Skip to content

rampstackco/claude-skills / skills/sprint-operations

sprint-operations

Verified

Run 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.

references/capacity-checklist.md

View on GitHub
# Capacity Checklist

Run this before every planning session. It turns "how much fits in the sprint?" into a number you can defend.

---

## 1. Gather the inputs

- [ ] Sprint length in working days
- [ ] Team roster, including agent lanes as separate rows
- [ ] Planned absences: vacation, holidays, training, on-call rotations
- [ ] Throughput and points completed for the last three to six sprints
- [ ] Planned vs unplanned ratio for the same sprints
- [ ] Carryover from the current sprint that will roll forward

If fewer than three sprints of history exist, say so in the plan and use the history you have. Do not borrow another team's numbers.

---

## 2. Compute available capacity

- [ ] Person-days available = sum over people of (sprint working days minus absence days)
- [ ] Capacity ratio = person-days available divided by person-days in a full-attendance sprint
- [ ] Note any role gap (no designer this sprint, no reviewer for one area)

Example: 5 people, 10-day sprint, 6 days of absence total. Available is 44 of 50. Ratio is 0.88.

---

## 3. Compute the planning target

- [ ] Baseline = trailing median throughput (tickets) or trailing median points completed
- [ ] Adjusted baseline = baseline multiplied by the capacity ratio
- [ ] Unplanned buffer = adjusted baseline multiplied by (1 minus trailing planned vs unplanned ratio)
- [ ] Planning target = adjusted baseline minus unplanned buffer
- [ ] Subtract carryover that is already committed

Example: trailing median 34 points. Ratio 0.88 gives 30. Trailing planned share 0.8, so the buffer is 6. Target is 24 points. Carryover is 5. New commitment: up to 19 points.

---

## 4. Check the agent lanes

- [ ] Agent-lane throughput is planned separately from human throughput
- [ ] Review capacity is counted: every agent PR needs a human reviewer, and that time comes out of human capacity
- [ ] Dispatches planned do not exceed the reviewers' capacity to review them in the sprint

A lane that can produce ten PRs while the team can review four will produce six PRs of WIP.

---

## 5. Check the commitment

- [ ] Every committed ticket meets the definition of ready (see `ticket-authoring`)
- [ ] No single ticket is larger than about a third of one person's sprint
- [ ] The sprint goal can be met with the committed list alone
- [ ] Stretch items are labeled as stretch and excluded from the commitment
- [ ] The capacity math is written into the planning record

---

## 6. Hours, only if finance needs them

- [ ] Hours are logged only on tickets with a capitalizable stage
- [ ] If a points-to-hours ratio is published, it is this team's ratio from its own trailing three to six sprints
- [ ] The ratio's computation window and date are stated next to it
- [ ] The ratio is republished at the start of each quarter
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall