From architecture-investigation
Audit a freshly-written investigation plan for gaps — vague verifications, missing schema rows, underweight phases, single-option strategies — then close every gap by re-reading the brief, re-reading the codebase, or grilling the user again via AskUserQuestion. Iterates until the plan is solid. Invoked by the `/architecture-investigation:investigate` orchestrator after `write-investigation-plan` and before the user reviews. Sets `status: reviewed` when done.
How this skill is triggered — by the user, by Claude, or both
Slash command
/architecture-investigation:peer-review-planThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. Identify the investigation id. If unclear, list `findings/*` and use `AskUserQuestion` to ask.
findings/* and use AskUserQuestion to ask.findings/<id>/plan.md. Must exist with status: draft or status: reviewed.findings/<id>/brief.md. Must exist with status: approved — the brief is the contract the plan delivers against. If the brief is not approved, refuse and tell the user to approve the brief first.You audit the plan, close gaps, and produce a tighter plan. The user reviews what you hand back. Catch what the plan writer missed.
verify-step can't check; doesn't match the brief's deliverablesVERIFICATION-FORMAT.md)For every gap, try in this order:
brief.md. Many plan gaps are downstream of a brief detail the plan writer missed.findings/<id>/items/... from a prior run if one exists. Plan refinements often look like prior runs.AskUserQuestion with 3–4 multi-choice options and a recommendation. Typical plan-grilling questions:
When a gap is closed autonomously, edit plan.md in place. When you grill the user, append the Q&A to grilling.md under ## Plan refinement Q&A (from peer-review-plan) so the trail stays in one file.
Same loop as peer-review-brief. Max 3 iterations. After 3, surface remaining gaps to the user via AskUserQuestion and let them choose Answer now / Accept with gaps flagged.
Set plan.md frontmatter to status: reviewed. Hand back to the orchestrator.
npx claudepluginhub grooviz/aqzsedrf2 --plugin architecture-investigationCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.