{"skill":{"slug":"memory","displayName":"Memory","summary":"Infinite organized memory that complements your agent's built-in memory with unlimited categorized storage.","description":"---\nname: Memory\nslug: memory\nversion: 1.0.2\nhomepage: https://clawic.com/skills/memory\ndescription: Infinite organized memory that complements your agent's built-in memory with unlimited categorized storage.\nchangelog: Redesigned as complementary system, user-defined categories, optional sync from built-in memory.\nmetadata: {\"clawdbot\":{\"emoji\":\"🧠\",\"requires\":{\"bins\":[]},\"os\":[\"linux\",\"darwin\",\"win32\"]}}\n---\n\n# Memory 🧠\n\n**Superpowered memory that never forgets.**\n\nYour agent has basic built-in memory. This skill adds infinite, perfectly organized memory for everything else — parallel and complementary, never conflicting.\n\n## How It Works\n\n```\nBuilt-in Agent Memory          This Skill (~/memory/)\n┌─────────────────────┐        ┌─────────────────────────────┐\n│ MEMORY.md           │        │ Infinite categorized storage │\n│ memory/ (daily logs)│   +    │ Any structure you want       │\n│ Basic recall        │        │ Perfect organization         │\n└─────────────────────┘        └─────────────────────────────┘\n         ↓                                  ↓\n   Agent basics                    Everything else\n   (works automatically)           (scales infinitely)\n```\n\n**Not a replacement.** Your agent's built-in memory keeps working. This adds a parallel system for unlimited, organized storage.\n\n## Setup\n\nOn first use, read `setup.md` to configure the memory system with the user. Key decisions:\n1. What categories do they need?\n2. Should we sync anything from built-in memory?\n3. How do they want to find things?\n\n## When to Use\n\nUser needs organized long-term storage beyond basic agent memory: detailed project histories, extensive contact networks, decision logs, domain knowledge, collections, or any structured data that grows over time.\n\n## Architecture\n\nMemory lives in `~/memory/` — a dedicated folder separate from built-in agent memory.\n\n```\n~/memory/\n├── config.md              # System configuration\n├── INDEX.md               # What's stored, where to find it\n│\n├── [user-defined]/        # Categories the user needs\n│   ├── INDEX.md           # Category overview\n│   └── {items}.md         # Individual entries\n│\n└── sync/                  # Optional: synced from built-in memory\n    └── ...\n```\n\n**The user defines the categories.** Common examples:\n- `projects/` — detailed project context\n- `people/` — contact network with full context\n- `decisions/` — reasoning behind choices\n- `knowledge/` — domain expertise, reference material\n- `collections/` — books, recipes, anything they collect\n\nSee `memory-template.md` for all templates.\n\n## Quick Reference\n\n| Topic | File |\n|-------|------|\n| First-time setup | `setup.md` |\n| All templates | `memory-template.md` |\n| Organization patterns | `patterns.md` |\n| Problems & fixes | `troubleshooting.md` |\n\n---\n\n## Core Rules\n\n### 1. Separate from Built-In Memory\n\nThis system lives in `~/memory/`. Never modify:\n- Agent's MEMORY.md (workspace root)\n- Agent's `memory/` folder (if it exists in workspace)\n\n**Parallel, not replacement.** Both systems work together.\n\n### 2. User Defines Structure\n\nDuring setup, ask what they want to store. Create categories based on their needs:\n\n| They say... | Create |\n|-------------|--------|\n| \"I have many projects\" | `~/memory/projects/` |\n| \"I meet lots of people\" | `~/memory/people/` |\n| \"I want to track decisions\" | `~/memory/decisions/` |\n| \"I'm learning [topic]\" | `~/memory/knowledge/[topic]/` |\n| \"I collect [things]\" | `~/memory/collections/[things]/` |\n\n**No preset structure.** Build what they need.\n\n### 3. Every Category Has an Index\n\nEach folder gets an INDEX.md that lists contents:\n\n```markdown\n# Projects Index\n\n| Name | Status | Updated | File |\n|------|--------|---------|------|\n| Alpha | Active | 2026-02 | alpha.md |\n| Beta | Paused | 2026-01 | beta.md |\n\nTotal: 2 active, 5 archived\n```\n\nIndices stay small (<100 entries). When full, split into subcategories.\n\n### 4. Write Immediately\n\nWhen user shares important information:\n1. Write to appropriate file in ~/memory/\n2. Update the category INDEX.md\n3. Then respond\n\nDon't wait. Don't batch. Write immediately.