Code Review Skills

| Generates conventional commit messages using AI. It analyzes code changes and suggests a commit message adhering to the conventional commits specification. Use this skill when you need help writing clear, standardized commit messages, especially after making code changes and preparing to commit. Trigger with terms like "create commit", "generate commit message", or "write commit".

| Identify and avoid Exa anti-patterns and common integration mistakes. Use when reviewing Exa code, onboarding new developers, or auditing existing Exa integrations for correctness. Trigger with phrases like "exa mistakes", "exa anti-patterns", "exa pitfalls", "exa what not to do", "exa code review".

| Execute use when generating conventional commit messages from staged git changes. Trigger with phrases like "create commit message", "generate smart commit", "/commit-smart", or "/gc". Automatically analyzes changes to determine commit type (feat, fix, docs), identifies breaking changes, and formats according to conventional commit standards.

| Provides a GitHub pull request dashboard directly in the terminal. Use when the user wants to view PR status, check CI/CD progress, review bot comments, or merge pull requests without leaving Claude Code. Trigger with phrases like "show PR dashboard", "PR status", "check CI progress", "merge this PR", or "review pull request".

| This skill generates conventional commit messages using AI analysis of staged Git changes. It automatically determines the commit type (feat, fix, docs, etc.), identifies breaking changes, and formats the message according to conventional commit standards. Use this when asked to create a commit message, write a Git commit, or when the user uses the `/commit-smart` or `/gc` command. It is especially useful after changes have been staged with `git add`.

| Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin. it analyzes code for potential vulnerabilities like sql injection, xss, authentication flaws, and insecure dependencies. AI assistant uses this skill wh... Use when assessing security or running audits. Trigger with phrases like 'security scan', 'audit', or 'vulnerability'.

| This skill enables Claude to conduct a security-focused code review using the security-agent plugin. It analyzes code for potential vulnerabilities like SQL injection, XSS, authentication flaws, and insecure dependencies. Claude uses this skill when the user explicitly requests a security audit, asks for a code review with a focus on security, or mentions security concerns related to code. The security-agent plugin then provides structured security findings with severity ratings, code locations, impact assessments, and remediation guidance.

| Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "premium website", "portfolio site", "scroll animations", "Awwwards quality", or "brand experience". Covers dramatic typography, purposeful motion, scroll-based composition, and performance-optimized animation. For foundational UI, see refactoring-ui. For type selection, see web-typography. Trigger with 'top', 'design'.

| Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "UX review", "users are confused", "heuristic evaluation", "form usability", or "navigation problems". Covers Nielsen''s 10 heuristics, severity ratings, and information architecture. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology. Trigger with 'ux', 'heuristics'.

Automate 7-phase feature development with specialized agents (code-explorer, code-architect, code-reviewer). Use for multi-file features, architectural decisions, or encountering ambiguous requirements, integration patterns, design approach errors.

| Design and generate A2UI updateComponents and updateDataModel payloads for three modes (DTO component, non-DTO component, non-DTO page). Use when asked to create or refine A2UI cards, components, or pages from DTO/JSON/business data, generate Python transformer code for DTO-driven components, iterate on existing A2UI output files by diff, improve mobile UI quality, or validate A2UI rules such as surfaceId, root, path binding, and component-vs-page boundaries. Trigger when user mentions "A2UI", "a2ui", "AGenUI", "generate card", "generate page", "UI component", "生成卡片", "生成页面".

Use when refactoring code with poor names, when asked to improve naming, or when a user struggles to name a class/method/variable. Symptoms include -Manager/-Util suffixes, single-letter variables, process/handle/do verbs, primitive obsession, god methods with multiple responsibilities. Two modes — audit (broad scan, list opportunities) and improve (walk one specific identifier through the process).

Health-check the wiki: scan all pages for broken wikilinks, orphaned pages, stale index entries, missing connections, em-dash violations, orphaned assets, and schema errors. Produces a dated lint report. Always use this skill when the user says /wiki-lint, mentions broken links, dead wikilinks, orphaned pages, 'what's broken in my wiki', 'are my links working', 'which pages have no connections', or asks for a wiki health check. Also use when the user notices a link that doesn't resolve, suspects the index is out of date, or asks whether the wiki is in good shape - even if they don't say 'lint'. Never auto-fixes anything; reports only. When in doubt whether a wiki health check is being requested, use this skill. Requires filesystem read access and write access to archive/.

| Interactive code simulation engine that spawns ghost personas to review your code before it ships. Each ghost walks through your code line-by-line from a idempotency), The Enterprise Edge (business logic gaps, multi-currency, B2B tax exemptions, locale), Chaos Monkey (timeouts, partial failures, network partitions, OOM). Produces a chaos timeline, structured bug report with severity ratings, and three resolution tiers (quick fix, robust architecture, generated test suite). Use this skill whenever the user mentions code review, PR review, "find bugs", "what could go wrong", "will this break", "is this safe", "stress test", "edge cases", design review, pre-merge check, dry run, chaos test, or wants a second opinion on any code — even if they don't explicitly ask for "ghost personas" or "simulation". Also trigger when someone pastes a code snippet with any question about its correctness or safety.

> Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools — pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI is getting faster or slower, which GitHub Actions workflow is the slow or flaky long-pole, how long PRs take from open to merge, how an author's merge time compares to the cohort, which open PRs have failing or pending CI, or where a specific pull request is stuck. Triggers on "engineering analytics", "is CI getting slower", "slow workflow", "flaky CI", "time to merge", "cycle time", "PR throughput", "failing checks", "where is PR <n> stuck", "CI long pole", "what's holding up this PR".

Reads and analyzes source code files or project structures, identifies bugs, and suggests structural architectural or security improvements.

> Deep code audit that finds dead wiring, silent failures, unfinished features, placeholder stubs, bloated files, and unnecessary complexity. Produces an actionable doing a thorough PR review of the entire codebase. "find placeholders", "check for stubs", "prune the code", "code cleanup", "implementation review", "completeness check", "find unused code".

N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques, and a blind judge panel decides residual disputes. Manual-invoke ONLY: trigger when the user explicitly runs /adversarial-empirical-review or names 'adversarial-empirical-review' / 'adversarial empirical review'. Do NOT auto-trigger on generic 'review my results', 'check my tables', or manuscript-editing requests. For prose-style refinement use style-emulation instead; this skill AUDITS WHETHER THE TABLES ARE CORRECT — that each number in the tables is what the analysis code computes, reproduces from the data, and is internally consistent. It is an empirical + code review: the manuscript is read only to resolve table numbering, and prose is not examined.

| Diagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND pipeline over-predicts a label (precision low, recall high) and a prompt clarification is proposed to tighten it, (2) a pilot/validation gate fails and the fix candidates are prompt edits, (3) inter-rater agreement on the the exact feature the revision would exclude, no prompt can pass a gold-scored gate — recall craters while precision barely moves. Also documents the verified surgical-pilot design (single-section diff, tune/holdout split, pre-registered gate, perturbation check on untouched sections).

| pyfixest demeaner_backend="cupy64" (including its CPU fallback when cupy is absent) is NOT numerically identical to the default numba backend and does adding demeaner_backend="cupy64" to existing pf.feols/fepois calls changes the printed coefficient table, (2) a regression report suddenly gains rows with absurd estimates (e.g. coef 435.8, SE 7106) for controls absorbed by the fixed effects, (3) diffing outputs before/after a backend change, or (4) anything parses a pyfixest text report by line position.

Use when implementing any change in existing code — when tempted to clean up nearby code, add unrequested validation or options, fix something "arguably in scope", or when the diff is growing past what was asked.

Agent Teams PR review with Devil's Advocate. Spawns 5 team members — 4 specialist reviewers + 1 adversarial challenger — to produce confidence-rated findings. Only findings that survive cross-examination make the final report.

Perform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js), Brandur Leach (Postgres), Vercel Performance, Simon Willison (LLM pipelines), Karri Saarinen (UI quality), Vitaly Friedman (UX quality), Kent Beck (test quality). Uses parallel subagents for deep, independent review. Produces prioritised P1/P2/P3 findings. Stack: Next.js App Router / React / TypeScript / tRPC / Prisma / Neon / Clerk.

Language-agnostic workflow for code reviews and security audits using a Two-Axis (Standards vs Spec) approach against Clean Code/SOLID principles, generating formal refactoring plans.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Omni-expert principal software architect. Triggers on requests for app development, coding, refactoring, or architectural design. Enforces clean code, clean architecture, deep reasoning, mandatory testing, and strict anti-ambiguity protocols.

> Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Supports for over-engineering review (ponytail-review), repo-wide audit (ponytail-audit), and debt tracking (ponytail-debt).

Language-agnostic workflow for code reviews and security audits using a Two-Axis (Standards vs Spec) approach against Clean Code/SOLID principles, generating formal refactoring plans.

> Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Supports for over-engineering review (ponytail-review), repo-wide audit (ponytail-audit), and debt tracking (ponytail-debt).