If you're running multiple agents on a project and keep losing track of who's doing what or which branches are safe to merge, this gives you the discipline of work items, ownership, and merge gates. It treats agents like teammates on a Kanban board: backlog, ready, running, review, blocked, merged. Each card has acceptance criteria, a branch or worktree, and explicit evidence before integration. The real win is forcing you to answer "who owns this, what changed, what gate failed" before merging anything. It works with dynamic workflow mode, tmux setups, or external orchestrators. Honest take: this is overkill for solo work but necessary once agent fan-out starts producing output that nobody can safely integrate.
npx -y skills add affaan-m/everything-claude-code --skill team-agent-orchestration --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot