agentleFS
scaletoscaleto/Antigravity-Super-Skill-Architecture/skills/99-common-utils/project-memory/SKILL.md

project-memory

Skill8 starsChanged 10 months agoMITView on GitHub

Global Memory System to maintain and manage shared project context.

26 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If key is provided, navigates the object to find the value.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project Memory Skill

This skill acts as the system's "hippocampus," responsible for storing, retrieving, and updating long-term project contextual information.

Purpose

To provide a single source of truth about project status, technical decisions, and global configurations, accessible to all authorized agents.

Capabilities

1. read_context

Reads information from the global context.

  • Input:
    • key (optional): The specific key to read (e.g., tech_stack.languages). If omitted, returns the entire context.
  • Behavior:
    1. Loads memory-store/global_context.yaml.
    2. If key is provided, navigates the object to find the value.
    3. Returns the value or the entire object.

2. update_context

Updates or inserts information into the global context.

  • Input:
    • key: The key to update (e.g., active_phase.current). Supports dot notation for nesting.
    • value: The new value.
  • Behavior:
    1. Loads memory-store/global_context.yaml.
    2. Updates the value at the specified path.
    3. Saves the file.
    4. Returns confirmation.

3. log_decision

Logs an important decision or milestone in the project log.

  • Input:
    • title: Title of the decision.
    • description: Brief description.
    • status: Status (e.g., PROPOSED, ACCEPTED, DEPRECATED).
    • adr_link (optional): Link to the corresponding ADR file.
  • Behavior:
    1. Loads memory-store/global_context.yaml.
    2. Adds an entry to the decisions_log list with the current timestamp.
    3. Saves the file.

Usage (A2A)

Tech Stack Query

request = {
    "type": "QUERY",
    "target": "project-memory",
    "payload": {
        "action": "read_context",
        "key": "tech_stack"
    }
}

Phase Update

request = {
    "type": "TASK",
    "target": "project-memory",
    "payload": {
        "action": "update_context",
        "key": "active_phase.status",
        "value": "Completed"
    }
}

File Structure

  • memory-store/: Data storage directory.
    • global_context.yaml: Main context file.
  • SKILL.md: This file.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.