“Code review”

Semantic code review with provable assertions about code quality

Review a change (a diff, a branch, or an implement pass's output) against the plan that authorized it and against engineering quality, then issue a verdict…

Structured Codex code review when explicitly requested.

Use when reviewing HarmonyOS (ArkTS/ArkUI) code, when file extensions are .ets/.ts in HarmonyOS context, or when checking ArkUI component implementations…

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Structured Codex, Claude, Amp, Pi, or Kimi code review when explicitly requested.

End-to-end quality assurance and secure engineering for any software repo: code review, test strategy, bug triage, debugging, flaky-test repair, coverage…

Comprehensive Vue.js 3 best practices, code review, and continuous learning skill.

ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX…

Review a set of code changes against two separate axes, Standards (does it follow this repo's documented rules?) and Spec (does it do what the issue/PRD…

Review session PRs, named PRs, or a repository.

Multi-angle diff review with a verify pass at a chosen effort level.

CEO/founder-mode plan review.

Automated Codex review loop for PR code.

Review a solution before approving it, like a GitHub changes tab: a file tree of red and green pseudo-code the user can comment on inline, then answer…

The review gate — effort-scaled, multi-angle review of the working diff or the changes since a fixed point, every finding independently verified.

Independent cross-tool review of finished implementation work — a diff against its brief and plan, reviewed by the other tool.

Game development workflow skills for Claude Code.

Developer role in AID methodology.

Measure JavaScript and TypeScript function complexity, join LCOV test coverage, compute CRAP scores, and gate delivery on a threshold.

Rendered guardrail framework: keep a repo's hard rules in one-rule-per-file GRL sources behind a compact router, and render only the rules a task needs.

Rigorous agentic engineering workflow — 23 playbooks and 23 principle rules for bug fixes, features, refactors, performance work, investigations, architecture…

Guide maintainable, resilient, test-double-friendly code: clear names, decomposition, safe defaults, idempotency, bounded retries, observability, and quality…

Find, verify, and synthesize scientific literature with traceable citations.