Atlassian Admin
Atlassian product administration and organization management.
$skillfish add ~skills/atlassian-admin Real Conversations
See how the Atlassian Admin skill responds to actual requests. These are representative examples of what your AI agent will produce.
We have 150 users across Jira, Confluence, and Bitbucket. We just had a security audit and need to review who has admin access and remove people who left the company. How do I do this efficiently?
Atlassian Access Audit — 150 Users
Step 1: Export user list from Atlassian Admin
- Go to admin.atlassian.com → your organization
- Users → Export users (CSV) Columns: email, display name, product access, last active date, account status
Step 2: Cross-reference with HR offboarding list Match exported emails against your HR system's terminated employees list. In Google Sheets:
=IFERROR(VLOOKUP(A2, TerminatedList!A:A, 1, FALSE), "Active")
Flag all matches as "Immediate deactivation required."
Step 3: Admin access audit
Filter the export for users with org-admin or site-admin roles. Best practice:
- Org-admin: Maximum 2–3 people (IT leads only)
- Site-admin per product: Maximum 3–5 people
Step 4: Remediation actions
| Action | How | Timeline |
|---|---|---|
| Deactivate terminated users | Admin console → User → Deactivate | Immediate |
| Remove excess org-admins | Admin → Roles → Edit | This week |
| Enforce SSO | Admin → Security → SAML SSO | 30 days |
| Enable 2FA enforcement | Admin → Security → Two-step verification | 7 days |
Step 5: Prevent recurrence
- Connect Atlassian Access to your IdP (Okta, Azure AD) — users deprovisioned in IdP are automatically deactivated in Atlassian
- Set up a quarterly access review in your GRC tool or calendar
Want me to write the SAML SSO configuration steps for Okta or Azure AD?
Get Started
How to install and use this skill in your preferred environment.
Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.
Models & Context
Which AI models and context windows work best with this skill.
Recommended Models
Larger models produce more detailed, production-ready outputs.
Context Window
This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.
All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.
Pro tips for best results
Be specific
Include numbers — users, budget, RPS — so the skill can size the architecture.
Share constraints
Compliance needs, team size, and existing stack all improve the output.
Iterate
Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.
Combine skills
Pair with companion skills below for end-to-end coverage.
Ready to try Atlassian Admin?
Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.
$skillfish add ~skills/atlassian-admin