Search

PythonReactSEOPDF
GitHub Skill

prompt

Capture each prompt into Graphiti memory (episodes) for this repo/user.

TonyCasey☆ 3 Repository stars0 Repository forks

Installation

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.

View source ↗Guides

Skill instructions

Purpose

Store every prompt (and optional role/kind) as a memory episode in Graphiti MCP, so agents can recall recent context.

Triggers

  • "load prompt", "capture prompt", or any per-prompt hook integration
  • Use when you want every prompt stored automatically.

Usage

  • lisa-prompt add --text "..." [--role user|assistant] [--kind Direction|Decision|Requirement|Observation] [--force]
  • By default uses GRAPHITI_ENDPOINT and GRAPHITI_GROUP_ID from .lisa/.env. Falls back to http://localhost:8010/mcp/ and lisa.

Notes

  • Adds a fingerprint tag to avoid duplicate prompts unless --force is passed.
  • Output: JSON with status/action.

Examples

Read the usage examples in the source repository.

View source ↗

Source history

Indexed on
2026-01-20
Index updated
2026-02-03
Branch
main

Index and sync dates describe this directory. View the source repository for code history.

GitHub ↗

chat Comments (0)

chat_bubble_outline

No comments yet. Be the first to share your thoughts!