Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Guides the creation of agile epics with comprehensive definition including business value, success criteria, and breakdown into user stories. Use when the user wants to create an agile epic, define large bodies of work, break down features into user stories, or document strategic initiatives. This should trigger for requests such as Create an agile epic; Write an epic; I need to create an epic; Define an epic; Epic definition. Part of Plinth Toolkit
.claude/skills/jabrena-012-agile-epic/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-10 | ✓→✗ | ▼ Worse | -32% | 0% |
Guide the agent to systematically gather information and generate a comprehensive epic definition in Markdown format. An epic represents a large body of work that can be broken down into smaller user stories, features, or tasks. This is an interactive SKILL.
What is covered in this Skill?
Before generating the epic document, gather all required information through structured questions. Use exact wording from the template and wait for user responses. Always get current date before starting.
Run date before starting and use it to replace all date placeholders in the generated epic document.
Ask the template questions in strict order, using exact wording and waiting for user responses before continuing.
Step constraints:
Create the epic Markdown with all required sections (scope, value, features, dependencies, risks, and success criteria) and apply the actual current date.
Close with actionable next steps for story breakdown, planning, and epic tracking.
For detailed guidance, examples, and constraints, see references/012-agile-epic.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→fail | 11,762 | 7,173 | -39% | 1 | 1 | 0% | 1,718 | 1,047 | -39% | 0 | 0 | — |
case-01 | fail→fail | 8,114 | 6,627 | -18% | 1 | 1 | 0% | 1,247 | 1,070 | -14% | 0 | 0 | — |
case-02 | fail→fail | 7,411 | 10,822 | +46% | 1 | 1 | 0% | 1,283 | 911 | -29% | 0 | 0 | — |
case-03 | fail→fail | 7,898 | 4,993 | -37% | 1 | 1 | 0% | 1,126 | 811 | -28% | 0 | 0 | — |
case-04 | fail→fail | 10,311 | 11,259 | +9% | 1 | 1 | 0% | 1,543 | 1,031 | -33% | 0 | 0 | — |
case-06 | pass→pass | 13,365 | 11,889 | -11% | 1 | 1 | 0% | 2,142 | 2,553 | +19% | 0 | 0 | — |
case-07 | pass→pass | 10,640 | 10,923 | +3% | 1 | 1 | 0% | 2,006 | 2,508 | +25% | 0 | 0 | — |
case-08 | pass→pass | 11,669 | 12,306 | +5% | 1 | 1 | 0% | 2,243 | 2,522 | +12% | 0 | 0 | — |
case-09 | pass→pass | 13,370 | 10,772 | -19% | 1 | 1 | 0% | 2,187 | 2,473 | +13% | 0 | 0 | — |
case-10 | pass→fail | 8,797 | 6,808 | -23% | 1 | 1 | 0% | 1,362 | 926 | -32% | 0 | 0 | — |
case-11 | fail→fail | 11,734 | 7,723 | -34% | 1 | 1 | 0% | 1,805 | 949 | -47% | 0 | 0 | — |
case-12 | fail→fail | 7,437 | 2,688 | -64% | 1 | 1 | 0% | 1,553 | 1,005 | -35% | 0 | 0 | — |
case-13 | fail→fail | 11,553 | 6,045 | -48% | 1 | 1 | 0% | 1,685 | 1,017 | -40% | 0 | 0 | — |
case-14 | pass→pass | 10,643 | 6,364 | -40% | 1 | 1 | 0% | 1,517 | 1,471 | -3% | 0 | 0 | — |
case-15 | fail→pass | 17,030 | 7,007 | -59% | 1 | 1 | 0% | 2,597 | 1,553 | -40% | 0 | 0 | — |
case-16 | fail→pass | 13,664 | 19,848 | +45% | 1 | 1 | 0% | 2,309 | 3,254 | +41% | 0 | 0 | — |
case-17 | pass→pass | 13,321 | 8,446 | -37% | 1 | 1 | 0% | 2,038 | 1,815 | -11% | 0 | 0 | — |
case-18 | fail→fail | 7,774 | 5,866 | -25% | 1 | 1 | 0% | 1,226 | 869 | -29% | 0 | 0 | — |
case-19 | fail→pass | 7,688 | 4,256 | -45% | 1 | 1 | 0% | 1,032 | 1,024 | -1% | 0 | 0 | — |
case-20 | pass→pass | 12,006 | 5,412 | -55% | 1 | 1 | 0% | 1,809 | 1,395 | -23% | 0 | 0 | — |
case-21 | pass→pass | 13,615 | 16,714 | +23% | 1 | 1 | 0% | 1,191 | 3,354 | +182% | 0 | 0 | — |
case-22 | fail→pass | 14,191 | 10,493 | -26% | 1 | 1 | 0% | 2,198 | 2,180 | -1% | 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 13 counted toward the lift figure. The other 9 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 +14 percentage points is the difference between those two pass rates over the 13 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.