review-orchestratorlisted

Orchestrates all code review agents to audit recent .NET changes. Accepts --commits N or --days N to define review scope, discovers agents dynamically, runs them in parallel, and produces a severity-grouped report with actionable recommendations. Triggers on: code review, review code, review changes, audit code, check code quality, clanker check, state bloat, grab bag review, check for flag bloat, mutation review, clanker discipline.
e128/dotnet-reference · ★ 2 · Code & Development · score 71

Install: claude install-skill e128/dotnet-reference

# Review Orchestrator Skill ## Scope Parameters The user's message must include a scope. Extract it from natural language; if none is provided, ask for one. | Pattern in user message | Effect | |--------------------------------|---------------------------------------------------| | `days N` / `last N days` | `scripts/diff.sh --json` (days-scoped discovery) | | `commits N` / `last N commits` | `scripts/diff.sh --json` (commit-range discovery) | | `dry run` / `preview` | Discovery only, no agents | | `critical only` / `high+` | Filter report by min severity | ## How It Works ### Phase 1: Discovery 1. **Parse arguments** from user input 2. **Gather change context** — run `scripts/diff.sh --json` for working-tree intelligence (staged/unstaged files, affected projects, test coverage hints, and commit-range changed files). 3. **Filter to .NET files**: `.cs`, `.csproj`, `.slnx`, `.props` 4. **Detect mechanical files** — run `scripts/internal/mechanical-diff.sh --json`; files classified `MECHANICAL` (every changed token is a pure namespace-prefix substitution) are excluded from deep agent review. Add a one-line note to the report: "N files excluded: namespace rename only." This prevents a single mechanical refactor from inflating the diff 10-20x and wasting agent budget. 5. **Generate unified diff** for the review window — this is the primary input for all agents 6