Sprint Metrics
Calculate and analyze sprint metrics for "$ARGUMENTS". Measure velocity, analyze burndown, calculate cycle time and commitment ratio, identify outlier stories, and generate trend recommendations.
Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"project-management-sprint-metrics","workflow":"project-management","phase":3,"project":"<project>","event":"skipped","artifact":"03-review.md","note":"<reason or \"none given\">"}.
Prerequisites
Part of a workflow. This skill is phase 3 (Review) of the Scrum workflow (project-management); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or project-management when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.
Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"project-management-sprint-metrics","workflow":"project-management","phase":3,"project":"<project>","event":"refused","artifact":"03-review.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"project-management-sprint-metrics","workflow":"project-management","phase":3,"project":"<project>","event":"started","artifact":"03-review.md","note":""}.
Check that .singularskills/project-management/<project>/00-initiate.md exists. If it does not, tell the user to run an Initiate skill first (e.g., project-charter) and stop.
Process
Read existing context:
- Read
.singularskills/project-management/<project>/00-initiate.mdfor project context and team setup - Read
.singularskills/project-management/<project>/03-review.mdif it exists (for sprint review and completed stories) - Read
.singularskills/project-management/<project>/02-sprint.mdif it exists (for sprint state, standup history, and daily progress) - Read
.singularskills/project-management/<project>/01-plan.mdif it exists (for sprint backlog, estimates, and velocity targets)
- Read
Calculate velocity:
- Count total story points completed this sprint (only stories that met their definition of done)
- Do not count partially completed stories — they carry over to the next sprint at full points
- Note the committed velocity (what was planned) vs. actual velocity (what was delivered)
- Express velocity as a single number: X story points completed in this sprint
Compare velocity to last 3-5 sprints:
- If historical sprint data is available, list velocity for each of the last 3-5 sprints
- Calculate the average velocity across those sprints
- Calculate the velocity trend: improving (upward over 3+ sprints), declining (downward over 3+ sprints), or stable (within +/- 10% of average)
- If this sprint's velocity is significantly different from the average (more than 20% higher or lower), note the likely cause
- If no historical data is available, note this as the baseline sprint and skip trend analysis
Analyze burndown:
- Compare actual burndown to ideal burndown line (linear from total points to zero over sprint days)
- Identify patterns in the burndown:
- Flat start: no points completed in the first few days (stories too large, slow ramp-up)
- Cliff at end: most points completed in the last 1-2 days (stories not broken down enough, deadline pressure)
- Scope increase: total points went up mid-sprint (late additions, scope creep)
- Smooth decline: steady progress throughout (healthy sprint)
- Note any scope changes: stories added or removed mid-sprint, with the reason
- Calculate the gap between actual and ideal burndown at the midpoint of the sprint
Calculate cycle time per story:
- For each completed story, calculate days from "in progress" to "done"
- Calculate the average cycle time across all completed stories
- Calculate the median cycle time (less affected by outliers than the average)
- Break down cycle time by phase if data is available: development time, review time, testing time
- Compare cycle time to story size: do larger stories (more points) take proportionally longer?
Calculate commitment ratio:
- Commitment ratio = (completed story points / committed story points) x 100%
- Interpret the ratio:
- > 100%: team completed more than committed (stretch goals pulled in, or undercommitted)
- 80-100%: healthy range, team is committing accurately
- 60-80%: underperforming, investigate causes (overcommitment, blockers, estimation issues)
- < 60%: significant gap, sprint was disrupted or estimates were far off
- Compare to previous sprints' commitment ratios to see if accuracy is improving
Identify outlier stories:
- Find stories that took significantly longer than estimated (actual cycle time > 2x expected)
- For each outlier, document: the story, estimated vs. actual effort, and the root cause
- Common causes: unclear requirements, unexpected technical complexity, dependency delays, scope expansion
- Find stories completed much faster than estimated (actual < 0.5x expected) — these suggest overestimation
- Use outlier analysis to improve future estimation accuracy
Generate trend recommendations:
- Based on all metrics, provide 3-5 actionable recommendations:
- If velocity is declining: investigate causes (team changes, technical debt, morale)
- If commitment ratio is consistently low: reduce sprint scope or improve estimation
- If cycle time is increasing: break stories smaller, reduce WIP, improve review speed
- If burndown shows cliff pattern: encourage daily progress, break stories into smaller tasks
- If scope changes are frequent: improve sprint planning and protect the sprint backlog
- Prioritize recommendations by impact on team effectiveness
- Note what is going well — metrics are not just about finding problems
- Based on all metrics, provide 3-5 actionable recommendations:
Write the artifact — append to
.singularskills/project-management/<project>/03-review.mdunder a## Sprint Metricssection. Create the file with a# Review — <project>heading if it does not exist; if a## Sprint Metricssection already exists, replace only that section. The section contains:- Velocity — this sprint's velocity, committed vs. actual
- Velocity Trend — comparison to last 3-5 sprints with trend classification
- Burndown Analysis — actual vs. ideal burndown pattern and observations
- Cycle Time — average and median cycle time per story, breakdown by phase if available
- Commitment Ratio — percentage with interpretation and trend
- Outlier Stories — stories that deviated significantly from estimates with root causes
- Trend Recommendations — 3-5 actionable recommendations based on metrics
Output
Sprint metrics appended to .singularskills/project-management/<project>/03-review.md. Present a summary highlighting:
- Sprint velocity (actual vs. committed)
- Velocity trend (improving/declining/stable)
- Average cycle time per story
- Commitment ratio with interpretation
- Top recommendation for improving team effectiveness
Record the run. After you have written your section, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"project-management-sprint-metrics","workflow":"project-management","phase":3,"project":"<project>","event":"finished","artifact":"03-review.md","note":""}.
This artifact is shared by every skill of phase 3 (Review). The frontmatter is written once, by whoever creates the file: if you create it, open it with the block below (skill is the phase title, started the time of that first write; gate is passed when the gate ran clean and skipped under --skip-checks); if it already exists, leave the block alone except to update finished and to set gate to the worst value among the sections (skipped over passed).
---
skill: Review
workflow: project-management
phase: 3
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---
Open your ## Sprint Metrics section with one italic line, *<skill name> · <ISO timestamp> · gate: <passed|skipped>* (your skill name is project-management-sprint-metrics).
End your section with ### Decisions and ### Open questions (one level under your ## Sprint Metrics heading, so the section stays one block), in this shape:
### Decisions
- <what was chosen> — <why> — <what was rejected>
### Open questions
- <what the next phase or a reviewer must settle>