SkillAgentSearch skills...

confluence-automation

Automate Confluence page creation, content search, space management, labels, and hierarchy navigation via Rube MCP (Composio). Always search tools first for current schemas.

Install / Use

npx skills add davepoon/buildwithclaude --skill confluence-automation

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

87/100

Category

Automation

Supported Platforms

Universal

Our assessment of confluence-automation

confluence-automation scores 87/100 on our quality scale, 1614th of 2,790 Automation skills we index.

Its SKILL.md is 11 KB long, well organised into 18 sections and no code examples: a thorough specification that gives an agent plenty to work with.

With 3,752 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
13/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated today, so confluence-automation is actively maintained.
  • Our last check on 2026-11-01 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

Review

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs the agent to add https://rube.app/mcp as an MCP server, routing Confluence API traffic and OAuth flows through a third-party proxy.

AI review: risky

  • The skill instructs the agent to add https://rube.app/mcp as an MCP server, routing Confluence API traffic and OAuth flows through a third-party proxy.
  • It tells the agent to invoke RUBE_MANAGE_CONNECTIONS and follow returned auth links to establish an ACTIVE Confluence connection, handing credential/token management to an external service.
  • No malicious commands are present, but the setup meaningfully weakens safeguards by relying on an unofficial proxy for sensitive Confluence operations.

AI review by kimi-k2.7-code on 2026-10-02. Automated pattern scan on 2026-10-02. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

confluence-automation compared with similar skills

All 4 of these similar skills score higher than confluence-automation; compare them before choosing.

SkillScoreStarsUpdatedFormat
confluence-automation (this skill)by davepoon873.8ktodaySKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
CowAgentby zhayujie10048.0ktodayCLAUDE.md

Frequently asked questions

How do I install confluence-automation?
Run npx skills add davepoon/buildwithclaude --skill confluence-automation. The install tabs above show the steps for each supported agent.
Which AI agents does confluence-automation work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is confluence-automation safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs the agent to add https://rube.app/mcp as an MCP server, routing Confluence API traffic and OAuth flows through a third-party proxy. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is confluence-automation still maintained?
The repository was last updated today, so confluence-automation is actively maintained.

name: confluence-automation description: Automate Confluence page creation, content search, space management, labels, and hierarchy navigation via Rube MCP (Composio). Always search tools first for current schemas. requires: mcp: [rube] category: storage-docs

Confluence Automation via Rube MCP

Automate Confluence operations including page creation and updates, content search with CQL, space management, label tagging, and page hierarchy navigation through Composio's Confluence toolkit.

Toolkit docs: composio.dev/toolkits/confluence

Prerequisites

  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Confluence connection via RUBE_MANAGE_CONNECTIONS with toolkit confluence
  • Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

  1. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
  2. Call RUBE_MANAGE_CONNECTIONS with toolkit confluence
  3. If connection is not ACTIVE, follow the returned auth link to complete Confluence OAuth
  4. Confirm connection status shows ACTIVE before running any workflows

Core Workflows

1. Create and Update Pages

When to use: User wants to create new documentation or update existing Confluence pages

Tool sequence:

  1. CONFLUENCE_GET_SPACES - List spaces to find the target space ID [Prerequisite]
  2. CONFLUENCE_SEARCH_CONTENT - Find existing page to avoid duplicates or locate parent [Optional]
  3. CONFLUENCE_GET_PAGE_BY_ID - Get current page content and version number before updating [Prerequisite for updates]
  4. CONFLUENCE_CREATE_PAGE - Create a new page in a space [Required for creation]
  5. CONFLUENCE_UPDATE_PAGE - Update an existing page with new content and incremented version [Required for updates]
  6. CONFLUENCE_ADD_CONTENT_LABEL - Tag the page with labels after creation [Optional]

Key parameters:

  • spaceId: Space ID or key (e.g., "DOCS", "12345678") -- space keys are auto-converted to IDs
  • title: Page title (must be unique within a space)
  • parentId: Parent page ID for creating child pages; omit to place under space homepage
  • body.storage.value: HTML/XHTML content in Confluence storage format
  • body.storage.representation: Must be "storage" for create operations
  • version.number: For updates, must be current version + 1
  • version.message: Optional change description

Pitfalls:

  • Confluence enforces unique page titles per space; creating a page with a duplicate title will fail
  • UPDATE_PAGE requires version.number set to current version + 1; always fetch current version first with GET_PAGE_BY_ID
  • Content must be in Confluence storage format (XHTML), not plain text or Markdown
  • CREATE_PAGE uses body.storage.value while UPDATE_PAGE uses body.value with body.representation
  • GET_PAGE_BY_ID requires a numeric long ID, not a UUID or string

