Deterministic team development workflow for Claude Code. Enforces a mandatory sequence of phases (Setup → Brainstorm → Plan → Execute → Quality Check → Ship) with Linear integration, TDD requirements, and quality gates. Activates when working on issues/tasks, when user mentions Linear issues (e.g., ENG-123), when starting development work, when preparing to ship code, or when orchestrating parallel work on parent issues with sub-tasks. Commands: /team:task, /team:feature, /team:quality-check, /team:ship.
Enforces a deterministic phase-gated workflow (Setup → Brainstorm → Plan → Execute → Quality Check → Ship) with Linear integration and TDD requirements. Activates when working on Linear issues, preparing to ship code, or orchestrating parallel work on parent issues with sub-tasks.
/plugin marketplace add jeremyodell/claude-assistant/plugin install team-workflow@claude-assistant-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Enforces a deterministic, phase-gated development workflow with Linear integration and quality enforcement.
/team:task ENG-123
↓
Phase 0: Setup (fetch issue, update status, create branch)
↓
Phase 1: Brainstorm (design thinking, post to Linear)
↓
Phase 2: Plan (task breakdown, post to Linear)
↓
Phase 3: Execute (TDD for every change)
↓
Phase 4: Quality Check (/team:quality-check)
↓
Phase 5: Ship (/team:ship → PR + Linear update)
/team:feature PROJ-100 --parallel=3
↓
Validation (check sub-issues, detect cycles, Linear MCP)
↓
Setup (create feature branch from main)
↓
Wave 1: Spawn agents for tasks with no blockers
↓ [PROJ-101, PROJ-102, PROJ-103 run in parallel]
↓ Each runs /team:task, branches from feature branch
↓
Merge: Completed tasks merge back to feature branch
↓
Wave 2: Spawn agents for newly unblocked tasks
↓ [PROJ-104, PROJ-105 depend on Wave 1]
↓
Repeat until all tasks complete or fail
↓
Summary: Present results, offer next actions (PR, retry, etc.)
/team:task $ISSUE_IDStart work on a Linear issue. Enforces all workflow phases.
/team:feature $PARENT_ISSUE_ID [--parallel=N]Orchestrate parallel execution of sub-tasks under a parent issue. Analyzes dependencies, spawns color-coded subagents, and coordinates merges on a shared feature branch.
Arguments:
$PARENT_ISSUE_ID - Linear issue ID of the parent (e.g., PROJ-100)--parallel=N - Max concurrent agents (default: 3, range: 1-6)Execution:
blockedBy relations/team:quality-checkRun all quality gates. Blocks PR creation on failure.
Gates:
npm test - ZERO failuresnpm run lint - ZERO errorsnpm run typecheck - ZERO errors/code-review - ZERO high-confidence (≥80%) issues/team:shipCreate PR, update Linear to "In Review", post PR link.
Uses Linear MCP server for:
mcp__linear__get_issue - Fetch issue detailsmcp__linear__update_issue - Update statusmcp__linear__create_comment - Post design/plan/PR linksEvery change requires tests first:
There is NO change too small for TDD.
All gates must pass with ZERO errors before shipping:
Branch naming: feat/$ISSUE_ID-slugified-title
Commit format:
feat(ENG-123): brief description
- Main change
- Secondary change
Closes ENG-123
The plugin includes hooks that:
Phases 1-2 always use Superpowers for design thinking and planning.
Phase 3 (Execute) uses conditional execution mode:
| Plan Type | Execution Mode | Token Usage |
|---|---|---|
| Specific (code blocks, file paths) | Direct | ~60% less |
| Vague (exploration needed) | Subagent | Standard |
Flags:
--direct - Force direct execution--use-subagents - Force subagent executionRule of thumb:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.