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

2.8 KiB

Raw Blame History

name, description, user-invocable, allowed-tools

name	description	user-invocable	allowed-tools
team-onboard	Generate onboarding context for new agents or contributors. Use when the user says "onboard", "new to project", "ramp up", "context dump", or invokes /team-onboard. Creates a personalized learning path based on role.	true	Bash, Read, Grep, Glob

Onboarding Guide

Generate a personalized onboarding context package for new agents or contributors based on their role.

Workflow

1. Detect Role

Determine the newcomer's role from the command argument. If not provided, present the options:

developer — writing code (client, server, tooling)
designer — game design, systems design, UX
content — writing, narrative, copy, localization
ops — process, sprints, CI/CD, infrastructure
new-agent — AI agent joining the team

2. Generate Learning Path

Build a reading list tailored to the role:

All roles (core context):

CLAUDE.md — project instructions and conventions
TEAM.md — team roster and roles
decisions/README.md — decision index and domain map
Active sprint briefing — current work context

Developer additions:

Architecture decisions (decisions/architecture.md)
Relevant source directories (server/src/, client/scripts/)
Test patterns and how to run tests
Build and lint commands (make help)

Designer additions:

Scope and content decisions (decisions/scope.md, decisions/content.md)
Design docs (docs/design/)
Workshop history (docs/workshops/)

Content additions:

Content decisions (decisions/content.md)
Voice and tone guides
Content templates and examples

Ops additions:

Process decisions (decisions/process.md)
Sprint history (docs/sprints/)
Ticket workflow and CLI usage
CI/CD setup and configuration

New agent additions:

Agent personality files (.claude/agents/)
Example agent configurations
Briefing template (docs/briefings/)

3. Active Context

Provide a snapshot of current project state:

Current sprint:

db/connectors/sprint status

In-flight work:

db/connectors/ticket list --status in_progress

Recent decisions: Last 5 decisions by date from decisions/ files.

Open questions:

db/connectors/sqlite-query "SELECT id, title FROM decisions WHERE type='question' AND status='open'"

4. First Task Suggestions

Scan the backlog for good first tasks:

Low complexity, no blockers, well-described tickets
Tickets tagged as "good first issue" or similar
Tasks that help the newcomer learn the codebase while contributing

5. Output

Present a structured onboarding document with:

Ordered reading list (most important first)
Key context summary (don't make them read everything)
Current state snapshot
Suggested first actions with ticket references

2.8 KiB Raw Blame History