Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate a structured sprint brief from sprint data and goals. Use when asked to write a sprint brief, create a sprint summary, document sprint goals and scope, or produce a team-facing sprint overview. Produces a scannable brief with sprint goal, rationale, grouped work, critical path, risks, and definition of done.
.claude/skills/mohitagw15856-sprint-brief/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 192% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 148% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 162% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 228% | 0% |
Produce a clear, scannable sprint brief that every team member — engineer, designer, PM — can read in under three minutes and understand exactly what we're doing and why.
Ask the user for these if not provided:
Sprint Goal: 1-2 sentences — specific and measurable] Why This Sprint Matters: Connect to quarterly OKR in 2-3 sentences]
What We're Building:
Critical Path: The 2-3 tickets everything else depends on]
Risks to Flag:
Carry-over from Last Sprint: List + impact on current goal]
Definition of Done: Specific, agreed criteria for sprint success]
This skill ships with support files — use them when they are available:
references/goal-writing.md — Writing Sprint Goals That Steer. Apply it while producing the output; it carries the calibration and judgment calls the method summary above compresses.templates/brief-one-pager.md — a fill-in version of the deliverable with the quality gates inline. Offer it when the user wants to work the document themselves rather than have it generated.Score any output of this skill before handing it over; 32+ is ship-quality.
| Dimension | 0 | 5 | 10 | |---|---|---|---| | Goal scoreability | Goal is a task list or a vague direction ("make progress on X") — nobody could score it at sprint end | Goal states one outcome but the pass/fail line is fuzzy (no number, date, or observable test) | Goal is a single outcome statement with an explicit pass/fail test anyone on the team could apply on the last day | | Critical path precision | No critical path, or "the important tickets" — reader can't tell which slippage is fatal | Critical path tickets are named but without sequencing or the date/trigger at which the goal fails | Named tickets in dependency order, with the deadline that kills the goal and a clear fatal-vs-survivable split from the rest of the board | | Risk actionability | Risks are a worry list — no mitigations, no owners | Each risk has a mitigation or an owner, but responses are generic ("monitor closely") | Every risk has a concrete mitigation with a ready-by date and a single named owner, and states whether it threatens the goal or just a ticket | | Capacity honesty | Carry-over listed without impact; board is silently overloaded | Carry-over impact on the goal is stated, but the brief doesn't act on it — overload is flagged as a risk and left there | Carry-over is costed against capacity and the brief shows the resolution: named scope cuts, a de-scoped goal, or an explicit team-agreed overload acceptance |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 17,297 | 21,809 | +26% | 1 | 1 | 0% | 2,813 | 4,219 | +50% | 0 | 0 | — |
case-02 | fail→pass | 17,814 | 19,442 | +9% | 1 | 1 | 0% | 2,426 | 3,835 | +58% | 0 | 0 | — |
case-03 | pass→pass | 21,345 | 24,730 | +16% | 1 | 1 | 0% | 2,586 | 4,336 | +68% | 0 | 0 | — |
case-04 | pass→fail | 26,111 | 30,878 | +18% | 1 | 1 | 0% | 4,059 | 6,165 | +52% | 0 | 0 | — |
case-10 | pass→pass | 17,632 | 21,953 | +25% | 1 | 1 | 0% | 1,784 | 3,401 | +91% | 0 | 0 | — |
case-05 | pass→pass | 11,043 | 17,423 | +58% | 1 | 1 | 0% | 2,179 | 3,363 | +54% | 0 | 0 | — |
case-06 | pass→pass | 15,678 | 17,601 | +12% | 1 | 1 | 0% | 1,881 | 3,258 | +73% | 0 | 0 | — |
case-07 | fail→pass | 13,859 | 22,560 | +63% | 1 | 1 | 0% | 1,475 | 4,312 | +192% | 0 | 0 | — |
case-08 | pass→pass | 23,418 | 26,660 | +14% | 1 | 1 | 0% | 2,923 | 4,212 | +44% | 0 | 0 | — |
case-09 | fail→pass | 8,230 | 14,856 | +81% | 1 | 1 | 0% | 1,517 | 3,764 | +148% | 0 | 0 | — |
case-11 | pass→pass | 19,404 | 21,560 | +11% | 1 | 1 | 0% | 2,082 | 4,245 | +104% | 0 | 0 | — |
case-12 | fail→pass | 13,894 | 16,836 | +21% | 1 | 1 | 0% | 1,594 | 4,182 | +162% | 0 | 0 | — |
case-13 | fail→fail | 12,521 | 18,248 | +46% | 1 | 1 | 0% | 1,444 | 3,435 | +138% | 0 | 0 | — |
case-14 | fail→fail | 21,716 | 20,161 | -7% | 1 | 1 | 0% | 2,240 | 3,708 | +66% | 0 | 0 | — |
case-15 | fail→pass | 6,468 | 22,953 | +255% | 1 | 1 | 0% | 1,097 | 3,599 | +228% | 0 | 0 | — |
case-16 | fail→fail | 16,758 | 18,783 | +12% | 1 | 1 | 0% | 2,065 | 3,465 | +68% | 0 | 0 | — |
case-17 | fail→pass | 10,723 | 19,538 | +82% | 1 | 1 | 0% | 1,162 | 3,599 | +210% | 0 | 0 | — |
case-18 | pass→pass | 10,663 | 20,283 | +90% | 1 | 1 | 0% | 2,010 | 4,590 | +128% | 0 | 0 | — |
case-19 | fail→pass | 10,476 | 30,241 | +189% | 1 | 1 | 0% | 1,953 | 4,631 | +137% | 0 | 0 | — |
case-20 | fail→pass | 9,066 | 12,891 | +42% | 1 | 1 | 0% | 1,599 | 3,321 | +108% | 0 | 0 | — |
case-21 | pass→pass | 21,522 | 19,484 | -9% | 1 | 1 | 0% | 2,700 | 4,558 | +69% | 0 | 0 | — |
case-22 | fail→fail | 10,155 | 10,554 | +4% | 1 | 1 | 0% | 1,927 | 3,030 | +57% | 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 +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.