AUV SceneBridge / view-memory lane code quality reviewer. Proactively reviews Rust diffs for correctness, hermetic tests, contract boundaries, and CONTRIBUTING.local.md veto items. Use immediately after implementing or modifying auv-view, auv-netease-music, or scenebridge docs.
Reviews staged changes (or a branch / PR) against this repo's firmware rules - split-role safety, USB endpoint budget, EEPROM layout, codegen sync, docs staleness. Writes the full report to .claude/code-reviews/ - .md and never fixes anything itself; the user reads the report and picks what to act on. Use proactively…
Reviews changes under lib/sync/, import/export, and MCP task write paths against the documented PocketBase v0.23+ gotchas plus prior Codex adversarial data-loss findings. Read-only. Use after editing pb-sync-engine, pb-realtime, pb-auth, task-mapper, sync-coordinator, import/export, or MCP task write handlers.
Architecture health analyst for ArchViber deepanalyze. Reviews the IR from a senior architect's perspective: coupling, layering, dependency direction, missing abstractions, blast radius of changes.
Reviews USS stylesheets and the C# strings that reference them against the Aspid.FastTools BEM grammar (class names) and the positional grammar (custom properties). Use after edits to any .uss file or to any code holding USS class names / --aspid- variables (Constants.cs, AspidStyles.cs, component .cs files).
Seams in this repo where two sides — a producer and a consumer — must agree on a shape neither the compiler nor a single-file review checks. Issue #127: the #121 stale-wiring bug (manifest advertised subcommands main.rs no longer dispatched) is this class. A reviewer existence-checking one side ("does the field…
Use this agent to verify a session's or handoff's factual claims against ground truth (git state, files, and read-only environment/production checks) and against the repo's invariants doc, BEFORE those claims are trusted, logged, or acted on. It catches confabulation — claims that sound done but aren't. Dispatch it at…
A read-only audit agent that waits for all audit parts to finish, then combines their findings into one report. It removes duplicates, groups issues by priority and file, and keeps supporting evidence and recommendations.
Use PROACTIVELY after changing Rust core/runtime/verifier/solver/refinement semantics. Audits symbolic BMC versus the solver-independent Monitor/BFS, false-negative risk, dependency boundaries, and cross-implementation evidence. Read-only on source; may run focused tests.
Reviews changes to this CopilotKit v2 + A2UI workshop app (server.ts, src/lessons, src/catalog, src/components) for known framework pitfalls and the repo's established patterns. Use after editing agent/runtime/lesson/catalog code, before committing.
Reviews the working diff for whodecided against its invariants, checks test coverage, and flags what only a human can verify. Use before committing or before merge.
Performs architectural review of files undergoing large-scale updates. Use proactively when refactoring, restructuring modules, or reviewing code organization. Provides actionable suggestions for renaming, moving functions, and restructuring modules.
Comprehensive code reviewer. Use when asked to review a PR, diff, branch, or specific files/folders. Spawns 7 specialized sub-reviewers in parallel, then synthesizes findings into a prioritized verdict.
Cross-artifact QA reviewer. Verifies LO coverage, Bloom balance, tone consistency, and alignment between slide/note/transcript/quiz. Returns pass/revise verdicts per class and per section.
Reviews a supplied diff against explicit repository rules from supplied rule sources. Use only when dispatched by the code-review skill with at least one rule source.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: