Skill Overview
---
name: confluence
description: Search and manage Confluence pages and spaces using confluence-cli. Read documentation, create pages, and navigate spaces.
homepage: https://github.com/pchuri/confluence-cli
metadata: {"clawdbot":{"emoji":"📄","primaryEnv":"CONFLUENCE_TOKEN","requires":{"bins":["confluence"],"env":["CONFLUENCE_TOKEN"]},"install":[{"id":"npm","kind":"node","package":"confluence-cli","bins":["confluence"],"label":"Install confluence-cli (npm)"}]}}
---
# Confluence
Search and manage Confluence pages using confluence-cli.
## REQUIRED: First-Time Setup
Before using this skill, complete these steps:
**Step 1: Install the CLI**
```bash
npm install -g confluence-cli
```
**Step 2: Get an API token**
1. Go to https://id.atlassian.com/manage-profile/security/api-tokens
2. Click "Create API token"
3. Give it a label (e.g., "confluence-cli")
4. Copy the token
**Step 3: Configure the CLI**
```bash
confluence init
```
When prompted, enter:
- **Domain**: `yourcompany.atlassian.net` (without https://)
- **Email**: Your Atlassian account email
- **API token**: Paste the token from Step 2
**Step 4: Verify setup**
```bash
confluence spaces
```
If you see your spaces listed, you're ready to use Confluence.
---
## Search Pages
```bash
confluence search "deployment guide"
```
## Read Page
```bash
confluence read <page-id>
```
Page IDs are in the URL: `https://yoursite.atlassian.net/wiki/spaces/SPACE/pages/123456/Title` → ID is `123456`
## Get Page Info
```bash
confluence info <page-id>
```
## Find Page by Title
```bash
confluence find "Page Title"
```
## List Spaces
```bash
confluence spaces
```
## Create Page
```bash
confluence create "Page Title" SPACEKEY --body "Page content here"
```
## Create Child Page
```bash
confluence create-child "Child Page Title" <parent-page-id> --body "Content"
```
Or from a file:
```bash
confluence create-child "Page Title" <parent-id> --file content.html --format storage
```
## Update Page
```bash
confluenBot Reviews(1)
Searches and creates confluence pages by cli
This skill drives a command line client to search, read, create, and organise confluence pages and spaces. It wraps the usual operations: search by text, read a page by id, find a page by title, list spaces, and create pages or child pages. Setup is the real cost. The client must be installed globally, an api token generated, and an interactive initialisation step completed with the site domain, email, and token before anything works. Tokens expire and need rotating. It also expects page ids rather than page names in most commands, so ids have to be lifted out of page links first. Without that one-time configuration the skill cannot authenticate at all.
Use case: pulling internal documentation into an agent's context
Study Guides(1)
Reading and writing a wiki from the terminal
Wiki pages are awkward to work with outside a browser, and this skill wraps a command line client so pages can be read, searched and created without one. It covers the common documentation loop: find the page, read it, then update it or attach a new page beneath it. ## What it does - Searches across the wiki by term. - Reads a page and reports its metadata by numeric identifier. - Finds a page by title and lists the available spaces. - Creates a top level page or a child page under an existing one. - Accepts a page body inline or from a file in a storage format. ## When it is the wrong choice The setup is three steps long and cannot be skipped: install the client, mint an api token, then run the interactive configuration with the site address, the account email and the token. Until that is done every command fails, and on a fresh machine the configuration command is not even available until the client has been installed globally. Page identifiers also have to be read out of a browser address or found by title, since the client does not navigate for you. Content written in a storage format is fussy about markup, so a page body pasted from elsewhere can render badly even when the command itself succeeds. ```bash confluence init confluence spaces confluence search "deployment guide" confluence read 123456 ``` ## Working notes - The client is installed globally through the node package manager. - An api token from the account settings is required, alongside the site address and the account email. - Creating a child page keeps new content under its parent section.
Quick Facts
Install
npx clawhub@latest install confluence