Central issue tracker for AI-assisted coding workflows. Manage tasks, track work, and maintain context with simple CLI commands.
npx claudepluginhub sentiolabs/arc --plugin arcShow 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
Search and browse arc documentation
Initialize arc in the current project
List arc issues with optional filtering.
Migrate legacy `~/.arc/projects/` configurations to server-side workspace path registrations.
Get oriented with the current project
Manage filesystem paths associated with the current project. Paths link directories to projects for automatic project resolution.
Output AI-optimized workflow context
Manage projects
Quick start guide for arc
Find ready-to-work tasks with no blockers
Manage the arc CLI itself (update, release channel)
Manage the arc server daemon
Show detailed information about an issue
Show project statistics
Agent team operations
Update an issue's status, priority, or other fields
Show which project is active and how it was resolved
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 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 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.
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.
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.
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 setup and 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 when encountering any bug, test failure, unexpected behavior, nil pointer, panic, or error that needs root cause investigation — especially when the user says "debug", "investigate", "why is this failing", "root cause", or pastes a stack trace or error log. This is the arc-native debugging skill that enforces systematic investigation before any fix attempt. Always prefer this over generic debugging when the project uses arc issue tracking.
You MUST use this skill at the end of any session, when the user says "land the plane", "wrap up", "done for the day", "finish up", "session complete", "push and close", or indicates work is complete. This is the arc-native session completion protocol that captures remaining work as arc issues, runs quality gates, updates arc issue statuses, commits, and pushes. Always prefer this over generic branch-finishing 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.
You MUST use this skill to break a design or feature into implementation tasks — especially after brainstorming, when the user says "plan this", "break this down", "create tasks", or wants to turn a design into actionable arc issues with exact file paths. Creates self-contained arc issues that subagents can implement with zero prior context. Always prefer this over generic planning when the project uses arc issue tracking.
You MUST use this skill after implementing a task to get code review — especially when the user says "review this", "check my code", "review the changes", or after any implementation task completes. Dispatches the arc-reviewer agent with git diff and task spec, then triages feedback by severity. Always prefer this over generic code review when the project uses arc issue tracking.
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.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
AI-powered development tools for code review, research, design, and workflow automation.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams