mirror of
https://github.com/Donchitos/Claude-Code-Game-Studios.git
synced 2026-06-27 04:51:46 +00:00
ad540fe75d
48 coordinated Claude Code subagents for indie game development: - 3 leadership agents (creative-director, technical-director, producer) - 10 department leads (game-designer, lead-programmer, art-director, etc.) - 23 specialist agents (gameplay, engine, AI, networking, UI, tools, etc.) - 12 engine-specific agents (Godot, Unity, Unreal with sub-specialists) Infrastructure: - 34 skills (slash commands) for workflows, reviews, and team orchestration - 8 hooks for commit validation, asset checks, session management - 11 path-scoped rules enforcing domain-specific standards - 28 templates for design docs, reports, and collaborative protocols Key features: - User-driven collaboration protocol (Question → Options → Decision → Draft → Approval) - Engine version awareness with knowledge-gap detection (Godot 4.6 pinned) - Phase gate system for development milestone validation - CLAUDE.md kept under 80 lines with extracted doc imports Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2.1 KiB
2.1 KiB
Hook: post-sprint-retrospective
Trigger
Manual trigger at the end of each sprint (typically invoked by the producer agent or the human developer).
Purpose
Automatically generates a retrospective starting point by analyzing the sprint
data: what was planned vs completed, velocity changes, bug trends, and common
blockers. This is not a git hook but a workflow hook invoked through the
producer agent.
Implementation
This is a workflow hook, not a git hook. It is invoked by running:
@producer Generate sprint retrospective for Sprint [N]
The producer agent should:
- Read the sprint plan from
production/sprints/sprint-[N].md - Calculate metrics:
- Tasks planned vs completed
- Story points planned vs completed (if used)
- Carryover items from previous sprint
- New tasks added mid-sprint
- Average task completion time
- Analyze patterns:
- Most common blockers
- Which agent/area had the most incomplete work
- Which estimates were most inaccurate
- Generate the retrospective:
# Sprint [N] Retrospective
## Metrics
| Metric | Value |
|--------|-------|
| Tasks Planned | [N] |
| Tasks Completed | [N] |
| Completion Rate | [X%] |
| Carryover from Previous | [N] |
| New Tasks Added | [N] |
| Bugs Found | [N] |
| Bugs Fixed | [N] |
## Velocity Trend
[Sprint N-2]: [X] | [Sprint N-1]: [Y] | [Sprint N]: [Z]
Trend: [Improving / Stable / Declining]
## What Went Well
- [Automatically detected: tasks completed ahead of estimate]
- [Facilitator adds team observations]
## What Went Poorly
- [Automatically detected: tasks that were carried over or cut]
- [Automatically detected: areas with significant estimate overruns]
- [Facilitator adds team observations]
## Blockers
| Blocker | Frequency | Resolution Time | Prevention |
|---------|-----------|----------------|-----------|
## Action Items for Next Sprint
| # | Action | Owner | Priority |
|---|--------|-------|----------|
## Estimation Accuracy
| Area | Avg Planned | Avg Actual | Accuracy |
|------|------------|-----------|----------|
- Save to
production/sprints/sprint-[N]-retro.md