\n\n### 5. Search Then Navigate\n\nTo find information:\n1. **Ask first:** \"Is this in ~/memory/ or built-in memory?\"\n2. **Search:** grep or semantic search in ~/memory/\n3. **Navigate:** INDEX.md → category → specific file\n\n```bash\n# Quick search\ngrep -r \"keyword\" ~/memory/\n\n# Navigate\ncat ~/memory/INDEX.md           # What categories exist?\ncat ~/memory/projects/INDEX.md  # What projects?\ncat ~/memory/projects/alpha.md  # Specific project\n```\n\n### 6. Sync from Built-In (Optional)\n\nIf user wants certain info copied from built-in memory:\n\n```\n~/memory/sync/\n├── preferences.md    # Synced from built-in\n└── decisions.md      # Synced from built-in\n```\n\n**Sync is one-way:** Built-in → this system. Never modify built-in.\n\n### 7. Scale by Splitting\n\nWhen a category grows large:\n- INDEX.md > 100 entries → split into subcategories\n- Create sub-INDEX.md for each subcategory\n- Root INDEX.md points to subcategories\n\n```\n~/memory/projects/\n├── INDEX.md           # \"See active/, archived/\"\n├── active/\n│   ├── INDEX.md       # 30 active projects\n│   └── ...\n└── archived/\n    ├── INDEX.md       # 200 archived projects\n    └── ...\n```\n\n---\n\n## What to Store Here (vs Built-In)\n\n| Store HERE (~/memory/) | Keep in BUILT-IN |\n|------------------------|------------------|\n| Detailed project histories | Current project status |\n| Full contact profiles | Key contacts quick-ref |\n| All decision reasoning | Recent decisions |\n| Domain knowledge bases | Quick facts |\n| Collections, inventories | — |\n| Anything that grows large | Summaries |\n\n**Rule:** Built-in for quick context. Here for depth and scale.\n\n---\n\n## Finding Things\n\n### For Small Memory (<50 files)\n```bash\n# Grep is fast enough\ngrep -r \"keyword\" ~/memory/\n```\n\n### For Large Memory (50+ files)\nNavigate via indices:\n```\n1. ~/memory/INDEX.md → find category\n2. ~/memory/{category}/INDEX.md → find item\n3. ~/memory/{category}/{item}.md → read details\n```\n\n### For Huge Memory (500+ files)\nUse semantic search if available, or hierarchical indices:\n```\n~/memory/projects/INDEX.md → \"web projects in web/\"\n~/memory/projects/web/INDEX.md → \"alpha project\"\n~/memory/projects/web/alpha.md → details\n```\n\n---\n\n## Maintenance\n\n### Weekly (5 min)\n- Update INDEX.md files if entries added\n- Archive completed/inactive items\n\n### Monthly (15 min)\n- Review category sizes\n- Split large categories\n- Remove outdated entries\n\n### When Memory is Slow\n- Check INDEX.md sizes (keep <100 lines)\n- Split big categories into subcategories\n- Archive old content\n\n---\n\n## Common Traps\n\n- **Modifying built-in memory** → Never touch agent's MEMORY.md or workspace memory/. This system is parallel.\n\n- **No indices** → Without INDEX.md, finding things requires searching all files. Always maintain indices.\n\n- **One giant category** → 500 items in one folder is slow. Split into subcategories.\n\n- **Syncing everything** → Don't copy all built-in memory. Only sync what needs organization here.\n\n- **Waiting to write** → Write immediately when user shares info. Don't batch.\n\n---\n\n## Security & Privacy\n\n**Data location:**\n- All data in `~/memory/` on user's machine\n- No external services required\n- No network requests\n\n**This skill does NOT:**\n- Access built-in agent memory (only reads if syncing)\n- Send data anywhere\n- Store credentials (never store secrets in memory)\n\n---\n\n## Related Skills\nInstall with `clawhub install <slug>` if user confirms:\n- `decide` - Decision tracking patterns\n- `escalate` - When to involve humans\n- `learn` - Adaptive learning\n\n## Feedback\n\n- If useful: `clawhub star memory`\n- Stay updated: `clawhub sync`\n","tags":{"latest":"1.0.2"},"stats":{"comments":0,"downloads":16441,"installsAllTime":249,"installsCurrent":249,"stars":17,"versions":3},"createdAt":1770671754795,"updatedAt":1778989303952},"latestVersion":{"version":"1.0.2","createdAt":1771774645950,"changelog":"Redesigned as complementary system, user-defined categories, optional sync from built-in memory.","license":null},"metadata":{"setup":[],"os":["linux","darwin","win32"],"systems":null},"owner":{"handle":"ivangdavila","userId":"s178jdk12x4qj3gs2se3etxf3h83h7ft","displayName":"Iván","image":"https://avatars.githubusercontent.com/u/81719670?v=4"},"moderation":null}