Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when you need Jira CLI (`jira`) installation/authentication guidance and a maintainer-authored Jira issue inventory workflow. The agent does not ingest raw Jira issue or JQL output directly; it asks the Jira project maintainer/operator to author sanitized issue summaries before analysis or @014-agile-user-story handoff. This should trigger for requests such as jira issue list; List Jira issues; Jira JQL issue query; Jira CLI issue workflow. Part of Plinth Toolkit
.claude/skills/jabrena-044-planning-jira/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 189% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 180% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 134% | 0% |
Use jira setup guidance for Jira issue workflows: first run an interactive check - if jira is not installed, stop, ask whether the user wants installation guidance, wait for an answer, then continue. When jira is available, validate configuration and ask the Jira project maintainer/operator to provide a sanitized issue inventory. For requirements analysis, use only maintainer-authored sanitized Jira summaries.
What is covered in this Skill?
jira is installed; offer installation guidance only when the user agreesjira version, jira configure)Do not fabricate issue data; use only sanitized summaries authored or approved by the Jira project maintainer/operator. Never print API tokens or secrets.
jira is missing, stop, ask whether the user wants installation guidance, wait - do not skip to issue listingjira is available before issuing subcommandsCheck jira version; if missing, stop and ask whether the user wants installation guidance before any issue operations.
Ensure Jira CLI is configured (site/account/token flow via CLI prompts) before running private workspace commands.
Ask the Jira project maintainer/operator to provide a sanitized issue inventory containing only the issue key, sanitized summary, status, assignee, updated time, and URL when useful. Do not ask them to paste raw jira issue list, JQL, description, or comment exports.
Do not retrieve raw Jira issue list, description, or comment bodies. If analysis needs detail beyond the sanitized inventory, ask the Jira project maintainer/operator for a sanitized summary of the relevant Jira issue context and note that raw discussion content was not ingested.
Support create, assign, and transition actions using CLI commands while avoiding secret exposure.
For detailed guidance, examples, and constraints, see references/044-planning-jira.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 | 13,226 | 5,001 | -62% | 1 | 1 | 0% | 2,167 | 1,480 | -32% | 0 | 0 | — |
case-02 | fail→pass | 5,151 | 9,219 | +79% | 1 | 1 | 0% | 779 | 2,251 | +189% | 0 | 0 | — |
case-03 | fail→fail | 5,576 | 11,140 | +100% | 1 | 1 | 0% | 811 | 2,543 | +214% | 0 | 0 | — |
case-04 | pass→pass | 2,203 | 2,847 | +29% | 1 | 1 | 0% | 242 | 1,136 | +369% | 0 | 0 | — |
case-05 | pass→pass | 2,914 | 3,493 | +20% | 1 | 1 | 0% | 435 | 1,262 | +190% | 0 | 0 | — |
case-06 | pass→pass | 5,118 | 4,484 | -12% | 1 | 1 | 0% | 768 | 1,421 | +85% | 0 | 0 | — |
case-07 | fail→pass | 3,585 | 4,258 | +19% | 1 | 1 | 0% | 494 | 1,382 | +180% | 0 | 0 | — |
case-08 | fail→pass | 9,067 | 2,716 | -70% | 1 | 1 | 0% | 1,523 | 1,143 | -25% | 0 | 0 | — |
case-09 | fail→pass | 14,494 | 4,337 | -70% | 1 | 1 | 0% | 2,089 | 1,373 | -34% | 0 | 0 | — |
case-10 | pass→pass | 5,269 | 3,574 | -32% | 1 | 1 | 0% | 811 | 1,319 | +63% | 0 | 0 | — |
case-11 | pass→pass | 8,790 | 3,677 | -58% | 1 | 1 | 0% | 1,276 | 1,222 | -4% | 0 | 0 | — |
case-12 | fail→pass | 4,756 | 5,906 | +24% | 1 | 1 | 0% | 707 | 1,655 | +134% | 0 | 0 | — |
case-13 | pass→pass | 3,576 | 5,688 | +59% | 1 | 1 | 0% | 578 | 1,646 | +185% | 0 | 0 | — |
case-14 | pass→pass | 10,288 | 4,624 | -55% | 1 | 1 | 0% | 1,595 | 1,367 | -14% | 0 | 0 | — |
case-15 | fail→pass | 6,707 | 2,552 | -62% | 1 | 1 | 0% | 1,080 | 1,084 | +0% | 0 | 0 | — |
case-16 | fail→pass | 7,805 | 6,177 | -21% | 1 | 1 | 0% | 1,132 | 1,746 | +54% | 0 | 0 | — |
case-17 | fail→pass | 3,982 | 3,547 | -11% | 1 | 1 | 0% | 620 | 1,303 | +110% | 0 | 0 | — |
case-18 | fail→pass | 9,537 | 3,257 | -66% | 1 | 1 | 0% | 1,440 | 1,255 | -13% | 0 | 0 | — |
case-19 | fail→pass | 6,569 | 3,886 | -41% | 1 | 1 | 0% | 884 | 1,322 | +50% | 0 | 0 | — |
case-20 | pass→pass | 12,058 | 5,488 | -54% | 1 | 1 | 0% | 1,575 | 1,460 | -7% | 0 | 0 | — |
case-21 | fail→pass | 4,620 | 11,056 | +139% | 1 | 1 | 0% | 517 | 1,861 | +260% | 0 | 0 | — |
case-22 | fail→pass | 10,292 | 3,918 | -62% | 1 | 1 | 0% | 1,570 | 1,194 | -24% | 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 +55 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.