搜索

PythonReactSEOPDF
GitHub Skill

prompt

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

TonyCasey☆ 3 仓库 Stars0 仓库 Forks

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。

查看来源 ↗使用指南

技能说明

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.

使用示例

查看来源仓库中的使用示例与配置说明。

查看来源 ↗

来源历史

收录时间
2026-01-20
索引更新时间
2026-02-03
Branch
main

收录与同步日期属于本站记录。源码修改历史请查看来源仓库。

GitHub ↗

chat Comments (0)

chat_bubble_outline

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