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/retro-template.md

View on GitHub
# Sprint Retro Template

The retro changes one thing about how the team works. This template runs the meeting. When a retro turns up something significant (a missed goal with a systemic cause, an incident, a repeated failure), write it up with `after-action-report`. Do not build a second write-up format here.

Timebox: 45 to 60 minutes for a two-week sprint.

---

## Before the meeting

- [ ] Pull the sprint's metrics: cycle time, carryover, planned vs unplanned, rework rate, and agent-lane metrics if any
- [ ] Pull the open actions from the last retro and their status
- [ ] Choose a format (below). Rotate formats every few sprints to avoid autopilot.

---

## Agenda

1. **Set the frame (5 min).** Read the blameless principle: we look at systems, not people.
2. **Last retro's actions (5 min).** Done, not done, or dropped. Unfinished actions are discussed before new ones.
3. **Data (5 min).** Show the metrics with a three-sprint trend. No discussion yet.
4. **Gather (15 min).** Silent writing, then grouping, using the chosen format.
5. **Pick (5 min).** Dot-vote. Take the top one to three themes.
6. **Dig (15 min).** For each theme, ask why until you reach something the team can change.
7. **Act (5 min).** One to three actions, each with an owner and a date, each entered as a ticket.

---

## Formats

| Format | Prompts | Good when |
|---|---|---|
| Start, stop, continue | What should we start, stop, keep doing? | Default |
| Mad, sad, glad | What frustrated, disappointed, pleased you? | Morale is a topic |
| Sailboat | Wind (helped), anchors (slowed), rocks (risks ahead) | Planning risks for the next sprint |
| Timeline | Plot the sprint day by day, mark highs and lows | A sprint with a clear turning point |

---

## Record

```
SPRINT: [number or name]
DATE: [YYYY-MM-DD]
FACILITATOR: [name]
FORMAT: [format]

LAST RETRO ACTIONS
| Action | Owner | Status |
|---|---|---|

METRICS SHOWN
- Cycle time p50 / p85: [N] / [N] days (trend: [up/down/flat])
- Carryover: [N] percent
- Planned share: [0.xx]
- Rework rate: [N] percent
- Agent lanes: honest-stop rate [N] percent, review rework [N] percent

TOP THEMES
1. [Theme]
2. [Theme]

ACTIONS
| Action | Owner | Due | Ticket |
|---|---|---|---|

ESCALATE TO AN AFTER-ACTION REPORT? [no / yes: topic]
```

---

## Writing actions

- Weak: "Communicate better."
- Strong: "Add a 'blocked by review' column to the board and set a 24-hour review target. Owner: Priya. Due: next planning."

An action without an owner and a date is a wish.
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