mcpField
M
memory-extractor

memory-extractor

github.com/learnpromptAgent workflows24068 installsUpdated 16w ago
Repository

About memory-extractor

memory-extractor is a skill for preserving durable collaboration context from recent conversations. It helps agents record preferences, working feedback, project constraints, and external references without saving transient task state.

Key features

  1. 01Captures preferences and work feedback
  2. 02Records project constraints and deadlines
  3. 03Stores pointers to external systems
  4. 04Builds a manifest of existing memories
  5. 05Organizes memory by topic

Use cases

  1. 01Preserving a user's lasting work preferences
  2. 02Recording project deadlines and non-code constraints
  3. 03Checking existing memory topics before updates

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/learnprompt/cc-harness-skills --skill memory-extractor

After installing, type/memory-extractorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
references/
prompt-template.md
source-notes.md
scripts/
memory_manifest.py

Details

From the project README

Memory Extractor

Use this skill when you want to persist durable collaboration context from the latest conversation turns.

Use It For

  • capturing user preferences
  • saving feedback about how to work
  • recording non-code project constraints or deadlines
  • storing pointers to external systems

Avoid It For

  • storing code structure or file locations
  • saving short-lived task state that belongs in a plan
  • duplicating an existing memory topic without checking first

Quick Start

Build a manifest of existing memories:

python3 {baseDir}/scripts/memory_manifest.py --memory-root /path/to/memory

Then use the portable prompt in references/prompt-template.md.

Four Types

  • user
  • feedback
  • project
  • reference

Rules

  • save only durable signals
  • avoid code-state facts that can drift
  • prefer updating an existing topic file
  • organize by topic, not chronology

Supporting Files

Comments

Markdown supported