Files

T

jpmschweitzerandClaude Opus 4.6 7158ae9cf5 feat(meta): add whatsinagame multi-agent team starter kit

Claude-native starter kit that bootstraps multi-agent team
infrastructure for any project. Clone once, install as a global
skill, run /kit-install in any project directory.

Includes:
- 3-tier profile system (minimal/standard/full: 3-12 agents)
- 16 agent archetype templates with personality spectrum
- 18 skill templates using domain-action naming convention
- Stakeholder persona panel for workshops and PR reviews
- SQLite ticketing DB with CLI tools (config-based DB paths)
- Decision tracking, sprint lifecycle, workshop orchestration
- Multi-git-host support (GitHub, Gitea, GitLab)
- /kit-update skill for syncing with source repo evolution
- Naming theme support for agent identity/flavor
- Smoke tests for all three profile tiers

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-18 02:22:30 +01:00

2.0 KiB

Raw Blame History

name, description, user-invocable, allowed-tools

name	description	user-invocable	allowed-tools
health-check	Generate team health metrics dashboard. Use when the user says "health check", "metrics", "team health", or invokes /health-check. Calculates sprint velocity, cycle time, PR turnaround, and decision coverage.	true	Bash, Read, Grep, Glob

Team Health Check

Generate a team health metrics dashboard covering sprint velocity, cycle time, PR turnaround, and decision coverage.

Workflow

1. Sprint Metrics

Calculate velocity and throughput trends:

db/connectors/sqlite-query "SELECT s.name, COUNT(CASE WHEN t.status='done' THEN 1 END) as done, COUNT(t.id) as total FROM sprints s LEFT JOIN tickets t ON t.sprint_id = s.id GROUP BY s.id ORDER BY s.id DESC LIMIT 5"

Compute:

Velocity: tickets completed per sprint (trend over last 3 sprints)
Cycle time: average time from in_progress to done
Completion rate: done / (done + carry-over)

2. Code Review Metrics

From git and PR history:

Total PR count and merge rate for the period
Time to first review (from PR open to first comment/approval)
Approval vs. rejection rate

3. Decision Coverage

Check alignment between decisions and implementation:

Active decisions without implementing tickets (orphans)
Decisions per domain file (architecture, perception, content, scope)
Open questions (Q-NNN items) and their age

4. Backlog Health

Assess the overall backlog state:

Total backlog size grouped by priority
Tickets without a team assignment
Stale tickets: no update in 30+ days

5. Output

Format as a structured dashboard:

## Team Health — {date}

### Sprint Velocity (last 3)
| Sprint | Done | Total | Rate |
|--------|------|-------|------|

### Cycle Time
Average: N days | Trend: improving/stable/declining

### Decision Coverage
| Domain | Decisions | With Tickets | Gap |
|--------|-----------|-------------|-----|

### Backlog
Total: N | Unassigned: N | Stale (30d+): N

### Risks
- {risk items with context and suggested actions}

2.0 KiB Raw Blame History