confluence-assistant — Claude Code skill: what it does, how to install
confluence-assistant operates Confluence spaces through Atlassian MCP tools. Helps Claude Code search team documentation, create structured pages, and update existing entries using Markdown.
CC-BY-4.0 ★ 7,191 updated 2026-10-24
npx skills add tech-leads-club/agent-skills --skill confluence-assistant -a claude-codeWhat confluence-assistant does
The skill connects Claude Code to Confluence workflows via Atlassian MCP. It looks for a site URL such as https://example.atlassian.net/ or a Cloud ID UUID directly in the chat history. If neither exists, the agent prompts the user before running queries. Content discovery starts with search, using Rovo natural language search instead of raw keyword lookups.
When creating or modifying documentation via createConfluencePage or updateConfluencePage, the skill enforces Markdown. HTML syntax in the page body is strictly forbidden. It also separates numeric page identifiers, numeric space identifiers, and uppercase space keys to avoid failed API calls.
Without an active Atlassian MCP integration, this skill cannot make any calls. The instructions explicitly disallow using it for Jira tasks, local workspace files, or regular web browsing.
What it helps with
- search Confluence documentation with natural language queries
- publish new documentation pages formatted in Markdown
- update existing Confluence pages and append new sections
- browse Confluence spaces and list their contents
- add discussion comments to team pages
Example prompts for the agent
- Find the API documentation in Confluence and add a new section to it
- Create an ADR page titled ADR-001 in the TECH space
- Search our Confluence for onboarding guides and summarize what you find
How to install confluence-assistant
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill confluence-assistant -a claude-code2Manually: put the files in place
~/.claude/skills/confluence-assistant/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/confluence-assistant/
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill confluence-assistant -a codex2Manually: put the files in place
.agents/skills/confluence-assistant/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill confluence-assistant -a cursor2Manually: put the files in place
.cursor/skills/confluence-assistant/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install tech-leads-club/agent-skills 'packages/skills-catalog/skills/(development)/confluence-assistant'2Manually: put the files in place
.github/skills/confluence-assistant/SKILL.md1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill confluence-assistant -a gemini-cli2Platform CLI
gemini skills install https://github.com/tech-leads-club/agent-skills --path 'packages/skills-catalog/skills/(development)/confluence-assistant'Manually: put the files in place
.devin/skills/confluence-assistant/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about confluence-assistant
How do I install confluence-assistant in Claude Code?
Run npx skills add tech-leads-club/agent-skills --skill confluence-assistant -a claude-code in your terminal. You can also save the file directly to ~/.claude/skills/confluence-assistant/SKILL.md.
What does confluence-assistant do?
It directs Claude Code on how to query and edit Confluence via Atlassian MCP. It manages page searches, reads content by identifier, and formats page updates using Markdown.
What credentials or parameters are required?
You need a working Atlassian MCP server along with your Confluence URL (such as https://example.atlassian.net/) or Atlassian Cloud ID UUID.
Source text
SKILL.md · CC-BY-4.0
---
name: confluence-assistant
description: Expert in Confluence operations using Atlassian MCP. Use when the user says "search Confluence", "create a Confluence page", "update a page", "find documentation in Confluence", "list spaces", or "add a comment to a page". Do NOT use for Jira issues, general web search, or local file creation.
license: CC-BY-4.0
metadata:
author: Waldemar Neto - github.com/waldemarnt
version: '1.0.0'
---
# Confluence Assistant
You are an expert in using Atlassian MCP tools to interact with Confluence.
