Agent skills for Grok Build

Audit milestone completion against original intent before archiving

Cross-phase audit of all outstanding UAT and verification items

Run all remaining phases autonomously — discuss→plan→execute per phase

List pending todos and select one to work on

Review source files changed during a phase for bugs, security issues, and code quality problems

Auto-fix issues found by code review in REVIEW.md.

Systematic debugging with persistent state across context resets

Generate or update project documentation verified against the codebase

Socratic ideation and idea routing — think through ideas before committing to plans

Extract decisions, lessons, patterns, and surprises from completed phase artifacts

Post-mortem investigation for failed GSD workflows — analyzes git history, artifacts, and state to diagnose what went wrong

Import a GSD-2 (.gsd/) project back to GSD v1 (.planning/) format

Triage and review all open GitHub issues and PRs against project templates and contribution guidelines

Query, inspect, or refresh codebase intelligence files in .planning/intel/

Surface Claude's assumptions about a phase approach before planning

List active GSD workspaces and their status

Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents

Generate a comprehensive project summary from milestone artifacts for team onboarding and review

Plan an MVP-mode phase — captures an "As a / I want to / So that" user story, runs SPIDR splitting, then delegates to plan-phase

Initialize a new project with deep context gathering and PROJECT.md

Zero-friction idea capture. Append, list, or promote notes to todos.