agentleFS
cogotemartinezcogotemartinez/ai-second-brain-template/.claude/skills/update-memory/SKILL.md

update-memory

Skill9 starsChanged 9 months agoMITView on GitHub

Force manual memory update (normally automatic at end of conversations)

5 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

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check what domain the current conversation relates to

    line 15
  2. Distinctive:

    If unclear, ask the user which domain to update

    line 16
  3. Distinctive:

    Add new content in the appropriate sections

    line 31
  4. Distinctive:

    Keep the existing structure

    line 32
  5. Distinctive:

    Add dates where relevant

    line 34
  6. Distinctive:

    Ask if anything should be adjusted

    line 38
  7. Distinctive:

    Only add information explicitly discussed or confirmed

    line 68
  8. Distinctive:

    Don't make assumptions or add speculative content

    line 69
  9. Distinctive:

    Use the same formatting style as existing content

    line 71
  10. Distinctive:

    Ask for clarification if unsure what to capture

    line 72

“Common” is measured: kept by at least 6 in 10 of the 4 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

/update-memory

Force a manual update to memory.md for a domain.

Note: Memory is updated automatically at the end of significant conversations. This command is only for forcing a manual update if needed.

Process

  1. Identify the domain:
    • Check what domain the current conversation relates to
    • If unclear, ask the user which domain to update
  2. Read the current memory file:
    • Read domains/[domain]/memory.md
    • Understand the existing structure and content
  3. Identify what to add: Based on the conversation, look for:
    • Decisions made - choices the user made
    • New information - facts learned about their situation
    • Learnings - insights or principles discovered
    • Status changes - updates to current state
    • History events - significant milestones
  4. Update the file:
    • Add new content in the appropriate sections
    • Keep the existing structure
    • Use consistent formatting
    • Add dates where relevant
  5. Confirm the update:
    • Show the user what was added
    • Ask if anything should be adjusted

What to Capture

Decisions

### [Month Year]
- Decided to [specific decision]
- Chose [option A] over [option B] because [reason]

Learnings

### Principles
- [Insight that applies broadly]

### Notes
- [Specific detail about their situation]

Status Changes

### Current Status
| Item | Status | Notes |
|------|--------|-------|
| [Item] | [New status] | [Context] |

Important

  • Only add information explicitly discussed or confirmed
  • Don't make assumptions or add speculative content
  • Preserve all existing content - only add, don't remove
  • Use the same formatting style as existing content
  • Ask for clarification if unsure what to capture

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.