research
01Command
Deep research before planning. Launches parallel agents to search docs, web, and codebase, then synthesizes findings into actionable context.
Command
Deep research before planning. Launches parallel agents to search docs, web, and codebase, then synthesizes findings into actionable context.
Command
Run user acceptance testing against spec requirements for formal sign-off.
Command
Brainstorm a feature idea through conversation until it's ready for /spec.
Command
Start a new bugfix spec with structured bug analysis, design, and tasks.
Command
Run full post-completion pipeline (accept, docs, release, retro).
Command
Generate user-facing documentation from spec and implementation.
Command
Execute one spec task by running Claude in autonomous mode.
Command
Loop spec execution until all tasks are complete.
Command
Refine requirements or design for an existing spec.
Command
Generate release notes, changelog, and deployment checklist.
Command
Run a retrospective on a completed spec to capture lessons learned.
Command
Show status and progress of current spec.
Command
Regenerate tasks from updated spec requirements and design.
Command
Validate spec completeness and consistency.
Command
Run post-deployment smoke tests against a live environment.
Command
Start a new spec-driven development workflow for a feature.
Command
Extract and formalize domain terminology into a canonical glossary, flagging ambiguities and proposing precise terms. Saves to UBIQUITOUSLANGUAGE.md.
Command
Zoom out and provide a high-level map of modules and callers for unfamiliar code.
Command
Commands use / prefix in Claude Code and $ prefix in Codex. Execution scripts (spec-loop.sh, spec-exec.sh, etc.) are run from the terminal in your project root.