agentleFS
shahshreyshahshrey/unclaw/.claude/skills/memory-update/SKILL.md

memory-update

Skill17 starsChanged 7 months agoMITView on GitHub

Distill this session's key learnings into long-term memory. Use after completing significant work or when user says "update memory" or "save this session".

3 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

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Hot (identity/memory.md): Only things needed in every future conversation — current state, active work, key facts, session log.

    line 10
  2. Very specific:

    Read identity/memory.md and relevant memory/*.md files

    line 15
  3. Very specific:

    Keep identity/memory.md under 2500 tokens

    line 24

“Common” is measured: kept by at least 6 in 10 of the 3 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

Review the conversation and update the memory system:

Hot/Cold Routing

  • Hot (identity/memory.md): Only things needed in every future conversation — current state, active work, key facts, session log.
  • Cold (memory/*.md): Detailed context by topic — projects, preferences, decisions, people.

Steps

  1. Read identity/memory.md and relevant memory/*.md files
  2. Identify what's worth keeping: decisions, preferences, project context, people context
  3. Route to the right layer:
    • Current state / active work → identity/memory.md
    • Detailed project info → memory/projects.md
    • Preference patterns → memory/preferences.md
    • Decisions with reasoning → memory/decisions.md
    • People context → memory/people.md
  4. Merge, don't duplicate. Consolidate with existing entries.
  5. Keep identity/memory.md under 2500 tokens
  6. Datestamp new entries: <!-- added YYYY-MM-DD -->
  7. Report what was saved and where

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.