Your AI Assistant. Your Documentation. Your Custom Tools.

Connect Claude, Cursor, and any AI assistant to your data through MCP or CLI. Build custom skills and agents that automate workflows, answer questions, and extend your docs with code.

MCP-compatible • Works with Claude Desktop, Cursor, and more

50+
Pre-Built Skills
Custom Agents
1-Click
MCP Setup
5min
First Agent Live

Skills vs Agents: Understanding the Ecosystem

Two powerful concepts that work together

Skills

Single-purpose tools

A skill is a reusable function that performs one specific task. Think of it as a building block.

Example: Search Skill
Searches documentation for a keyword and returns results
Example: Create Doc Skill
Creates a new document with specified content
Example: Tag Skill
Adds or removes tags from documents
Simple, focused, reusable
Can be chained together
Pre-built library available

Agents

Orchestrate multiple skills

An agent is an intelligent workflow that combines multiple skills to accomplish complex tasks autonomously.

Example: Onboarding Agent
Uses Search + Create + Tag skills to build personalized onboarding docs
Example: Support Agent
Searches docs, formats answers, logs tickets automatically
Example: Audit Agent
Scans docs for outdated content, suggests updates, notifies owners
Multi-step workflows
Decision-making logic
Runs autonomously or on-demand

How They Work Together

Agents orchestrate skills to accomplish complex tasks

Agent receives request
"Create onboarding doc for new engineer"
Agent executes skills:
1. Search for onboarding templates
2. Create new doc from template
3. Tag with #onboarding #engineering
4. Add to Onboarding workflow
Result
Complete onboarding doc ready

Identities: Give Your Agents a Voice

An agent knows what to do. An identity defines how it sounds. Attach an identity to a workflow and every agent inside it writes with a consistent voice, tone, and persona — automatically.

Person

A specific individual's voice — useful for ghostwriting, personal brand content, or an agent that speaks as a named expert on your team.

Company

Your brand voice — tone of voice guidelines, style rules, and communication principles encoded once and applied by every agent across every output.

Hybrid

A blend of person and brand — ideal for a founder who wants outputs that feel personal but stay on-brand, or a team persona that mixes individual warmth with company style.

Agent vs Identity — What's the Difference?

An Agent is the worker
It searches docs, creates content, sends notifications, and makes decisions. The agent handles the logic and sequencing.
An Identity is the voice
It shapes how the output reads — formal or casual, first-person or third, empathetic or direct. The identity adds the persona layer on top of the agent's work.
Together:
The agent produces the right content. The identity makes it sound exactly like you — every time.

Attach Once, Apply Everywhere

Attach an identity to a workflow and every agent in that workflow inherits it. No per-agent configuration needed.

Identity— "Friendly, direct, first-person, British English"
Workflow— "Customer Support" or "Content Creation"
Every agent in the workflow writes in that voice
Consistent output — regardless of which agent produced it

Example: Support Agent + Brand Identity

Without an identity
Support Agent reply:

"The error you encountered is caused by an invalid API key. Please verify your credentials in the dashboard settings and retry the request."

Generic, robotic — could have come from anywhere.

With a "Friendly Brand" identity attached
Same agent, same facts — different voice:

"Hey! Looks like your API key might be incorrect. Head over to your dashboard settings to double-check — should be a quick fix. Let us know if you're still stuck!"

On-brand, warm, recognisably you.

Connect Your AI to Your Documentation

Model Context Protocol (MCP) integration in 60 seconds

What is MCP?

Model Context Protocol is a universal standard that lets AI assistants (Claude Desktop, Cursor, etc.) connect to external data sources—like your Contextium documentation.

With MCP, your AI can:
Search your documentation
Read and analyze documents
Create and update docs
Execute your custom skills

Remote MCP — Nothing to Install

Contextium runs a hosted MCP server. Just paste a short config snippet into your AI tool—no packages, no dependencies.

// VS Code — settings or mcp.json
{
"servers": {
"contextium": {
"url": "https://mcp.contextium.io"
}
}
}

See It In Action: Asking Claude About Your Docs

You ask Claude:
"What's our API authentication flow? Search my Contextium docs."
Claude uses MCP to search Contextium...
Claude responds:

"Based on your API Security Guide (tagged #api #security):

1. Client requests access token using API key

2. Server validates key and issues JWT token

3. Client includes token in Authorization header

4. Token expires after 24 hours, refresh required

Source: API-Security-Guide.md (updated 2 days ago)"

Claude searched your docs, found the right document, and gave you the exact answer—all in one conversation.