2. Search Content

When to use: User wants to find pages, blog posts, or content across Confluence

Tool sequence:

  1. CONFLUENCE_SEARCH_CONTENT - Keyword search with intelligent relevance ranking [Required]
  2. CONFLUENCE_CQL_SEARCH - Advanced search using Confluence Query Language [Alternative]
  3. CONFLUENCE_GET_PAGE_BY_ID - Hydrate full content for selected search results [Optional]
  4. CONFLUENCE_GET_PAGES - Browse pages sorted by date when search relevance is weak [Fallback]

Key parameters for SEARCH_CONTENT:

  • query: Search text matched against page titles with intelligent ranking
  • spaceKey: Limit search to a specific space
  • limit: Max results (default 25, max 250)
  • start: Pagination offset (0-based)

Key parameters for CQL_SEARCH:

  • cql: CQL query string (e.g., text ~ "API docs" AND space = DOCS AND type = page)
  • expand: Comma-separated properties (e.g., content.space, content.body.storage)
  • excerpt: highlight, indexed, or none
  • limit: Max results (max 250; reduced to 25-50 when using body expansions)

CQL operators and fields:

  • Fields: text, title, label, space, type, creator, lastModified, created, ancestor
  • Operators: =, !=, ~ (contains), !~, >, <, >=, <=, IN, NOT IN
  • Functions: currentUser(), now("-7d"), now("-30d")
  • Example: title ~ "meeting" AND lastModified > now("-7d") ORDER BY lastModified DESC

Pitfalls:

  • CONFLUENCE_SEARCH_CONTENT fetches up to 300 pages and applies client-side filtering -- not a true full-text search
  • CONFLUENCE_CQL_SEARCH is the real full-text search; use text ~ "term" for content body search
  • HTTP 429 rate limits can occur; throttle to ~2 requests/second with backoff
  • Using body expansions in CQL_SEARCH may reduce max results to 25-50
  • Search indexing is not immediate; recently created pages may not appear

3. Manage Spaces

When to use: User wants to list, create, or inspect Confluence spaces

Tool sequence:

  1. CONFLUENCE_GET_SPACES - List all spaces with optional filtering [Required]
  2. CONFLUENCE_GET_SPACE_BY_ID - Get detailed metadata for a specific space [Optional]
  3. CONFLUENCE_CREATE_SPACE - Create a new space with key and name [Optional]
  4. CONFLUENCE_GET_SPACE_PROPERTIES - Retrieve custom metadata stored as space properties [Optional]
  5. CONFLUENCE_GET_SPACE_CONTENTS - List pages, blog posts, or attachments in a space [Optional]
  6. CONFLUENCE_GET_LABELS_FOR_SPACE - List labels on a space [Optional]

Key parameters:

  • key: Space key -- alphanumeric only, no underscores or hyphens (e.g., DOCS, PROJECT1)
  • name: Human-readable space name
  • type: global or personal
  • status: current (active) or archived
  • spaceKey: For GET_SPACE_CONTENTS, filters by space key
  • id: Numeric space ID for GET_SPACE_BY_ID (NOT the space key)

Pitfalls:

  • Space keys must be alphanumeric only (no underscores, hyphens, or special characters)
  • GET_SPACE_BY_ID requires numeric space ID, not the space key; use GET_SPACES to find numeric IDs
  • Clickable space URLs may need assembly: join _links.webui (relative) with _links.base
  • Default pagination is 25; set limit explicitly (max 200 for spaces)

4. Navigate Page Hierarchy and Labels

When to use: User wants to explore page trees, child pages, ancestors, or manage labels

Tool sequence:

  1. CONFLUENCE_SEARCH_CONTENT - Find the target page ID [Prerequisite]
  2. CONFLUENCE_GET_CHILD_PAGES - List direct children of a parent page [Required]
  3. CONFLUENCE_GET_PAGE_ANCESTORS - Get the full ancestor chain for a page [Optional]
  4. CONFLUENCE_GET_LABELS_FOR_PAGE - List labels on a specific page [Optional]
  5. CONFLUENCE_ADD_CONTENT_LABEL - Add labels to a page [Optional]
  6. CONFLUENCE_GET_LABELS_FOR_SPACE_CONTENT - List labels across all content in a space [Optional]
  7. CONFLUENCE_GET_PAGE_VERSIONS - Audit edit history for a page [Optional]

Key parameters:

