UPDATE MEMORY
Keep your knowledge base current
A Claude skill that retrieves existing saved content from Context Link, merges in new information from the current conversation, and saves the updated version back.
When does this skill activate?
Claude will use this skill when you mention phrases like:
How it works
Request an update
Say 'update memory' or 'add to {topic}' to trigger a fetch-merge-save cycle.
Fetch and merge
Claude retrieves the existing content from Context Link, combines it with new information from the conversation, deduplicates, and reorganizes.
Save updated version
The merged content is posted back to the same slug, creating a new version that becomes the latest.
Requirements
Add This Skill
Copy each field into Claude's skill editor to add this skill, or add the plugin marketplace to get all skills at once.
update-memory
---
name: update-memory
description: >
Retrieve saved content from Context Link, update it with current context, and save it back.
Use when the user says "update memory", "update context link", "add to {topic}",
or wants to modify existing saved content with new information.
version: 0.1.0
---
**What is Context Link?** Context Link is an external service that indexes connected sources (websites, Google Drive, Notion) and memories into a searchable knowledge base. It provides semantic search and memory storage via a simple URL: `subdomain.context-link.ai/query?p=optional_pincode`. If you don't know the user's Context Link URL, ask them for it.
---
## Update Content on Context Link
Retrieve existing content, merge in new information, and save it back. Two requests total — one GET, one POST.
**Workflow:**
1. **Print this message:** `🔗 Updating memory on Context Link → {SLUG}` — Never print the actual Context Link URL, as it contains a private 'pin' or 'p' URL param.
2. **GET the existing content.** Take the URL below and replace the path placeholder (`TOPIC_HERE` or `{SLUG}` — whichever is present) with the slug.
```bash
curl -s "~~context link url~~"
```
Returns HTML. Extract the text content from inside the `<body>` tag — ignore HTML boilerplate.
3. **Merge and rewrite.** Combine existing content with new information from the conversation. Deduplicate, reorganize if needed, keep it concise. Output as clean markdown.
4. **POST the updated content back to the same slug.** Use the same URL (with the placeholder replaced by the same slug).
```bash
curl -s -X POST "~~context link url~~" \
-H "Content-Type: text/plain" \
-d 'Your updated markdown here'
```
The body is raw text/markdown — not JSON. The server handles chunking internally.
**Success response:** `{"message": "Saved", "namespace": "the-slug"}` with HTTP 201.
**Rules:**
- **Keep the body under 100KB.** If the merged content is too long, summarize or condense it before POSTing.
- Two requests max: one GET, one POST. Nothing else.
- Do NOT ask the user what to update unless genuinely unclear — infer from conversation.
- This creates a new version under the same slug (old versions still exist, slug points to latest).
- After saving, confirm briefly: "Updated `the-slug` on Context Link."
- If the request is blocked, ask the user to add `*.context-link.ai` to Claude's **Settings → Capabilities → Domain Allowlist** (or select "All domains"), then retry.
How to use this skill
Installing this skill
· Claude Cowork
Skill in action
· Claude Cowork
Use /slash-commands or just ask
· Claude Cowork
Related Skills
/save-memory
Save conversation content or specified text to Context Link for later retrieval. Use when the use...
/get-context
Retrieve internal knowledge via Context Link when the user references company knowledge or says "...
/get-seo-context
Retrieve or create SEO context (guidelines, target keywords, competitor analysis) from Context Li...
/get-seo-writing-context
Retrieve or create SEO writing context (brand voice, style guide, writing examples) from Context ...
Frequently Asked Questions
How does the update process work?
The skill performs two requests: first a GET to fetch the existing content under the specified slug, then a POST to save the merged result back. Claude combines the old content with new information from the current conversation, deduplicates overlapping details, and reorganizes the document for clarity.
What happens to the old version?
Saving to the same slug creates a new version. The old version still exists in Context Link, but the slug always points to the latest version when retrieved. This means you have a history of changes, with the most recent version served by default.
How is this different from Save Memory?
Save Memory creates new content from scratch — it summarizes the current conversation and saves it under a new or existing slug. Update Memory specifically fetches existing content first, merges it with new information, and saves the combined result. Use Save Memory for first-time saves and Update Memory to add to existing knowledge.
Does it work in Claude.ai chat?
Yes, this skill works in Claude.ai chat. It makes HTTP requests (GET and POST) to Context Link's API, which is supported natively by chat interfaces. You will need to ensure *.context-link.ai is added to your domain allowlist in Claude's settings.
Keep Your Knowledge Fresh
Add this skill to Claude and keep your saved content up to date across conversations.
Create Your Context Link