GET CONTEXT
Your knowledge, always available to Claude
A Claude skill that retrieves internal knowledge, brand guidelines, documentation, and saved context from your Context Link knowledge base — instantly available in any conversation.
When does this skill activate?
Claude will use this skill when you mention phrases like:
How it works
Ask for context
Mention a topic or say 'get context' to trigger a knowledge base lookup.
Semantic search
Context Link searches your connected sources using vector embeddings to find the most relevant content.
Informed responses
Claude uses the retrieved context to give answers grounded in your actual company knowledge.
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.
get-context
---
name: get-context
description: >
Retrieve internal knowledge via Context Link when the user references company knowledge
or says "get context", "use context link", "check context link", or asks about internal
information that may be stored in their knowledge base.
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 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.
---
## Get Context from Context Link
Retrieve content from the user's Context Link knowledge base.
**When to use:** The user references internal company knowledge, brand positioning, saved content, or says "get context" / "use context link."
**Workflow:**
1. **Print this message:** `🔗 Retrieving context on {TOPIC} from Context Link` — Never print the actual Context Link URL, as it contains a private 'pin' or 'p' URL param.
2. **Determine the topic.** Use the phrase the user requested, or infer the general topic from conversation context. Lowercase it, replace spaces with dashes.
3. **Send a GET request.** Take the URL below and replace the path placeholder (`TOPIC_HERE` or `{SLUG}` — whichever is present) with the topic slug (lowercase, dashes-for-spaces).
```bash
curl -s "~~context link url~~"
```
4. **Handle the response.**
- The response is HTML. Extract the text content from inside the `<body>` tag — ignore HTML boilerplate.
- Use the returned content as the primary source material for answering the user's question.
- Supplement with external sources only if the Context Link data is insufficient.
5. **If the request fails or returns empty**, report the failure explicitly before continuing. Do not silently skip retrieval.
**Rules:**
- Always attempt retrieval before answering questions about internal/company knowledge.
- Do not ask the user what topic to search unless truly ambiguous — infer from context.
- One GET request per query. Do not retry unless the user asks.
- 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...
/update-memory
Retrieve saved content from Context Link, update it with current context, and save it back. Use w...
/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
What sources can Context Link connect to?
Context Link indexes content from websites (via sitemap crawling), Google Drive documents, Notion pages, and manually saved memories. All content is converted to vector embeddings for semantic search.
How does the retrieval work?
When you ask for context, the skill calls Context Link's API with your query. It uses cosine similarity search over vector embeddings to find the most relevant chunks of content, then returns them for Claude to use.
Is my data private?
Yes. Your content is stored in your own Context Link account and only accessible via your authenticated API. Each organisation has its own isolated knowledge base.
Can I use this in Claude.ai chat?
Yes, this skill works in Claude.ai, ChatGPT, and similar chat interfaces. It makes HTTP requests to Context Link's API, which is supported natively by these platforms.
How is this different from Claude's built-in knowledge?
Claude's training data is fixed and general. Context Link gives Claude access to your specific, up-to-date company knowledge — brand guidelines, product docs, SOPs, meeting notes, and anything else you've connected.
Connect Your Knowledge
Add this skill to Claude and give it access to your company knowledge base.
Create Your Context Link