Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create, modify, and govern reusable Jira and Confluence templates, blueprints, and standardized content structures. Use for org-wide templates, custom blueprints, page layouts, and automated content generation.
.claude/skills/borghei-atlassian-templates/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-17 | ✓→✗ | ▼ Worse | 29% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 26% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 56% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 45% | 0% |
Specialist in creating, modifying, and managing reusable templates and files for Jira and Confluence. Ensures consistency, accelerates content creation, and maintains org-wide standards through canonical, parameterized templates rather than per-use-case sprawl.
Before building the template, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Grab a ready-made starting point from the template libraries below, then follow the full creation/modification workflow in references/workflows-and-governance.md.
Load the reference that matches the task — keep this file lean and pull detail on demand:
In Scope: Confluence page template design and deployment, Jira issue description templates, blueprint development, template governance and lifecycle management, template versioning, usage analytics tracking, user training on template usage, macro-enhanced dynamic templates.
Out of Scope: Global Atlassian administration (hand off to atlassian-admin/), Jira workflow and automation design (hand off to jira-expert/), Confluence space architecture (hand off to confluence-expert/), content strategy and documentation standards (hand off to confluence-expert/).
Limitations: Confluence Cloud templates cannot include all macro types (some advanced macros require manual insertion after page creation). Jira issue templates are limited to description field content -- they cannot pre-set custom field values without automation rules. Template analytics require Confluence Premium or a marketplace analytics app for detailed usage metrics.
| Integration | Direction | What Flows | |-------------|-----------|------------| | confluence-expert/ | Bidirectional | Confluence expert defines content standards; template creator implements them as templates | | jira-expert/ | Templates -> Jira | Issue description templates, workflow documentation templates | | atlassian-admin/ | Admin -> Templates | Global template deployment approval, governance policies | | scrum-master/ | SM -> Templates | Sprint ceremony template requirements, retrospective format preferences | | senior-pm/ | PM -> Templates | Executive reporting templates, portfolio tracking layouts | | delivery-manager/ | DM -> Templates | Post-mortem templates, release checklist templates, runbook structures |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 15,843 | 12,197 | -23% | 1 | 1 | 0% | 2,516 | 3,164 | +26% | 0 | 0 | — |
case-02 | fail→fail | 12,755 | 9,562 | -25% | 1 | 1 | 0% | 2,072 | 2,717 | +31% | 0 | 0 | — |
case-03 | pass→pass | 12,177 | 13,350 | +10% | 1 | 1 | 0% | 2,134 | 3,327 | +56% | 0 | 0 | — |
case-04 | pass→pass | 14,504 | 13,651 | -6% | 1 | 1 | 0% | 2,188 | 3,181 | +45% | 0 | 0 | — |
case-05 | pass→pass | 10,138 | 7,627 | -25% | 1 | 1 | 0% | 1,575 | 2,264 | +44% | 0 | 0 | — |
case-06 | fail→fail | 15,749 | 13,758 | -13% | 1 | 1 | 0% | 2,538 | 3,299 | +30% | 0 | 0 | — |
case-07 | fail→fail | 16,473 | 12,749 | -23% | 1 | 1 | 0% | 2,490 | 3,189 | +28% | 0 | 0 | — |
case-08 | fail→fail | 15,836 | 12,716 | -20% | 1 | 1 | 0% | 2,974 | 3,317 | +12% | 0 | 0 | — |
case-09 | pass→pass | 7,339 | 10,239 | +40% | 1 | 1 | 0% | 1,177 | 2,675 | +127% | 0 | 0 | — |
case-10 | pass→pass | 12,108 | 14,173 | +17% | 1 | 1 | 0% | 1,858 | 3,557 | +91% | 0 | 0 | — |
case-11 | pass→pass | 12,149 | 12,282 | +1% | 1 | 1 | 0% | 2,047 | 2,970 | +45% | 0 | 0 | — |
case-12 | fail→pass | 14,452 | 16,317 | +13% | 1 | 1 | 0% | 2,219 | 3,678 | +66% | 0 | 0 | — |
case-13 | fail→fail | 10,862 | 11,616 | +7% | 1 | 1 | 0% | 1,485 | 2,951 | +99% | 0 | 0 | — |
case-14 | pass→pass | 11,743 | 10,506 | -11% | 1 | 1 | 0% | 2,002 | 2,756 | +38% | 0 | 0 | — |
case-15 | pass→pass | 17,228 | 14,796 | -14% | 1 | 1 | 0% | 2,572 | 3,442 | +34% | 0 | 0 | — |
case-16 | pass→pass | 11,567 | 7,623 | -34% | 1 | 1 | 0% | 1,831 | 2,300 | +26% | 0 | 0 | — |
case-17 | pass→fail | 15,257 | 12,427 | -19% | 1 | 1 | 0% | 2,351 | 3,024 | +29% | 0 | 0 | — |
case-18 | pass→pass | 12,818 | 9,284 | -28% | 1 | 1 | 0% | 2,034 | 2,541 | +25% | 0 | 0 | — |
case-19 | pass→pass | 12,950 | 10,404 | -20% | 1 | 1 | 0% | 2,091 | 2,948 | +41% | 0 | 0 | — |
case-20 | pass→pass | 13,372 | 15,039 | +12% | 1 | 1 | 0% | 2,060 | 3,341 | +62% | 0 | 0 | — |
case-21 | fail→fail | 17,271 | 13,493 | -22% | 1 | 1 | 0% | 2,415 | 3,042 | +26% | 0 | 0 | — |
case-22 | fail→fail | 12,676 | 16,860 | +33% | 1 | 1 | 0% | 2,028 | 3,318 | +64% | 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 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are 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.