Skip to content
Skills Library
AI & agents · Automation

memory-remember

/memory-remember

Store a memory into the appropriate Engram file. Trigger when a new preference, decision, milestone, or natural conversation summary point is identified, or when the user explicitly asks to remember something.

Licence
MIT
Last repository change
26.05.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.05.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Store a memory into the appropriate Engram file. Trigger when a new preference, decision, milestone, or natural conversation summary point is identified, or when the user explicitly asks to remember something.

Original author description

Store a memory into the appropriate Engram file. Trigger when a new preference, decision, milestone, or natural conversation summary point is identified, or when the user explicitly asks to remember something.

How it works

  1. When to Use
  2. Workflow
Original SKILL.md headings · 63 lines, 372 words
SKILL.md preview
---
name: memory-remember
description: Store a memory into the appropriate Engram file. Trigger when a new preference, decision, milestone, or natural conversation summary point is identified, or when the user explicitly asks to remember something.
---

# Memory Remember

Store information into the appropriate memory file.

## When to Use

Trigger proactively — do not wait for the user to ask — when:

- A new user preference or decision is discovered during conversation
- A milestone, architecture decision, or lesson learned is identified
- The conversation reaches a natural summary point or is ending
- The user explicitly asks to remember something

## Workflow

### 1. Read Configuration

Read `.claude/memory-settings.json` to get the configured file names.

### 2. Get Current Timestamp

Before writing, run `date '+%Y-%m-%d %H:%M'` via Bash to get the current timestamp. Use this for any dated entry. Use `date '+%Y-%m-%d'` when only a date is needed.

### 3. Classify Content

Determine which file the memory belongs to:

| Type | Target File | Examples |
|------|-------------|----------|
| **Preference** | preferences file | User likes, dislikes, habits, settings, personal info, project conventions |
| **Conversation Summary** | conversations file | What was discussed, tasks completed, decisions made in this session |
| **Long-Term Memory** | longterm file | Life events, milestones, architecture decisions, lessons learned, relationship changes |

### 4. Write to Appropriate File

#### Preferences File
- Read the current file
- Find the appropriate section for the new information
- Edit the existing section content (update, don't duplicate)
- Update the `Last Updated: {DATE}` header to today's date

#### Conversations File
- **Prepend** new entry to the TOP of the file (below the header, above existing entries)
- Format: `### YYYY-MM-DD HH:MM - Topic` (use the timestamp from step 2)
- Include: brief summary of what was discussed, key decisions, action items
- Keep summaries concise (3-8 lines)

#### Long-Term Memory File
- **Append** to the appropriate section within the file
- Format: `- YYYY-MM-DD: Description` (use date from step 2)
- NEVER delete existing entries — only add new ones
- Place under the correct subsection (Milestones, Decisions, Lessons Learned, etc.)

### 5. Confirmation

Briefly mention what was saved (one line), e.g.:
- "Noted your preference for TypeScript over JavaScript."
- "Saved conversation summary about the auth refactor."
- "Recorded the migration to PostgreSQL as an architecture decision."

Do NOT be verbose about the saving process — keep it natural and seamless.

Versions

The database has no other skills named memory-remember.

Database snapshot: 13.11.2026 · package version f9d948ddab0d (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100remember
    Capture a durable learning so future sessions reuse it automatically. Use when the user corrects Claude, states a preference or rule, shares a debugging insight, or says 'remember this'. Writes to agent-memory.
  • 100mem0-remember
    Stores a memory verbatim from user input with appropriate type classification and metadata. Use when the user says remember this, save this, store this, note that, or explicitly asks to record a decision, preference, convention, or learning.
  • 82memory
    Save, change or forget a durable fact when the user says remember, note that, commit to memory or forget
  • 100remember
    Promote reusable project knowledge to the right memory surface. Activate when user says: remember this, save this, store this, remember, memorize, keep this for later.
  • 100memory-recall
    Search and recall memories from the Engram files. Trigger when a topic may relate to past discussions, when the user references previous context, or when the user asks "do you remember…".
  • 95remember
    Stores a memory verbatim from user input with appropriate category classification. Use when the user says remember this, save this, store this, note that, or explicitly asks to record a preference, decision, goal, or lesson.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.