Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Integrates with Atlassian products to manage project tracking and documentation via MCP protocol. Use when querying Jira issues with JQL filters, creating and updating tickets with custom fields, searching or editing Confluence pages with CQL, managing sprints and backlogs, setting up MCP server authentication, syncing documentation, or debugging Atlassian API integrations.
.claude/skills/jeffallan-atlassian-mcp/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 17 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 3% | 0% |
maxResults=1 before full executionLoad detailed guidance based on context:
| Topic | Reference | Load When | |-------|-----------|-----------| | Server Setup | references/mcp-server-setup.md | Installation, choosing servers, configuration | | Jira Operations | references/jira-queries.md | JQL syntax, issue CRUD, sprints, boards, issue linking | | Confluence Ops | references/confluence-operations.md | CQL search, page creation, spaces, comments | | Authentication | references/authentication-patterns.md | OAuth 2.0, API tokens, permission scopes | | Common Workflows | references/common-workflows.md | Issue triage, doc sync, sprint automation |
# Open issues assigned to current user in a sprint
project = PROJ AND status = "In Progress" AND assignee = currentUser() ORDER BY priority DESC
# Unresolved bugs created in the last 7 days
project = PROJ AND issuetype = Bug AND status != Done AND created >= -7d ORDER BY created DESC
# Validate before bulk: test with maxResults=1 first
project = PROJ AND sprint in openSprints() AND status = Open ORDER BY created DESC# Find pages updated in a specific space recently
space = "ENG" AND type = page AND lastModified >= "2024-01-01" ORDER BY lastModified DESC
# Search page text for a keyword
space = "ENG" AND type = page AND text ~ "deployment runbook"json{ "mcpServers": { "atlassian": { "command": "npx", "args": ["-y", "@sooperset/mcp-atlassian"], "env": { "JIRA_URL": "https://your-domain.atlassian.net", "JIRA_EMAIL": "user@example.com", "JIRA_API_TOKEN": "${JIRA_API_TOKEN}", "CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki", "CONFLUENCE_EMAIL": "user@example.com", "CONFLUENCE_API_TOKEN": "${CONFLUENCE_API_TOKEN}" } } } }
> Note: Always load JIRA_API_TOKEN and CONFLUENCE_API_TOKEN from environment variables or a secrets manager — never hardcode credentials.
maxResults=1 probe first)When implementing Atlassian MCP features, provide:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→pass | 16,090 | 6,953 | -57% | 1 | 1 | 0% | 2,575 | 2,256 | -12% | 0 | 0 | — |
case-04 | pass→pass | 19,002 | 12,189 | -36% | 1 | 1 | 0% | 3,433 | 3,240 | -6% | 0 | 0 | — |
case-01 | fail→pass | 20,481 | 14,746 | -28% | 1 | 1 | 0% | 4,404 | 4,085 | -7% | 0 | 0 | — |
case-02 | fail→pass | 19,618 | 15,892 | -19% | 1 | 1 | 0% | 4,142 | 4,300 | +4% | 0 | 0 | — |
case-03 | fail→fail | 18,207 | 14,815 | -19% | 1 | 1 | 0% | 3,754 | 3,898 | +4% | 0 | 0 | — |
case-05 | pass→pass | 16,405 | 8,921 | -46% | 1 | 1 | 0% | 2,757 | 2,580 | -6% | 0 | 0 | — |
case-06 | pass→pass | 16,691 | 12,848 | -23% | 1 | 1 | 0% | 2,715 | 3,368 | +24% | 0 | 0 | — |
case-07 | pass→pass | 10,389 | 6,696 | -36% | 1 | 1 | 0% | 1,670 | 2,162 | +29% | 0 | 0 | — |
case-08 | pass→pass | 10,480 | 8,002 | -24% | 1 | 1 | 0% | 1,653 | 2,456 | +49% | 0 | 0 | — |
case-09 | fail→pass | 10,294 | 17,212 | +67% | 1 | 1 | 0% | 1,548 | 2,464 | +59% | 0 | 0 | — |
case-11 | pass→pass | 8,698 | 3,323 | -62% | 1 | 1 | 0% | 1,423 | 1,598 | +12% | 0 | 0 | — |
case-12 | pass→pass | 5,208 | 4,621 | -11% | 1 | 1 | 0% | 900 | 1,985 | +121% | 0 | 0 | — |
case-13 | pass→pass | 3,879 | 4,812 | +24% | 1 | 1 | 0% | 665 | 1,865 | +180% | 0 | 0 | — |
case-14 | fail→pass | 10,749 | 5,125 | -52% | 1 | 1 | 0% | 2,050 | 2,111 | +3% | 0 | 0 | — |
case-15 | fail→fail | 13,202 | 5,636 | -57% | 1 | 1 | 0% | 2,199 | 1,989 | -10% | 0 | 0 | — |
case-16 | pass→pass | 12,390 | 8,824 | -29% | 1 | 1 | 0% | 2,262 | 2,521 | +11% | 0 | 0 | — |
case-17 | pass→pass | 29,711 | 14,911 | -50% | 1 | 1 | 0% | 3,017 | 3,298 | +9% | 0 | 0 | — |
case-18 | pass→pass | 12,741 | 9,738 | -24% | 1 | 1 | 0% | 2,506 | 2,823 | +13% | 0 | 0 | — |
case-19 | pass→pass | 4,096 | 4,081 | -0% | 1 | 1 | 0% | 647 | 1,697 | +162% | 0 | 0 | — |
case-20 | pass→pass | 11,538 | 15,390 | +33% | 1 | 1 | 0% | 2,124 | 2,468 | +16% | 0 | 0 | — |
case-21 | pass→pass | 9,328 | 10,637 | +14% | 1 | 1 | 0% | 1,637 | 2,921 | +78% | 0 | 0 | — |
case-22 | pass→pass | 9,457 | 8,215 | -13% | 1 | 1 | 0% | 1,364 | 1,839 | +35% | 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 +23 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.