Atlassian Confluence expert for creating and managing spaces, knowledge bases, and documentation. Configures space permissions and hierarchies, creates page templates with macros, sets up documentation taxonomies, designs page layouts, and manages content governance. Use when users need to build or restructure a Confluence space, design page hierarchies with permission structures, author or standardise documentation templates, embed Jira reports in pages, run knowledge base audits, or establish documentation standards and collaborative workflows.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Master-level expertise in Confluence space management, documentation architecture, content creation, macros, templates, and collaborative knowledge management.
Primary Tool: Atlassian Remote MCP server (bundled .mcp.json, server key atlassian). Tools are camelCase and surface as mcp__atlassian__<toolName>. Canonical tool list: project-management/references/atlassian-mcp-tools.md. Never invent tool names — if a capability isn't in that list, it is not available via MCP.
Key Operations (obtain cloudId once via mcp__atlassian__getAccessibleAtlassianResources):
// List spaces (space CREATION is not available via MCP — see below)
mcp__atlassian__getConfluenceSpaces (cloudId)
// Create a page under a parent — body must be storage-format XHTML or ADF, never wiki markup
mcp__atlassian__createConfluencePage (cloudId, space, title="Sprint 42 Notes", parent page id, body="<p>Meeting notes in storage-format XHTML</p>")
// Update an existing page (fetch current version with getConfluencePage, then supply version + 1)
mcp__atlassian__updateConfluencePage (cloudId, pageId="789012", version=5, body="<p>Updated content</p>")
// Read a page (body + current version)
mcp__atlassian__getConfluencePage (cloudId, pageId="789012")
// Search with CQL
mcp__atlassian__searchConfluenceUsingCql (cloudId, cql='space = "TEAM" AND label = "meeting-notes" ORDER BY lastModified DESC')
// Retrieve child pages for hierarchy inspection
mcp__atlassian__getConfluencePageDescendants (cloudId, pageId="123456")
// Comments
mcp__atlassian__getConfluencePageFooterComments / mcp__atlassian__createConfluenceFooterComment (cloudId, pageId)
Not available via MCP — use the web UI or REST API instead:
Spaces > Create space or POST /wiki/api/v2/spacesDELETE /wiki/api/v2/pages/{id}/wiki/rest/api/content/{id}/labelIntegration Points:
See also:
references/macro-cheat-sheet.mdfor storage-format macro syntax,references/templates.mdfor the template library,references/space-architecture-patterns.mdfor space structure and permission patterns.
Space creation is not available via MCP — create the space in the Confluence UI (
Spaces > Create space) or via REST (POST /wiki/api/v2/spaces). The page tree inside it CAN be built via MCP (mcp__atlassian__createConfluencePage).
python3 scripts/space_structure_generator.py team_info.json --format json
name, size, type, projects. Consume the output: use the emitted page tree as the creation plan for step 5 — one mcp__atlassian__createConfluencePage call per node, passing the parent page id to nest children.Best Practices:
Recommended Structure:
Space Home
├── Overview & Getting Started
├── Team Information
│ ├── Team Members & Roles
│ ├── Communication Channels
│ └── Working Agreements
├── Projects
│ ├── Project A
│ │ ├── Overview
│ │ ├── Requirements
│ │ └── Meeting Notes
│ └── Project B
├── Processes & Workflows
├── Meeting Notes (Archive)
└── Resources & References
Run a content health audit before any restructure or governance review:
python3 scripts/content_audit_analyzer.py pages.json --format json
Input: a JSON page inventory (title, last_modified, view_count, author, labels, word_count) — build it by exporting page metadata via mcp__atlassian__getPagesInConfluenceSpace / mcp__atlassian__searchConfluenceUsingCql. Consume the output: the stale/orphaned/low-engagement findings become the archive list (label + move via UI, since label tools aren't on the MCP) and the update backlog for the quality standards below.
Article Types:
Quality Standards:
Syntax note: The
{macro}shorthand below is legacy wiki-markup notation, shown for readability only. Confluence Cloud pages created via MCP (createConfluencePage/updateConfluencePage) require storage format (XHTML) — e.g.{info}is really<ac:structured-macro ac:name="info"><ac:rich-text-body>...</ac:rich-text-body></ac:structured-macro>. For the storage-format syntax of every macro listed here, seereferences/macro-cheat-sheet.md; for ready-made storage-format page bodies, run the atlassian-templates scaffolder (python3 ../atlassian-templates/scripts/template_scaffolder.py meeting-notes).
Info, Note, Warning, Tip:
{info}
Important information here
{info}
Expand:
{expand:title=Click to expand}
Hidden content here
{expand}
Table of Contents:
{toc:maxLevel=3}
Excerpt & Excerpt Include:
{excerpt}
Reusable content
{excerpt}
{excerpt-include:Page Name}
Jira Issues:
{jira:JQL=project = PROJ AND status = "In Progress"}
Jira Chart:
{jirachart:type=pie|jql=project = PROJ|statType=statuses}
Recently Updated:
{recently-updated:spaces=@all|max=10}
Content by Label:
{contentbylabel:label=meeting-notes|maxResults=20}
Status:
{status:colour=Green|title=Approved}
Task List:
{tasks}
- [ ] Task 1
- [x] Task 2 completed
{tasks}
User Mention:
@username
Date:
{date:format=dd MMM yyyy}
Two-Column Layout:
{section}
{column:width=50%}
Left content
{column}
{column:width=50%}
Right content
{column}
{section}
Panel:
{panel:title=Panel Title|borderColor=#ccc}
Panel content
{panel}
Code Block:
{code:javascript}
const example = "code here";
{code}
Full template library with complete markup: see
references/templates.md. Key templates summarised below.
| Template | Purpose | Key Sections |
|---|---|---|
| Meeting Notes | Sprint/team meetings | Agenda, Discussion, Decisions, Action Items (tasks macro) |
| Project Overview | Project kickoff & status | Quick Facts panel, Objectives, Stakeholders table, Milestones (Jira macro), Risks |
| Decision Log | Architectural/strategic decisions | Context, Options Considered, Decision, Consequences, Next Steps |
| Sprint Retrospective | Agile ceremony docs | What Went Well (info), What Didn't (warning), Action Items (tasks), Metrics |
Permission patterns by space type: see
references/space-architecture-patterns.md. Note: space permissions are configured in the Confluence UI (Space settings > Permissions) — not via MCP.
Public Space:
Team Space:
Project Space:
Review Cycles:
Archiving Strategy:
Content Quality Checklist:
When to Escalate to Atlassian Admin:
When to Collaborate with Jira Expert:
When to Support Scrum Master:
When to Support Senior PM:
FROM Senior PM:
TO Senior PM:
FROM Scrum Master:
TO Scrum Master:
WITH Jira Expert:
Organization:
Maintenance:
Usage Metrics:
Health Indicators:
project-management/jira-expert/) — Jira issue macros and linking complement Confluence docsproject-management/atlassian-templates/) — Template patterns for Confluence content creationまだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
日本語の概要は準備中です。原文の説明を表示しています。
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
日本語の概要は準備中です。原文の説明を表示しています。
When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
日本語の概要は準備中です。原文の説明を表示しています。
Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
日本語の概要は準備中です。原文の説明を表示しています。
Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
日本語の概要は準備中です。原文の説明を表示しています。
Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
日本語の概要は準備中です。原文の説明を表示しています。