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>
42 lines
1.9 KiB
Markdown
42 lines
1.9 KiB
Markdown
# {Project Name} — Team Roster
|
|
|
|
## Team Leader
|
|
|
|
- **{Name}** — Overall coordination, final decisions, user interface. Runs the main Claude Code session and delegates to specialists.
|
|
|
|
## Core Team
|
|
|
|
| Agent | Role | Focus |
|
|
|-------|------|-------|
|
|
| **{Architect}** | Technical Architect | System architecture, feasibility, technology decisions |
|
|
| **{PM}** | Project Manager | Sprint planning, ticket management, coordination |
|
|
| **{QA}** | QA Engineer | Testing, verification, quality assurance |
|
|
| **{Documenter}** | Documenter & Librarian | Decision records, briefings, document search index |
|
|
{Additional agents based on project profile — examples:}
|
|
| **{Frontend}** | Frontend Developer | UI implementation, components, styling |
|
|
| **{Backend}** | Backend Developer | Server logic, APIs, data layer |
|
|
| **{Designer}** | Systems Designer | Feature design, mechanics, user flows |
|
|
| **{Copywriter}** | Copywriter | In-app text, documentation, microcopy |
|
|
|
|
## Stakeholder Panel
|
|
|
|
Personas used in design workshops to stress-test decisions from different user perspectives.
|
|
|
|
| Persona | Perspective | Workshop Role |
|
|
|---------|------------|---------------|
|
|
| **{Power User}** | Depth, configurability, efficiency | Catches oversimplification, demands keyboard shortcuts |
|
|
| **{Casual User}** | Simplicity, onboarding, forgiveness | Catches complexity, demands progressive disclosure |
|
|
| **{Skeptic}** | Performance, reliability, edge cases | Catches optimism bias, demands failure modes |
|
|
| **{Advocate}** | Accessibility, inclusivity, clarity | Catches assumptions, demands universal design |
|
|
|
|
## Agent Briefings
|
|
|
|
Each agent has a briefing file at `docs/briefings/{name}.md` containing:
|
|
|
|
- Role description and responsibilities
|
|
- Current sprint context
|
|
- Key decisions relevant to their domain
|
|
- Working agreements and conventions
|
|
|
|
Briefings are updated after each decision-producing discussion round.
|