I
Archive
Verified@ivangdavila
npx machina-cli add skill @ivangdavila/archive --openclawFiles (1)
SKILL.md
3.4 KB
Architecture
Archive storage lives in ~/archive/ with tiered structure. See memory-template.md for setup.
~/archive/
├── memory.md # HOT: recent items, ≤100 lines
├── index.md # Topic/tag index
├── items/ # Individual archived items
├── projects/ # Per-project collections
└── history.md # Search/access history
Quick Reference
| Topic | File |
|---|---|
| What to capture | capture.md |
| Search patterns | search.md |
| Resurfacing rules | resurface.md |
Core Rules
1. Capture Complete, Not Just Links
When user sends something to archive:
- Extract full content (not just URL)
- Generate 2-3 line summary
- Identify key quotes/data points
- Ask: "What's this for?" — store the WHY alongside the WHAT
- Assign semantic tags based on content + user history
2. Content Types
| Type | What to extract |
|---|---|
| Article/webpage | Full text, author, date, key quotes |
| Video (YouTube) | Title, creator, duration, timestamps mentioned |
| Tweet/thread | Full text, author, context, media |
| PDF/paper | Title, authors, abstract, cited references |
| Image | Description, source, context given |
| Idea/note | Raw text + timestamp + related items |
3. Storage Structure
Each archived item stored as:
items/{date}_{slug}.md
---
type: article
url: original-url
archived: 2026-02-16
why: "research for pricing strategy"
tags: [pricing, saas, strategy]
project: clawmsg
---
## Summary
...
## Key Points
...
## Full Content
...
4. Semantic Search
User can ask naturally:
- "What did I save about X?" → search by concept
- "That article about pricing from last month" → fuzzy time + topic
- "Everything for project Y" → project filter
- "Papers by author Z" → metadata search
NEVER require exact keywords. Match by meaning.
5. Proactive Resurfacing
When user works on a topic:
- Check if archived items relate
- Surface ONLY if genuinely relevant (max 1-2 per session)
- Include context: "You saved this 3 months ago when researching X"
6. Never Delete Without Asking
- Old items → mark as "possibly outdated", don't delete
- Duplicates → merge, keep both URLs
- Project closed → archive to cold storage, don't remove
7. Differentiation from Other Skills
| This skill | What it does | NOT this |
|---|---|---|
| archive | Preserves external content as snapshots | memory (agent context) |
| archive | Captures full content for permanence | bookmark (just URLs) |
| archive | Stores raw material | second-brain (processed knowledge) |
| archive | Immutable snapshots | pkm (evolving notes) |
Scope
This skill ONLY:
- Stores content user explicitly sends to archive
- Searches within archived content
- Surfaces related items when contextually relevant
This skill NEVER:
- Monitors or observes without explicit request
- Deletes content without confirmation
- Modifies original archived content
- Accesses external services without user action
Data Storage
All data in ~/archive/. Create on first use:
mkdir -p ~/archive/items ~/archive/projects
Overview
Archive stores user-sent content as full snapshots with metadata, enabling semantic search and proactive resurfacing. It handles multiple content types (articles, videos, tweets, PDFs, images, notes) and tags items for fast retrieval.
How This Skill Works
Content is saved under ~/archive with a tiered structure (memory.md, index.md, items/, projects/, history.md). On capture, the system extracts full content, generates a 2-3 line summary, identifies key quotes or data points, and assigns semantic tags; semantic search and proactive resurfacing surface relevant items when context arises.
When to Use It
- You want to save a webpage or article for long-term research and reference.
- You need to preserve a video, PDF, or image with full metadata for future use.
- You want to retrieve past notes by topic, project, or author using semantic search.
- You’re researching a project and want related items resurfaced when context becomes relevant.
- You want a safe, non-destructive archive that never deletes without user confirmation.
Quick Start
- Step 1: Save content to Archive (articles, videos, tweets, PDFs, images, ideas).
- Step 2: Review the generated summary, key points, and semantic tags stored under ~/archive/items.
- Step 3: Use search or resurfacing to locate related items or surface context during work.
Best Practices
- Capture the full content, not just the URL, and include a 2-3 line summary.
- Always store the WHY alongside the WHAT to preserve purpose.
- Assign semantic tags aligned to content and your history to improve search.
- Review items marked as possibly outdated before deleting; merge duplicates if needed.
- Organize by project with the projects/ directory and preserve access history in history.md.
Example Use Cases
- Archive a pricing strategy article: full text, author, date, key quotes, and tags like pricing, saas, strategy.
- Save a YouTube video: title, creator, duration, and notable timestamps for quick reference.
- Preserve a Twitter thread: full text, author, context, and any attached media.
- Archive a research PDF: title, authors, abstract, and cited references for citation-ready notes.
- Collect project notes: raw text with timestamp and links to related items for cross-linking.
Frequently Asked Questions
Add this skill to your agents