50+ Pre-Built Skills Ready to Use

Start with our library, then build your own

Search & Discovery

  • Semantic search across all docs
  • Tag-based filtering
  • Find similar documents
  • Full-text search with regex

Document Management

  • Create documents from templates
  • Update content programmatically
  • Bulk operations (tag, move, archive)
  • Version control and rollback

Organization

  • Add inline #tags to your files
  • Create and manage workflows
  • Find files by tag across your workspace
  • Archive outdated documents

Integrations

  • Slack notifications
  • GitHub webhook triggers
  • Email digest reports
  • Webhook endpoints (custom)

Analytics & Insights

  • Generate usage reports
  • Find outdated documents
  • Content quality scoring
  • Tag usage analytics

Automation

  • Scheduled backups
  • Auto-generate changelogs
  • Sync with external sources
  • Trigger workflows on events

Agents in Action: Real Project Workflows

See how teams use agents to automate documentation tasks

Automated Onboarding Agent

Generates personalized onboarding documentation for new team members in seconds.

Agent Workflow:
1. Detect: New team member added to workspace
2. Search: Find onboarding template for their department
3. Create: Generate personalized doc with their name, role, team
4. Tag: Add #onboarding #new-hire #[department]
5. Notify: Send Slack message with doc link to new hire and manager
Result: 2 hours → 30 seconds
Skills used: Search, Create, Tag, Notify

Customer Support Bot Agent

Answers customer questions from your docs, creates tickets for unresolved issues.

Agent Workflow:
1. Receive: Customer question via Slack/email
2. Search: Semantic search across #support #faq docs
3. Analyze: Determine if answer is found and accurate
4. Respond: Format answer with source citations
5. Escalate: If no answer found, create support ticket with context
Result: 80% questions auto-resolved
Skills used: Search, Analyze, Format, Create Ticket

Documentation Audit Agent

Scans all documentation weekly, finds outdated content, notifies owners to update.

Agent Workflow:
1. Scan: Check all docs not updated in 90+ days
2. Analyze: Check for broken links, outdated versions, deprecated info
3. Tag: Add #needs-review to flagged documents
4. Report: Generate report with findings
5. Notify: Email document owners with action items
Result: 95% documentation accuracy
Skills used: Scan, Analyze, Tag, Report, Notify

Build Your Own Skills & Agents

Easy-to-use SDK with full documentation

Create a Custom Skill

import { Skill } from '@contextium/sdk';

export const mySkill = new Skill({
  name: 'generate-summary',
  description: 'Generates a summary',

  async execute(docs) {
    // Your logic here
    const summary = analyzeDocs(docs);
    return summary;
  }
});

Deploy to Contextium and it's instantly available to all your agents and AI assistants.

Create a Custom Agent

import { Agent } from '@contextium/sdk';

export const myAgent = new Agent({
  name: 'onboarding-bot',

  async run(input) {
    // Chain multiple skills
    const template = await search();
    const doc = await create(template);
    await tag(doc, ['onboarding']);
    await notify(input.user);
  }
});

Agents can orchestrate multiple skills, make decisions, and run on schedules or triggers.

Ready to Build Your Documentation Platform?

Start with pre-built skills, connect your AI, and build custom agents for your unique workflows.

Skills & Agents Work Better With the Full Stack

Skills & Agents are one layer of a complete AI collaboration platform

Agents Are Loaded Per Workflow

Each workflow specifies which agents to load at session start. Your code review agent loads for the Engineering workflow, your content agent for Marketing — the right specialist is always in context, automatically.

Learn about Workflows

Planner, Builder, Reviewer Power Projects

The three core project roles are agents. The Planner writes the spec. The Builder implements phase by phase. The Reviewer grades before anything is marked complete. Build them once, reuse them across every project in your workspace.

Learn about Projects

Agents Read Your Task List

When an agent loads a workflow, it reads the active task list — status, priority, assignee, and due date. It picks up in-progress work first, then moves to the highest-priority to-do. No briefing needed between sessions.

Learn about Tasks

Publish Your Best Agents to the Marketplace

Once your agent is polished, publish it to the Contextium Marketplace for other teams to use. Browse hundreds of ready-made specialist agents — or install community-built ones into your workspace in a single click.

Learn about the Marketplace