vc-generate-plan

vc-audit-plans scans your active plan inventory to flag stale, completed, or obsolete artifacts and recommend archival or cleanup actions. It validates plan status against your codebase, detects misplaced task artifacts, and surfaces a summary table with classifications and next steps. Use it for periodic maintenance, post-burst reconciliation, or when plan cleanup has drifted.

vc-generate-spec turns research findings and user intent into a reviewable requirements document written for stakeholders, not engineers. It captures what users want and why before any implementation approach is chosen, serving as the authoritative bridge between discovery and planning. The skill enforces structured sections—from user stories through acceptance criteria—ensuring specs remain focused on observable outcomes and user-facing behavior.

This skill scaffolds multi-phase programs by generating an umbrella orchestration plan, Program Goal Charter, per-phase plan stubs, and a session-goal block. It enforces a 7-step inner loop (Research → Innovate → Plan-Supplement → PVL → Execute → EVL → Update-Process) with validation gates between phases, ensuring each phase is ready before the next begins. Use it when work naturally breaks into 3+ dependent phases across multiple packages or services.

vc-context-discovery is the canonical context-loading entry point for every agent session. It discovers and surfaces all nested files under process folders, extracts frontmatter metadata, and routes context by domain using keyword matching. Use the auto-discovery script or keyword-first routing to load exactly the docs your task needs.

vc-setup guides you through configuring an agent development harness tailored to your project. It detects your tech stack, asks clarifying questions to understand your codebase, then scaffolds the necessary directory structure and context files—always requesting approval before making changes. Works equally well on new projects and those with existing configurations.

vc-audit-context validates your project's context layer, routing tables, and shared-skill discovery across agents. Run built-in validators to catch missing context files, broken skill references, and protocol misalignment, then regenerate your machine-readable skill catalog.