菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Query and manage project state and drive shark workflows — epics, features, tasks, bugs, change-cards, ideas. Use for ALL project state queries, task lifecycle, status transitions (status set / advance --outcome), claim/release/heartbeat leases, blocking/unblocking, notes/context/related-docs, status dashboards, analytics, creating/updating/deleting entities, and any command starting with "shark". Also the router for `/shark <verb>` and triggers the dispatch loop on `/run <key>`.
Multi-angle parallel code review. Six specialist subagents run in parallel (A: line-by-line bugs + production caller chains, B: removed behavior + SOLID, C: cross-file contracts + structural sibling check, D: reuse/complexity/idioms, E: tests design + counter-factual, F: standards crosswalk with citations), then a consolidator verifies and ranks findings into a PASS / PASS-with-triage / FAIL report with Blocker / Non-blocker / Nit triage. Triggered by /deep-review (aliases: /comprehensive-review, /pr-review). Flags: --fix (apply one-liner safe fixes), --comment (post as inline GitHub PR comments). Prompts live in references/angle-*.md and references/consolidator.md — readable on any platform even without the Workflow tool.
Authoritative source for all validation, code review, and quality assurance workflows. Provides consistent quality gates across all development phases.
Write the test first, watch it fail, write minimal code to pass (user) - when implementing any feature or bugfix, before writing implementation code
Orchestrate User Acceptance Testing for a feature — gather evidence, run Codex as the sole assessor, present a no-opinion report to the user, record results, route rejections, and triage non-blocking findings.
Quick-capture and classify a work item discovered during development, routing it to the correct entity type (task, feature, bug, tech-debt, change-card, idea, or note) under the right parent. Searches existing entities first to avoid duplication, proposes a classification, and confirms before creating. Use when you encounter work that needs to be recorded for later, the user says "/triage", or something should be tracked but its home is unclear. This is a capture-and-classify tool, NOT a create-and-elaborate tool.
| name | sprint-analytics |
| display_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. |
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.
sprint summary {S###} --detailed --json -> sprint velocity --json -> entity notes -> 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.
/retro-sprint S### # Generate retro report and write to docs/sprints/
/retro-sprint S### --no-write # Print report to stdout; do not write to disk
See: workflows/retro-sprint.md for the full step-by-step workflow.
| 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 lookup 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 |
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 or --fieldhead, tail, or grepshark sprint summary --detailed --json returns full phase-level cycle-time data; consume the full object