Quality plugins

UX laws knowledge base and frontend code reviewer. Analyzes HTML/CSS/JS/React/Vue/Svelte code against 30 Laws of UX principles. Provides actionable recommendations for improving user experience. Use when building UI components, reviewing frontend code, or learning UX best practices. v1.4.1: ux-reviewer agent canonical-lint compliant (LR-1..LR-3). v1.6.0: Каждый агент пакета получил секцию `## Model tier`: какой ЯРУС нужен его работе и почему ярус задаёт самая трудная стадия, а не самая частая. Там же сказано, что значение `model:` во фронтматтере — привязка Claude Code, а не требование: в OMP/OpenCode/Codex/Gemini этих имён нет, надо подставить модель своего яруса и при промахе промахиваться ВВЕРХ. Лестница ярусов — `docs/GUIDE-AI-SDLC-PDLC-RU.md` §6.2, здесь она не пересказывается.

1 skill · 2 commands · 1 agent · hooks

Multi-perspective code analysis covering architecture, security, and best practices

2 commands · 3 agents

Performance analysis, test coverage review, and AI-powered code quality assessment

2 commands · 2 agents

Blocks the agent from finishing after code changes until tests, build or lint have passed.

1 skill · 1 command · hooks

Grades MCP (Model Context Protocol) servers against a published 28-rule quality rubric.

1 skill

Three-layer quality evaluation framework for Claude Code plugins with Elo ranking

1 skill · 3 commands · 2 agents

Multi-perspective code analysis covering architecture, security, and best practices

2 commands · 3 agents

Performance analysis, test coverage review, and AI-powered code quality assessment

2 commands · 2 agents

Stops Claude from finishing a turn that skips, weakens or deletes tests, hardcodes answers or switches checks off.

1 skill · hooks

Grades MCP (Model Context Protocol) servers against a published 28-rule quality rubric.

1 skill

Verify-first guardrails for Claude Code: hooks that block made-up APIs, force-push, AI commit credit and unverified "done" claims.

61 skills · hooks

Read-only audits for HAX content: WCAG 2.0 AA accessibility, UDL 3.0, cognitive-load chunking, Gagné's events of instruction, Mayer's multimedia principles, OER Schema, and content rating. Each audit ends with HAX-specific remediation.

53 skills

Code quality and validation: clone detection, multi-agent E2E validation, performance profiling, schema testing

10 skills

Track quality, detect drift, evolve prompts and approaches with evidence. Four skills: track, review, evolve, status.

4 skills

Utility toolkit — validation and quality checks against Claude Code specs and repo conventions.

4 skills

Comprehensive link validation: portability checks, lychee broken link detection, path policy linting

2 skills

Fail-fast Typecheck → Lint → Test → Security Audit gate. Auto-detects Node.js and Python. Forbids the agent from suppressing errors. Zero runtime dependencies.

1 skill

Tools for reviewing code quality

1 skill

Strip the sycophancy. Makes Claude honestly audit its own claimed-complete work against 17 named under-delivery patterns instead of polishing a summary over half-finished tasks.

1 skill

Canonical Claude Code agents, skills, commands, and hooks - copy only the team your project needs.

Canonical Claude Code agents, skills, commands, and hooks - copy only the team your project needs.

Improves agent navigation through a repository, turns session detours into approved map-file changes, and reconciles documentation and non-code development files with current behavior. Includes audit-only review, an approved layout migration, README review, host consistency and repository hygiene.

4 skills · 1 agent · hooks

Code reviews with specialized agents for architecture, security, test coverage, and Quarkus best practices. Use this plugin for systematic code quality checks.

1 skill · 1 command · 3 agents

Multi-perspective code analysis covering architecture, security, and best practices

2 commands · 3 agents

Performance analysis, test coverage review, and AI-powered code quality assessment

2 commands · 2 agents

Keeps docs, Markdown and code comments in ASD-STE100 Simplified Technical English: a writing skill plus a two-pass hook (Jev score, then a full review)

1 skill · 1 agent · hooks

Holds a session inside the task it was given: one open task with the files it may touch and the command that ends it, a guard that refuses writes outside that list, and checks that each ship with a violation and a near miss so none of them counts as coverage before it has been shown to work. It mounts beside a planning tool's roadmap, enforces the session boundary and never enforces the roadmap.

2 skills · hooks

AI-powered architectural review and code quality analysis

1 command · 1 agent

Professional web accessibility auditor. Scans HTML, JSX, Vue, and Svelte for WCAG 2.2 Level AA violations with plain-English findings and concrete fixes.

1 skill

Runs the right formatter/linter on every file Claude writes - go, python, js/ts, rust, nix

hooks