memory-capture

Capture and organize memories, decisions, and learnings to a memories.md file. Use when you want to save context for future sessions.

16 stars

Best use case

memory-capture is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Capture and organize memories, decisions, and learnings to a memories.md file. Use when you want to save context for future sessions.

Teams using memory-capture should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/memory-capture/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/development/memory-capture/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/memory-capture/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How memory-capture Compares

Feature / Agentmemory-captureStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Capture and organize memories, decisions, and learnings to a memories.md file. Use when you want to save context for future sessions.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Memory Capture

Help users capture important decisions, preferences, and learnings to their memories file for future reference.

## When to Use

Invoke this skill when the user wants to:
- Record a decision they made
- Save a preference for future sessions
- Document something they learned
- Create a note about the project or codebase

## Memory Locations

- **Personal memories**: `~/.factory/memories.md` - preferences that apply across all projects
- **Project memories**: `.factory/memories.md` - decisions specific to the current project

## Capture Process

### Step 1: Understand What to Remember

Ask the user to clarify:
- What specifically should be remembered?
- Is this a personal preference or project-specific?
- What's the context (why is this worth remembering)?

### Step 2: Categorize the Memory

Common categories:

**For Personal Memories:**
- Code style preferences
- Tool preferences
- Communication style
- Workflow patterns

**For Project Memories:**
- Architecture decisions
- Design choices
- Domain knowledge
- Known issues
- Team conventions

### Step 3: Format the Entry

Use this format:

```markdown
### [Date]: [Short Title]
**Category**: [Decision/Preference/Learning/Context]
**Summary**: [One sentence description]
**Details**: [Full explanation if needed]
**Reasoning**: [Why this matters - optional]
```

For simpler entries:
```markdown
- [Date] [Category]: [Description]
```

### Step 4: Append to Memories File

Add the formatted entry to the appropriate memories file.

If the file doesn't exist, create it with proper structure:

**For Personal (~/.factory/memories.md):**
```markdown
# My Development Memory

## Preferences
[preferences entries]

## Learnings
[learning entries]
```

**For Project (.factory/memories.md):**
```markdown
# Project Memory

## Decisions
[decision entries]

## Context
[context entries]

## Known Issues
[issue entries]
```

## Example Captures

### Architecture Decision

User says: "Remember that we chose PostgreSQL over MongoDB for this project"

Capture as:
```markdown
### 2024-02-15: Database Selection
**Category**: Architecture Decision
**Summary**: Chose PostgreSQL over MongoDB for the primary database
**Reasoning**: 
- Strong relational data model fits our domain
- ACID compliance needed for financial transactions
- Team has more PostgreSQL experience
- Better tooling for complex queries and reporting
```

### Personal Preference

User says: "I prefer early returns over nested conditionals"

Capture as:
```markdown
## Code Style Preferences

- [2024-02-15] I prefer early returns over nested conditionals for better readability
```

### Domain Knowledge

User says: "Note that free tier users are limited to 3 team members"

Capture as:
```markdown
### Business Rules

- Free tier: Limited to 3 team members
- Pro tier: Up to 20 team members
- Enterprise: Unlimited team members
```

### Technical Context

User says: "The auth service has a known issue with refresh tokens (#234)"

Capture as:
```markdown
## Known Issues

- [ ] Auth refresh token race condition (#234) - Can cause session loss during concurrent requests
```

## Tips

1. **Keep entries scannable** - Use headers and bullet points
2. **Include dates** - Context matters, decisions may change
3. **Note the "why"** - Future you will want to know
4. **Link to issues/PRs** - For traceability
5. **Review periodically** - Archive outdated memories

---

## Alternative Implementations

This skill is one of three ways to capture memories. Choose based on your workflow:

### Option 1: This Skill (Interactive)

Droid invokes this skill when you ask to remember something. Best when you want help categorizing and formatting memories.

**Usage:** "Remember that we chose PostgreSQL for ACID compliance"

### Option 2: Hook (Automatic)

A [UserPromptSubmit hook](/cli/configuration/hooks-guide) that triggers on phrases like "remember this:". Best for zero-friction capture.

