Skills publicadas
Mostrando 11 de 23deep-plan
Use when starting a new feature or idea that needs thorough pre-execution planning. Use instead of calling /product-review, /spec, and review skills individually.
claude-corps
Production workflow framework for Claude Code — multi-agent orchestration, parallel worktrees, autonomous task execution, and compound engineering skills
claude-corps
Production workflow framework for Claude Code — multi-agent orchestration, parallel worktrees, autonomous task execution, and compound engineering skills
claude-corps
Production workflow framework for Claude Code — multi-agent orchestration, parallel worktrees, autonomous task execution, and compound engineering skills
claude-corps
Production workflow framework for Claude Code — multi-agent orchestration, parallel worktrees, autonomous task execution, and compound engineering skills
debug
Use when facing a bug, test failure, or unexpected behavior that isn't immediately obvious
auto-run
Autonomous dispatch-reconcile loop for batch task processing. Use with /auto-run --through <id> to execute tasks unattended. Requires Linear MCP or tasks to exist. Supports --resume for checkpoint recovery and --skip-milestone-review.
benchmark
Use when you need measured performance evidence by running a repeatable command on the current branch and a baseline ref
claude-corps
Production workflow framework for Claude Code — multi-agent orchestration, parallel worktrees, autonomous task execution, and compound engineering skills
finish-task
Use when implementation and tests are complete and you're ready to close out a task
summarize-session
Use for a read-only progress snapshot without committing, pushing, or closing anything