Task Trellis Teams

Creates Trellis issues — projects, epics, features, or tasks — one hierarchy level at a time. Use when the user asks to create, decompose, or break down a project, epic, feature, or task in Trellis (e.g. "create a project", "create epics for P-…", "break down feature F-… into tasks", "decompose epic E-…"). Routes to the type-specific creation flow for the requested level only and stops there — does not auto-recurse to child levels.

QA-validates a completed Trellis issue by exercising the changed code the way it runs in production — drafts a test plan, gets user approval, then executes it and reports pass/fail/blocked. Use when asked to "QA", "verify", "validate the behavior of", "exercise", or "smoke-test" a completed Trellis task, feature, epic, or project by ID. This is verification via execution, not re-running the automated test suite.

Claims a single Trellis task and runs a plan-then-implement workflow — researches the task and parent feature, plans the implementation, writes the code, calls complete_task, and hands off to the paired reviewer teammate. Leaves changes uncommitted for review. Use when the user asks to "implement task", "claim task", or "work on task" by ID or scope. For multi-task feature orchestration, use task-trellis-teams:implement-trellis-issues instead.

Orchestrates Trellis issue creation using Claude Code Agent Teams. Use when asked to "create trellis issues", "create and review issues", "create verified issues", or when you want issues created by a writer teammate and automatically reviewed by a reviewer teammate with direct-message fix loops.

Verifies Trellis issues against original requirements for completeness, correctness, and appropriate scope. Use when asked to "verify issue", "validate trellis issue", "check issue completeness", or "review created issue".

Orchestrates implementation of Trellis issues using Claude Code Agent Teams. Use when asked to "implement feature", "implement trellis issues", "execute feature with teams", "implement tasks via agent teams", or whenever an agent-teams-based implementation run is desired. The lead spawns a fresh developer/reviewer pair per leaf task; teammates coordinate review/fix cycles via direct SendMessage. Commits per wave by default; supports --no-commit, --no-docs, and --version flags. Recursive by default; unplanned non-leaf issues are skipped, never expanded.

Reviews code changes from a completed task implementation for correctness, completeness, and simplicity. Use when asked to "review implementation", "review task code", "code review", "verify implementation", or after completing an issue implementation.