Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.
.claude/skills/davila7-jira/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 102% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 101% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 78% | 0% |
Natural language interaction with Jira. Supports multiple backends.
Run this check first to determine which backend to use:
1. Check if jira CLI is available:
→ Run: which jira
→ If found: USE CLI BACKEND
2. If no CLI, check for Atlassian MCP:
→ Look for mcp__atlassian__* tools
→ If available: USE MCP BACKEND
3. If neither available:
→ GUIDE USER TO SETUP| Backend | When to Use | Reference | |---------|-------------|-----------| | CLI | jira command available | references/commands.md | | MCP | Atlassian MCP tools available | references/mcp.md | | None | Neither available | Guide to install CLI |
> Skip this section if using MCP backend.
| Intent | Command | |--------|---------| | View issue | jira issue view ISSUE-KEY | | List my issues | jira issue list -a$(jira me) | | My in-progress | jira issue list -a$(jira me) -s"In Progress" | | Create issue | jira issue create -tType -s"Summary" -b"Description" | | Move/transition | jira issue move ISSUE-KEY "State" | | Assign to me | jira issue assign ISSUE-KEY $(jira me) | | Unassign | jira issue assign ISSUE-KEY x | | Add comment | jira issue comment add ISSUE-KEY -b"Comment text" | | Open in browser | jira open ISSUE-KEY | | Current sprint | jira sprint list --state active | | Who am I | jira me |
> Skip this section if using CLI backend.
| Intent | MCP Tool | |--------|----------| | Search issues | mcp__atlassian__searchJiraIssuesUsingJql | | View issue | mcp__atlassian__getJiraIssue | | Create issue | mcp__atlassian__createJiraIssue | | Update issue | mcp__atlassian__editJiraIssue | | Get transitions | mcp__atlassian__getTransitionsForJiraIssue | | Transition | mcp__atlassian__transitionJiraIssue | | Add comment | mcp__atlassian__addCommentToJiraIssue | | User lookup | mcp__atlassian__lookupJiraAccountId | | List projects | mcp__atlassian__getVisibleJiraProjects |
See references/mcp.md for full MCP patterns.
Issue keys follow the pattern: [A-Z]+-[0-9]+ (e.g., PROJ-123, ABC-1).
When a user mentions an issue key in conversation:
jira issue view KEY or jira open KEYmcp__atlassian__jira_get_issue with the keyCreating tickets:
Updating tickets:
Ask yourself:
lookupJiraAccountId first, or assignment silently fails.--no-input without all required fields (CLI) — Fails silently with cryptic errors. Check project's required fields first.If neither CLI nor MCP is available, guide the user:
To use Jira, you need one of:
1. **jira CLI** (recommended):
https://github.com/ankitpokhrel/jira-cli
Install: brew install ankitpokhrel/jira-cli/jira-cli
Setup: jira init
2. **Atlassian MCP**:
Configure in your MCP settings with Atlassian credentials.LOAD reference when:
Do NOT load reference for:
jira issue view KEY)| Task | Load Reference? | |------|-----------------| | View single issue | No | | List my tickets | No | | Create with description | Yes — CLI needs /tmp pattern | | Transition issue | Yes — need transition ID workflow | | JQL search | Yes — for complex queries | | Link issues | Yes — MCP limitation, need script |
References:
references/commands.mdreferences/mcp.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,211 | 6,397 | +99% | 1 | 1 | 0% | 427 | 1,805 | +323% | 0 | 0 | — |
case-02 | fail→fail | 4,194 | 3,239 | -23% | 1 | 1 | 0% | 780 | 1,837 | +136% | 0 | 0 | — |
case-03 | fail→fail | 4,020 | 7,930 | +97% | 1 | 1 | 0% | 703 | 1,836 | +161% | 0 | 0 | — |
case-04 | fail→pass | 6,190 | 3,932 | -36% | 1 | 1 | 0% | 987 | 1,991 | +102% | 0 | 0 | — |
case-05 | fail→pass | 7,180 | 7,093 | -1% | 1 | 1 | 0% | 1,414 | 2,848 | +101% | 0 | 0 | — |
case-06 | fail→fail | 9,733 | 6,954 | -29% | 1 | 1 | 0% | 1,064 | 1,842 | +73% | 0 | 0 | — |
case-07 | pass→pass | 6,558 | 2,046 | -69% | 1 | 1 | 0% | 1,315 | 1,860 | +41% | 0 | 0 | — |
case-08 | pass→pass | 7,957 | 4,510 | -43% | 1 | 1 | 0% | 1,618 | 2,318 | +43% | 0 | 0 | — |
case-09 | fail→pass | 6,833 | 2,217 | -68% | 1 | 1 | 0% | 1,251 | 1,882 | +50% | 0 | 0 | — |
case-10 | pass→pass | 3,347 | 1,409 | -58% | 1 | 1 | 0% | 598 | 1,779 | +197% | 0 | 0 | — |
case-11 | fail→pass | 5,689 | 1,629 | -71% | 1 | 1 | 0% | 1,147 | 1,780 | +55% | 0 | 0 | — |
case-12 | fail→pass | 6,165 | 2,892 | -53% | 1 | 1 | 0% | 1,129 | 2,004 | +78% | 0 | 0 | — |
case-13 | fail→pass | 5,268 | 1,022 | -81% | 1 | 1 | 0% | 1,022 | 1,693 | +66% | 0 | 0 | — |
case-14 | fail→pass | 6,936 | 2,021 | -71% | 1 | 1 | 0% | 1,525 | 1,913 | +25% | 0 | 0 | — |
case-15 | fail→fail | 5,744 | 5,025 | -13% | 1 | 1 | 0% | 1,031 | 2,460 | +139% | 0 | 0 | — |
case-16 | fail→fail | 9,588 | 5,337 | -44% | 1 | 1 | 0% | 1,649 | 2,376 | +44% | 0 | 0 | — |
case-17 | fail→pass | 9,663 | 2,224 | -77% | 1 | 1 | 0% | 1,673 | 1,865 | +11% | 0 | 0 | — |
case-18 | pass→pass | 4,094 | 1,869 | -54% | 1 | 1 | 0% | 627 | 1,914 | +205% | 0 | 0 | — |
case-19 | pass→pass | 7,316 | 3,108 | -58% | 1 | 1 | 0% | 1,155 | 2,116 | +83% | 0 | 0 | — |
case-20 | pass→pass | 5,032 | 2,278 | -55% | 1 | 1 | 0% | 884 | 1,904 | +115% | 0 | 0 | — |
case-21 | pass→pass | 10,732 | 4,823 | -55% | 1 | 1 | 0% | 2,300 | 2,677 | +16% | 0 | 0 | — |
case-22 | pass→pass | 8,536 | 5,841 | -32% | 1 | 1 | 0% | 1,978 | 2,760 | +40% | 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, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +36 percentage points is the difference between those two pass rates over the 18 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.