  • id: Page ID for child pages, ancestors, labels, and versions
  • cursor: Opaque pagination cursor for GET_CHILD_PAGES (from _links.next)
  • limit: Items per page (max 250 for child pages)
  • sort: Child page sort options: id, -id, created-date, -created-date, modified-date, -modified-date, child-position, -child-position

Pitfalls:

  • GET_CHILD_PAGES only returns direct children, not nested descendants; recurse for full tree
  • Pagination for GET_CHILD_PAGES uses cursor-based pagination (not start/limit)
  • Verify the correct page ID from search before using as parent; search can return similar titles
  • GET_PAGE_VERSIONS requires the page ID, not a version number

Common Patterns

ID Resolution

Always resolve human-readable names to IDs before operations:

  • Space key -> Space ID: CONFLUENCE_GET_SPACES with spaceKey filter, or CREATE_PAGE accepts space keys directly
  • Page title -> Page ID: CONFLUENCE_SEARCH_CONTENT with query param, then extract page ID
  • Space ID from URL: Extract numeric ID from Confluence URLs or use GET_SPACES

Pagination

Confluence uses two pagination styles:

  • Offset-based (most endpoints): start (0-based offset) + limit (page size). Increment start by limit until fewer results than limit are returned.
  • Cursor-based (GET_CHILD_PAGES, GET_PAGES): Use the cursor from _links.next in the response. Continue until no next link is present.

Content Formatting

  • Pages use Confluence storage format (XHTML), not Markdown
  • Basic elements: <p>, <h1>-<h6>, <strong>, <em>, <code>, <ul>, <ol>, <li>
  • Tables: <table><tbody><tr><th> / <td> structure
  • Macros: <ac:structured-macro ac:name="code"> for code blocks, etc.
  • Always wrap content in proper XHTML tags

Known Pitfalls

ID Formats

  • Space IDs are numeric (e.g., 557060); space keys are short strings (e.g., DOCS)
  • Page IDs are numeric long values for GET_PAGE_BY_ID; some tools accept UUID format
  • GET_SPACE_BY_ID requires numeric ID, not the space key
  • GET_PAGE_BY_ID takes an integer, not a string

Rate Limits

  • HTTP 429 can occur on search endpoints; honor Retry-After header
  • Throttle to ~2 requests/second with exponential backoff and jitter
  • Body expansion in CQL_SEARCH reduces result limits to 25-50

Content Format

  • Content must be Confluence storage format (XHTML), not Markdown or plain text
  • Invalid XHTML will cause page creation/update to fail
  • CREATE_PAGE nests body under body.storage.value; UPDATE_PAGE uses body.value + body.representation

Version Conflicts

  • Updates require exact next version number (current + 1)
  • Concurrent edits can cause version conflicts; always fetch current version immediately before updating
  • Title changes during update must still be unique within the space

Quick Reference

| Task | Tool Slug | Key Params | |------|-----------|------------| | List spaces | CONFLUENCE_GET_SPACES | type, status, limit | | Get space by ID | CONFLUENCE_GET_SPACE_BY_ID | id | | Create space | CONFLUENCE_CREATE_SPACE | key, name, type | | Space contents | CONFLUENCE_GET_SPACE_CONTENTS | spaceKey, type, status | | Space properties | CONFLUENCE_GET_SPACE_PROPERTIES | id, key | | Search content | CONFLUENCE_SEARCH_CONTENT | query, spaceKey, limit | | CQL search | CONFLUENCE_CQL_SEARCH | cql, expand, limit | | List pages | CONFLUENCE_GET_PAGES | spaceId, sort, limit | | Get page by ID | CONFLUENCE_GET_PAGE_BY_ID | id (integer) | | Create page | CONFLUENCE_CREATE_PAGE | title, spaceId, body | | Update page | CONFLUENCE_UPDATE_PAGE | id, title, body, version | | Delete page | CONFLUENCE_DELETE_PAGE | id | | Child pages | CONFLUENCE_GET_CHILD_PAGES | id, limit, sort | | Page ancestors | CONFLUENCE_GET_PAGE_ANCESTORS | id | | Page labels | CONFLUENCE_GET_LABELS_FOR_PAGE | id | | Add label | CONFLUENCE_ADD_CONTENT_LABEL | content ID, label | | Page versions | CONFLUENCE_GET_PAGE_VERSIONS | id | | Space labels | CONFLUENCE_GET_LABELS_FOR_SPACE | space ID |


Powered by Composio

Related Skills

View on GitHub
GitHub Stars3.8k
CategoryAutomation
Updated22h ago
Forks742

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions