Quality plugins

Static lint for Claude Code plugins and skills, with experimental LLM scoring for skills

1 skill · 3 commands · 2 agents

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

1 skill · 3 commands · 2 agents

Real-browser verification and assisted UI testing. /bymax-web-verify:test brings the full stack up (reuses or starts the backend, frontend in the Claude Desktop Browser pane) and walks a UI flow while the user watches, with console/network/server-log verification per step; agent-browser fallback in terminals. /bymax-web-verify:verify confirms a single web change in a live browser. /bymax-web-verify:setup installs the agent-browser CLI + Chrome in one shot. Depends on agent-browser; never bundles it. /bymax-web-verify:record captures a UI flow as a reviewable video: the project's own Playwright with video forced on for one run, human pacing (slowMo + resized timeout), trimmed and pacing-gated with ffmpeg/ffprobe, published with a plain-text walkthrough derived from the spec that ran.

4 commands · hooks

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

2 commands · 3 agents

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

2 commands · 3 agents

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

2 commands · 3 agents

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

2 commands · 3 agents

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

2 commands · 3 agents

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

2 commands · 3 agents

Vendored from wshobson/agents (MIT, Seth Hobson) at c4b82b0: multi-perspective code review with code-reviewer, architect-review, and security-auditor agents. Its code-reviewer is the default commit-time reviewer.

2 commands · 3 agents

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

2 commands · 3 agents

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

2 commands · 3 agents

Agency workflow skills for Claude Code. Currently: mobile-first UX QA across a device matrix, a dedicated iPhone Duo foldable QA, and a client proposal generator.

3 skills · 1 command

코드 리뷰, 테스트 자동화, 품질 검증 도구 (Suites 3.x 기반)

1 skill · 1 command · 2 agents

網羅的 E2E の 4 フェーズ分解 (環境セットアップ / propose 段階のケース列挙 / 実装 / 実行と結果報告)。Web=Playwright, モバイル=Maestro

4 skills

Lazy senior dev mode — forces the simplest solution that works (YAGNI, stdlib first, no unrequested abstractions). Forked from ponytail by Dietrich Gebert.

3 skills · hooks

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

2 commands · 2 agents

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

2 commands · 2 agents

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

2 commands · 2 agents

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

2 commands · 2 agents

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

2 commands · 2 agents

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

2 commands · 2 agents

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

2 commands · 2 agents

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

2 commands · 2 agents

Brutally honest, massively parallel audit + verification + remediation loop over a codebase, branch, PR, working tree, or recent change window. Bundles deep-audit + parallel-hardening-loop skills and a /parallel-harden slash command.

2 skills · 1 command

Multi-session code review with auto-fix loop. Isolated reviewer sessions for unbiased review.

2 commands · 1 agent

Make staleness fail a check instead of relying on someone remembering. Sets up hash-and-compare guards for summaries, translations, generated files and any fact restated in prose. Carries the discipline too: fix the class not the instance, and a new check is guilty until it has failed on demand.

1 skill · 1 command

Adversarially verifies artifacts by having an independent skeptic attempt to disprove them

1 skill · 1 agent

Choose a coding-standards profile for Python or React, see what each rule turns on and what it costs to satisfy before you say yes, and have it written into the configuration your linter already runs — with the half no linter can check handed back, labelled unenforced.

1 skill · hooks

Review standardisée de Pull Requests GitHub ou Azure DevOps avec note /20, ressenti global, axes d'amélioration et alignement avec les US rattachées

1 skill · 1 agent