See the [Memory Management guide](/guides/power-user/memory-management#automatic-memory-capture) for the hook implementation.

**Usage:** "Remember this: we use the repository pattern for data access"

### Option 3: Custom Slash Command (Manual)

A [custom slash command](/cli/configuration/custom-slash-commands) for quick, consistent capture.

Create `~/.factory/commands/remember.md`:

```markdown
---
description: Save a memory to your memories file
argument-hint: <what to remember>
---

Add this to my memories file (~/.factory/memories.md):

$ARGUMENTS

Format it appropriately based on whether it's a preference, decision, or learning. Include today's date.
```

**Usage:** `/remember we chose PostgreSQL for ACID compliance`

### Comparison

| Approach | Trigger | Best For |
|----------|---------|----------|
| **Skill** | Droid decides | Interactive categorization |
| **Hook** | Automatic on keywords | Zero-friction capture |
| **Slash Command** | You type `/remember` | Quick manual capture |

Related Skills

moai-foundation-memory

16
from diegosouzapw/awesome-omni-skill

Persistent memory across sessions using MCP Memory Server for user preferences, project context, and learned patterns

memorylane

16
from diegosouzapw/awesome-omni-skill

Zero-config persistent memory for Claude with automatic cost savings. Use when you need to remember project context, reduce API token costs, track learned patterns, manage memories across sessions, or curate/clean up memories. Automatically compresses context 6x and saves 84% on API costs. Keywords: memory, remember, recall, context, cost savings, reduce tokens, learn, patterns, insights, curate, clean up memories, review memories.

memory-sync

16
from diegosouzapw/awesome-omni-skill

Guided workflow for maintaining strategic redundancy between Serena memories and project documentation. Use after significant code changes, phase completions, or when new architectural patterns are discovered.

memory-management

16
from diegosouzapw/awesome-omni-skill

Guide for managing Claude Code memory effectively. Use when setting up project memory, optimizing CLAUDE.md files, configuring rules directories, or establishing cross-session knowledge patterns. Covers memory hierarchy, best practices, and context optimization.

memory

16
from diegosouzapw/awesome-omni-skill

Manages memory, SSOT files, and Plans.md operations. Use when user mentions メモリ, memory, SSOT, decisions.md, patterns.md, マージ, merge, Plans.md, 移行, migrate. Do NOT load for: 実装作業, レビュー, 一時的なメモ, セッション中の作業記録.

memory-conventions

16
from diegosouzapw/awesome-omni-skill

This skill should be used when persisting context between sessions, saving project state, loading previous session context, or managing longitudinal memory beyond beads issue tracking.

memory-bank

16
from diegosouzapw/awesome-omni-skill

Persistent project documentation system that maintains context across sessions. Creates structured Memory Bank files to preserve project knowledge, decisions, and progress.

context-memory

16
from diegosouzapw/awesome-omni-skill

Advanced context and memory management system for AI agents. Provides persistent memory across sessions through daily logs (memory/YYYY-MM-DD.md), long-term curated memory (MEMORY.md), conversation archives with semantic search, and automatic behavioral learning from user satisfaction tracking. Use when you need to: (1) Remember information across sessions, (2) Archive conversations before context loss, (3) Search past discussions, (4) Track and learn from user satisfaction patterns, (5) Maintain session continuity, (6) Implement proactive memory maintenance. Includes conversation-archiver.py and satisfaction-tracker.py scripts, session startup routines, and periodic reflection workflows.

ac-memory-manager

16
from diegosouzapw/awesome-omni-skill

Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.

atuin-memory

16
from diegosouzapw/awesome-omni-skill

Check, store, and retrieve project memories from atuin kv. Use when starting work on a project, recalling previous context, storing plans or specs, or when the user mentions memory, atuin, or project context.

memory-safety-patterns

16
from diegosouzapw/awesome-omni-skill

Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory...

helix-memory

16
from diegosouzapw/awesome-omni-skill

Long-term memory system for Claude Code using HelixDB graph-vector database. Store and retrieve facts, preferences, context, and relationships across sessions using semantic search, reasoning chains, and time-window filtering.