## When to Use
Use this skill when the user asks to:
- Search for Confluence pages or documentation
- Create new Confluence pages
- Update existing Confluence pages
- Navigate or list Confluence spaces
- Add comments to pages
- Get details about specific pages
## Configuration
**Project Detection Strategy (Automatic):**
1. **Check conversation context first**: Look for Cloud ID or Confluence URL already mentioned
2. **If not found**: Ask the user to provide their Cloud ID or Confluence site URL
3. **Use detected values** for all Confluence operations in this conversation
### Configuration Detection Workflow
When you activate this skill:
1. Check if Cloud ID or Confluence URL is already available in the conversation context
2. If not found, ask: "Which Confluence site should I use? Please provide a Cloud ID (UUID) or site URL (e.g. `https://example.atlassian.net/`)"
3. Use the provided value for all operations in this conversation
**Cloud ID format:**
- Can be a site URL (e.g., `https://example.atlassian.net/`)
- Can be a UUID from `getAccessibleAtlassianResources`
## Workflow
### 1. Finding Content (Always Start Here)
**Use `search` (Rovo Search) first** - it's the most efficient way:
```
search("natural language query about the content")
```
- Works with natural language
- Returns relevant pages quickly
- Most efficient first step
### 2. Getting Page Details
Depending on what you have:
- **If you have ARI** (Atlassian Resource Identifier): `fetch(ari)`
- **If you have page ID**: `getConfluencePage(cloudId, pageId)`
- **To list spaces**: `getConfluenceSpaces(cloudId, keys=["SPACE_KEY"])`
- **For pages in a space**: `getPagesInConfluenceSpace(cloudId, spaceId)`
### 3. Creating Pages
```
createConfluencePage(
cloudId,
spaceId="123456",
title="Page Title",
body="# Markdown Content\n\n## Section\nContent here..."
)
```
Always use **Markdown** in the `body` field — never HTML.
### 4. Updating Pages
```
updateConfluencePage(
cloudId,
pageId="123456",
title="Updated Title",
body="# Updated Markdown Content\n\n..."
)
```
Always use **Markdown** in the `body` field — never HTML.
## Best Practices
### ✅ DO
- **Always use Markdown** for page `body` field
- **Use `search` first** before other lookup methods
- **Use natural language** in search queries
- **Validate space exists** before creating pages
- **Include clear structure** in page content (headings, lists, etc.)
### ⚠️ IMPORTANT
- **Don't confuse:**
- Page ID (numeric) vs Space Key (string)
- Space ID (numeric) vs Space Key (CAPS_STRING)
- **CloudId** can be URL or UUID - both work
- **Use detected configuration** - Check conversation context or ask user for Cloud ID / URL
- **ARI format**: `ari:cloud:confluence:site-id:page/page-id`
## Examples
### Example 1: Search and Update a Page
```
User: "Find the API documentation page and add a new section"
1. search("API documentation")
2. getConfluencePage(cloudId, pageId="found-id")
3. updateConfluencePage(
cloudId,
pageId="found-id",
title="API Documentation",
body="# API Documentation\n\n## Existing Content\n...\n\n## New Section\nNew content here..."
)
```
### Example 2: Create a New Page in a Space
```
User: "Create a new architecture decision record"
1. getConfluenceSpaces(cloudId, keys=["TECH"])
2. createConfluencePage(
cloudId,
spaceId="space-id-from-step-1",
title="ADR-001: Use Microservices Architecture",
body="# ADR-001: Use Microservices Architecture\n\n## Status\nAccepted\n\n## Context\n...\n\n## Decision\n...\n\n## Consequences\n..."
)
```
### Example 3: Find and Read Page Content
```
User: "What's in our onboarding documentation?"
1. search("onboarding documentation")
2. getConfluencePage(cloudId, pageId="id-from-results")
3. Summarize the content for the user
```
## Output Format
When creating or updating pages, use well-structured Markdown:
```markdown
# Main Title
## Introduction
Brief overview of the topic.
## Sections
Organize content logically with:
- Clear headings (##, ###)
- Bullet points for lists
- Code blocks for examples
- Tables when appropriate
## Key Points
- Point 1
- Point 2
- Point 3
## Next Steps
1. Step 1
2. Step 2
3. Step 3
```
## Important Notes
- **Markdown is mandatory** — never use HTML or other formats in `body`
- **Search first** — most efficient way to find content
- **Validate IDs** — ensure space/page IDs exist before operations
- **Natural language** — Rovo Search understands intent, not just keywords
- **ID types** — don't confuse page ID (numeric) vs space key (string) vs space ID (numeric)
© Waldemar Neto - github.com/waldemarnt · CC-BY-4.0 · tech-leads-club/agent-skills