Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Administer the Atlassian suite (Jira/Confluence): user provisioning, groups, SSO/SAML, permissions, security policies, marketplace apps, backups, and org-wide governance. Use for admin config, access management, and system optimization.
.claude/skills/borghei-atlassian-admin/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 24% | 0% |
System administrator with deep expertise in Atlassian Cloud/Data Center management, user provisioning, security, integrations, and org-wide configuration and governance.
Load the reference that matches the task — keep this file lean and pull detail on demand:
In Scope: User provisioning and deprovisioning, group and permission management, SSO/SAML configuration, marketplace app lifecycle management, system performance optimization, security policy enforcement, backup and disaster recovery, audit logging and compliance, global configuration of Jira and Confluence settings, integration management.
Out of Scope: Project-specific Jira configuration (hand off to jira-expert/), space-specific Confluence setup (hand off to confluence-expert/), sprint execution (hand off to scrum-master/), strategic planning (hand off to senior-pm/), template content design (hand off to atlassian-templates/).
Limitations: Atlassian Cloud admin capabilities are constrained by plan tier (Free, Standard, Premium, Enterprise). Some admin operations (data residency, advanced audit logs) require Premium or Enterprise plans. SCIM auto-provisioning depends on IdP compatibility -- not all identity providers support the full SCIM 2.0 spec. Backup frequency and granularity differ between Cloud and Data Center editions.
| Integration | Direction | What Flows | |-------------|-----------|------------| | jira-expert/ | Admin -> Jira | Global workflow schemes, custom field creation, permission scheme deployment | | confluence-expert/ | Admin -> Confluence | Global templates, space permission schemes, blueprint configuration | | atlassian-templates/ | Admin -> Templates | Template governance policies, global template deployment approval | | senior-pm/ | Admin -> PM | Usage analytics, capacity planning data, cost optimization recommendations | | scrum-master/ | Admin -> SM | Team access provisioning, board configuration capabilities | | agile-coach/ | Admin -> Coach | Organizational user data for team structure mapping |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,122 | 19,274 | -9% | 1 | 1 | 0% | 2,999 | 4,067 | +36% | 0 | 0 | — |
case-02 | fail→fail | 14,210 | 13,222 | -7% | 1 | 1 | 0% | 2,279 | 2,753 | +21% | 0 | 0 | — |
case-03 | fail→fail | 9,673 | 9,802 | +1% | 1 | 1 | 0% | 1,661 | 2,358 | +42% | 0 | 0 | — |
case-04 | fail→fail | 13,264 | 11,557 | -13% | 1 | 1 | 0% | 2,003 | 2,455 | +23% | 0 | 0 | — |
case-05 | fail→fail | 16,377 | 14,474 | -12% | 1 | 1 | 0% | 2,513 | 3,003 | +19% | 0 | 0 | — |
case-06 | fail→pass | 9,939 | 10,371 | +4% | 1 | 1 | 0% | 1,627 | 2,366 | +45% | 0 | 0 | — |
case-07 | pass→pass | 19,416 | 17,912 | -8% | 1 | 1 | 0% | 2,889 | 3,573 | +24% | 0 | 0 | — |
case-08 | fail→pass | 17,198 | 11,957 | -30% | 1 | 1 | 0% | 2,723 | 2,723 | 0% | 0 | 0 | — |
case-09 | fail→pass | 15,201 | 17,110 | +13% | 1 | 1 | 0% | 2,282 | 3,480 | +52% | 0 | 0 | — |
case-10 | fail→fail | 14,493 | 18,936 | +31% | 1 | 1 | 0% | 2,396 | 3,681 | +54% | 0 | 0 | — |
case-11 | fail→fail | 13,792 | 14,330 | +4% | 1 | 1 | 0% | 2,286 | 3,009 | +32% | 0 | 0 | — |
case-12 | fail→fail | 17,839 | 20,355 | +14% | 1 | 1 | 0% | 2,643 | 4,066 | +54% | 0 | 0 | — |
case-13 | fail→pass | 13,046 | 10,958 | -16% | 1 | 1 | 0% | 1,965 | 2,442 | +24% | 0 | 0 | — |
case-14 | pass→pass | 13,490 | 14,712 | +9% | 1 | 1 | 0% | 2,044 | 2,946 | +44% | 0 | 0 | — |
case-15 | pass→pass | 11,045 | 9,945 | -10% | 1 | 1 | 0% | 1,729 | 2,319 | +34% | 0 | 0 | — |
case-16 | pass→pass | 9,112 | 9,036 | -1% | 1 | 1 | 0% | 1,469 | 2,256 | +54% | 0 | 0 | — |
case-17 | fail→pass | 18,686 | 14,808 | -21% | 1 | 1 | 0% | 2,228 | 3,260 | +46% | 0 | 0 | — |
case-18 | pass→pass | 15,633 | 16,126 | +3% | 1 | 1 | 0% | 2,580 | 3,363 | +30% | 0 | 0 | — |
case-19 | fail→fail | 20,325 | 24,364 | +20% | 1 | 1 | 0% | 3,074 | 4,417 | +44% | 0 | 0 | — |
case-20 | pass→pass | 9,187 | 13,263 | +44% | 1 | 1 | 0% | 1,393 | 2,100 | +51% | 0 | 0 | — |
case-21 | fail→fail | 10,795 | 22,510 | +109% | 1 | 1 | 0% | 1,850 | 2,821 | +52% | 0 | 0 | — |
case-22 | fail→fail | 9,491 | 14,711 | +55% | 1 | 1 | 0% | 1,437 | 3,210 | +123% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +27 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.