agentleFS
Sign inStart free
mnemoversemnemoverse/claude-plugin/skills/memory-save/SKILL.md

memory-save

Skill0 starsChanged 37 days agoMITView on GitHub

Saves a durable decision, preference, correction or lesson to long-term Mnemoverse memory as one self-contained fact, so later sessions and other connected tools can recall it. Use when the user says \"save this to memory\", \"note that we decided\", or \"that was wrong, it is actually\", or when a session settles something worth keeping. Never stores secrets.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. kid0317/crewai_mas_demo★ 164same name
    2. leessju/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Look for the tools memory_write and memory_stats.

    line 10
  2. Distinctive:

    Never store passwords, API keys, tokens, payment data, MFA codes, government IDs or health records.

    line 16
  3. Distinctive:

    One fact per memory: If the user gave several independent facts, save them separately and say how many were saved.

    line 20
  4. Very specific:

    Self-contained: Write content so it still makes sense when recalled months later in another tool: what was decided or observed, why, and …

    line 21
  5. Distinctive:

    Corrections are new memories: When something saved earlier turned out wrong, save the corrected statement and say in it what it replaces.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Save to memory

Check first

Look for the tools memory_write and memory_stats. If they are missing, memory is not connected: say so in one sentence and use the bundled setup skill if it is installed, otherwise https://mnemoverse.com/docs/api/install-by-host. Do not pretend the fact was saved.

What belongs in memory

Durable things: a stated preference, a decision and its reason, a correction, a fact about people, roles or project setup, a lesson from a failure. Chatter that only matters this turn does not belong.

Never store passwords, API keys, tokens, payment data, MFA codes, government IDs or health records. If the input contains any of these, refuse that part in one sentence and save the rest if anything is left.

How to write it

  1. One fact per memory. If the user gave several independent facts, save them separately and say how many were saved.
  2. Self-contained. Write content so it still makes sense when recalled months later in another tool: what was decided or observed, why, and where it came from (a file, a meeting, a test run) when that is known. Prefer the user's own words.
  3. The right place. Personal memory needs no domain. To keep a project's facts together, use a domain such as project:<repository-name>, and before writing to a named domain call memory_stats to reuse its exact spelling: a different case or a stray space opens a separate store. A shared room (beta) is written to only when the user means the room, with its address as domain.
  4. Corrections are new memories. When something saved earlier turned out wrong, save the corrected statement and say in it what it replaces. Nothing is edited in place.

After writing

The result says whether the memory was stored or refused. A write can be refused when memory already holds a statement too close to this one in the same domain. If the point really is the same, tell the user it is already known and do not reword it to force a duplicate in. If it is a correction or adds something new, write only what is different and lead with it, for example "Correction: staging deploys run on Thursday, not Friday"; if that is refused too, tell the user the correction was not saved.

Confirm with the stored text word for word, so the user sees exactly what future sessions will recall.

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.

Check your setup, free