rampstackco/claude-skills / skills/sprint-operations
sprint-operations
VerifiedRun the measurement and ceremony layer of a delivery team: the metric set, estimation and capacity, the five sprint ceremonies, and the sprint report and quarterly rollup. Use this skill whenever the user is acting as PMO or scrum lead, planning a sprint, running standup, refinement, review, or retro, measuring velocity, cycle time, or throughput, checking capacity, or reporting on how a team is doing. Triggers on PMO, sprint planning, plan the sprint, standup, refinement, backlog grooming, sprint review, retro, velocity, capacity, cycle time, lead time, throughput, WIP, burndown, carryover, sprint report, story points to hours, how is the team doing, delivery metrics, agent lanes. Also triggers when the user asks how much work fits in a sprint or whether a team is on track, even if they never say sprint or PMO.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 358 B |
| SKILL.md | skill md | 11.9 KB |
| references/capacity-checklist.md | markdown | 2.7 KB |
| references/example-sprint-report.md | markdown | 4.3 KB |
| references/metrics-reference.md | markdown | 5.9 KB |
| references/planning-template.md | markdown | 1.9 KB |
| references/refinement-template.md | markdown | 2.0 KB |
| references/retro-template.md | markdown | 2.5 KB |
| references/review-template.md | markdown | 1.5 KB |
| references/sprint-report-template.md | markdown | 2.3 KB |
| references/standup-template.md | markdown | 1.7 KB |
references/example-sprint-report.md
View on GitHub# Example Sprint Report
Fictional team: **Harbor team** at **Tidewell**, a field-inspection app for building inspectors. Five engineers, one product manager, one designer, and one agent lane (a coding agent running dispatched tickets, reviewed by the engineers). Two-week sprints.
All numbers below are fictional and internally consistent.
---
```
# Sprint 31 report: Harbor team
Dates: 2026-09-21 to 2026-10-02
Prepared by: Jordan Ellis (PM)
Data source: tracker export, 2026-10-02 17:00
## Goal
Inspectors can attach photos to a checklist item offline and sync them when back online.
Result: met. Offline attach and sync shipped to staging behind the offline_photos flag; accepted in review.
## Headline
Goal met with carryover down for the third sprint in a row, from 31 to 18 percent, after the team set a WIP limit of two per person in sprint 29. The agent lane is producing more, but review rework on its PRs rose to 43 percent; the action is to tighten the acceptance criteria in its dispatches.
## Metrics
| Metric | Sprint 29 | Sprint 30 | Sprint 31 | Note |
|---|---|---|---|---|
| Throughput (tickets) | 19 | 21 | 23 | Includes 5 agent-lane tickets |
| Points completed | 33 | 36 | 38 | |
| Cycle time p50 / p85 (days) | 3.5 / 8.0 | 3.0 / 7.0 | 2.5 / 6.0 | WIP limit effect |
| Lead time p50 / p85 (days) | 12 / 30 | 11 / 27 | 11 / 26 | Queue time unchanged |
| Average WIP | 13 | 10 | 9 | Limit is 10 for humans |
| Carryover percent | 31 | 24 | 18 | 4 of 22 committed |
| Planned share | 0.74 | 0.76 | 0.78 | 18 of 23 done were planned |
| Rework rate (percent) | 5 | 5 | 9 | 2 of 23 reopened; both agent-lane |
## Agent lanes
| Metric | Sprint 29 | Sprint 30 | Sprint 31 | Note |
|---|---|---|---|---|
| Dispatches issued | 5 | 7 | 9 | |
| Draft-PR cycle time p50 (hours) | 6 | 5 | 5 | Dispatch to PR ready |
| Review rework rate | 25 percent | 33 percent | 43 percent | 3 of 7 PRs needed changes |
| Honest-stop rate | 20 percent | 14 percent | 22 percent | 2 of 9 stopped with a reported blocker |
| Cost per merged PR | $11 | $10 | $9 | Agent spend only; review time not included |
Reviewer time on agent PRs (estimate, from review timestamps): about 1.5 person-days this sprint.
## Carryover
| Ticket | Title | Reason | Plan |
|---|---|---|---|
| HAR-412 | Sync: retry with backoff on flaky connections | Underestimated; touched two services not on its touches list | Re-estimated, split into two |
| HAR-418 | Photo compression on low-memory devices | Blocked on device lab access for 3 days | Access granted; first in next sprint |
| HAR-421 | Settings: storage usage display | Deprioritized for an unplanned P1 bug | Next sprint |
| HAR-425 | Agent lane: add sync telemetry events | Honest stop: event schema undefined in the dispatch | Schema decided in refinement; re-dispatch |
## Unplanned work
| Ticket | Title | Source | Size |
|---|---|---|---|
| HAR-430 | Checklist: crash when an item has 0 photos and is marked failed | Customer report, S2/P1 | 3 |
| HAR-431 | Login: token refresh loop on app resume | Monitoring alert | 2 |
| HAR-433 | Export: missing inspector name on PDF | Support | 1 |
| HAR-434 | Dependency security patch | Scheduled scan | 1 |
| HAR-436 | Staging data reset script | Team request | 1 |
## Risks and asks
- Review capacity is the constraint on the agent lane. Ask: hold dispatches at 9 per sprint until rework rate is back under 30 percent. Owner: Jordan.
- Device lab access is shared with another team. Ask: a standing booking for two days per sprint. Owner: Sam.
## Retro actions
| Action | Owner | Due |
|---|---|---|
| Every dispatch includes acceptance criteria copied from the story and a named test command | Jordan | Sprint 32 planning |
| Add "blocked by review" column with a 24-hour review target | Priya | Sprint 32 day 1 |
## Data gaps
Reviewer time on agent PRs is estimated from review timestamps, not logged. Labeled as an estimate above.
```
---
## Why this report works
- Every metric has three sprints of trend, so the reader sees direction.
- The agent lane has its own table, so its rework does not hide inside the team's rework rate.
- The honest stop on HAR-425 is reported as carryover with a cause, not hidden.
- The headline names the one trend that matters and the one action that follows from it.
- The data gap is stated instead of filled with a guess.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |