| name | Sprint Analytics |
| description | Post-close sprint retrospective analysis skill that reads shark sprint summary --detailed and velocity data, synthesizes five-section markdown retro reports with data-driven recommendations, and gates the archive operation on explicit user confirmation. |
Sprint Analytics
What This Is
A retrospective synthesis harness. It reads closed sprint data from shark — detailed summary, velocity history, and per-entity blocker and rejection notes — and produces a structured five-section retrospective report. Recommendations are generated by pattern-matching measurable thresholds against the sprint data, not by free-form advice.
shark sprint summary {S###} --detailed --json → shark sprint velocity --json → shark notes per entity → five-section retro report
It does NOT execute sprint work. It does NOT modify sprint state (other than an optional archive call gated on user confirmation). It reads, synthesizes, and reports.
Command
/shark retro-sprint S### # Generate retro report and write to docs/sprints/
/shark retro-sprint S### --no-write # Print report to stdout; do not write to disk
Read workflows/retro-sprint.md to get the full step-by-step workflow procedure.
The Five Sections
| Section | Data Source |
|---|
| Outcome | shark sprint summary --detailed --json (planned vs. completed count and Σ size) |
| Velocity Context | shark sprint velocity --json (this sprint vs. trailing average, with delta) |
| Carryover Analysis | shark notes {entity_key} for each carryover and rejected entity |
| Cycle-Time Highlights | Per-phase cycle times from the --detailed summary |
| Recommendations | Pattern-matched from the above data; 3–5 items; always quantitative triggers |
Recommendation Pattern Rules
The five triggers for recommendations (applied in order; top 3–5 by signal strength emitted):
trailing-avg velocity variance > 25% → "consider re-evaluating sprint capacity"any entity with size ≥ 8 completed → "split XL+ entities before next sprint planning"carryover_count > 30% of planned → "scope was too aggressive — planned {N}, carried {M}"any phase cycle time > 2× another phase → "investigate {phase} bottleneck — {X}× longer than {other phase}"any agent type allocated > capacity by 20% → "rebalance {agent_type} load — allocated {A} against capacity {C}"
JSON Handling
- All shark calls use
--json or --field
- Never truncate output with
head, tail, or grep
shark sprint summary --detailed --json returns full phase-level cycle-time data; consume the full object
