trellis

Execute a Trellis task list by dispatching each task to a Claude Code subagent in its own context window. Use when the user says "build with sub-agents", "build with subagents", or when a feature has 5-20 tasks with dependencies between them. Reads `.specs/<feature>/tasks.md` produced by the tasks skill. Each subagent gets focused context (guidelines + plan + task + learnings) and returns results to the orchestrating session. Supports parallel execution of independent tasks via background subagents with worktree isolation.

Execute a Trellis task list using Claude Code's /batch command for bulk, patterned changes across many files. Use when the user says "build with batch" or when a feature involves repetitive changes across dozens or hundreds of files (e.g., migrating from one library to another, applying naming conventions, adding error handling patterns). Reads `.specs/<feature>/tasks.md` produced by the tasks skill. Translates the task list into one or more /batch invocations with worktree-isolated parallel agents.

Creates or updates .specs/guidelines.md with project-wide stack, conventions, and principles. Use when starting a project or when a fundamental technology decision has changed.

Use when user wants to Creates a pitch document at .specs/{feature}/pitch.md defining a problem domain with constraints, appetite, and solution shape. Use to frame a feature before writing a spec.

Use when user wants to Creates a technical plan at .specs/{feature}/plan.md translating a spec's functional requirements into architecture, technology, and code decisions.

Use when user wants to Creates a lightweight experiment document at .specs/sketches/{slug}.md to test a technical hypothesis before committing to a larger initiative.

Use when user wants to Creates a full functional specification at .specs/{feature}/spec.md defining what a system does and why. Use to write or revise feature requirements.

Executes implementation from tasks.json through a check-driven feedback loop. Use when all spec artifacts are ready and implementation should begin.

Prepare implementation by decomposing a plan into an ordered task breakdown at .specs/{feature}/tasks.json. Use when a plan is ready and you need discrete, verifiable units of work organized in phases.

Orchestrates the spec-driven pipeline (pitch → spec → plan → build) with review gates between stages. Use when running the full feature pipeline or resuming from the last completed stage.

Use when user wants to Reviews a spec for ambiguities across six structured categories and resolves them in place. Use after writing or revising a spec, or for a fresh completeness review.

Use when user wants to Creates a regulatory and privacy review at .specs/{feature}/compliance.md by evaluating the spec against applicable regulations (GDPR, FERPA, FIPPA, COPPA, SOC 2).

Show pipeline status for all features. Use when checking progress across the spec pipeline.

Initialize a project for Trellis by creating trellis.json, the specs directory, and guidelines. Use when setting up Trellis for the first time.

Run all project checks (lint, tests, plugin validation). Use when verifying project health.

Run all project linters (JSON, Markdown, Python, shell). Use when checking code style and formatting.

Bump the project version (major, minor, or patch) across all manifest files and add a changelog entry. Use when preparing a release.

Run the project test suite. Use when verifying correctness after changes.