arc

Show blocked issues

Close an arc issue that's been completed.

Create a new arc issue. If arguments are provided:

Database management commands

Manage dependencies between issues

Use this agent for implementing a single task using TDD. Dispatched by the implement skill with a task description from arc. Receives task context, implements following RED → GREEN → REFACTOR → GATE, commits results, and reports back.

Use this agent for reviewing code changes against a task spec and project conventions. Dispatched by the review skill with a git diff and task description. Reports findings categorized by severity. Read-only — never modifies code.

Use this agent for documentation-only tasks. Dispatched by the implement skill for tasks labeled `docs-only`. Writes/updates markdown and docs without TDD overhead.

Use this agent for adversarial evaluation of implementation work against a task spec. Dispatched by the implement skill after the implementer completes. Writes independent acceptance tests from the spec alone — never sees the diff or the implementer's tests. Reports spec-intent gaps the implementer may have missed.

Use this agent when the user needs to interact with the project's issue tracking system via the `arc` CLI tool. This includes: finding recommended work (ready tasks, priorities, what to work on next), creating issues/epics/tasks, updating issue properties (status, priority, labels), closing issues with resolution notes, managing dependencies between issues (blocks, related, parent-child, discovered-from relationships), performing bulk operations (triage, closing multiple issues, creating epics with children), querying issues (listing, filtering, searching, showing details), or viewing dependency trees and blocked work analysis.

Deploy an agent team from arc's issue graph. Use when the user wants to parallelize work across multiple agents, parallelize epic tasks, says "deploy team", "spawn teammates", or wants to distribute arc epic tasks by role using teammate labels.

You MUST use this skill before claiming any work is complete, any test passes, or any fix works — especially before arc close, before telling the user "done", or when the user asks "does it work?", "did the tests pass?", "is it fixed?". Requires fresh verification evidence (not cached results). Always prefer this over ad-hoc verification when the project uses arc issue tracking.

General arc CLI reference and workflow context. Use when the user asks about arc commands, issue tracking workflows, when to use arc vs TodoWrite, or needs help with arc configuration.

You MUST use this skill for any design exploration, architecture decision, or trade-off analysis before implementation begins — especially when the user says "brainstorm", "explore the design", "think through", "what approach should we take", or describes a feature with multiple valid strategies. This is the arc-native brainstorming skill that writes designs to docs/plans/ and registers them for review via arc plan. Always prefer this over generic brainstorming when the project uses arc issue tracking.

You MUST use this skill to execute implementation tasks from an arc plan — especially when the user says "implement this", "build this", "execute the plan", "start coding", or wants to dispatch subagents for TDD execution of arc issues. The main agent orchestrates; it never writes implementation code directly. Always prefer this over generic implementation when the project uses arc issue tracking.

4 hooks across 3 events