflect live monitoring by Boss Man and strong anti-fabrication standards.

What This Skill Does

Provides search and management access to a personal knowledge base that stores conversation logs, research notes, journal entries, and task queues. Supports creating entries, uploading files, managing Kanban tasks, and delegating work to sub-agents via a job queue. All operations go through a REST API with a fixed key.

Centralizes memory, task management, file storage, and job delegation in one API instead of juggling separate tools for each.

When to use it

  • Retrieving what was discussed in a previous session
  • Finding saved research notes by topic or tag
  • Creating and moving tasks on a personal Kanban board
  • Delegating a coding or writing job to a sub-agent
  • Logging a decision or event for future reference

Example Workflow

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

INPUT

User asks: what did we discuss about market analysis last week?

AGENT
  1. 1Calls GET /api/entries with q=market-analysis and tag=market-analysis
  2. 2Reads the returned entries and their content
  3. 3Identifies the most relevant results by date and title
  4. 4Returns a summary of matching entries to the user
OUTPUT

A list of past entries about market analysis with dates and content summaries