8 Plugins aus öffentlichen Claude Code marketplaces. Jedes bündelt Skills, Slash-Commands, Agents, Hooks oder MCP servers, die zusammen installiert werden.
testany-agent-skillsTestAny-io/testany-agent-skills1
review-protufantunc/review-pro1Reiche das repo mit .claude-plugin/marketplace.json ein und wir listen jedes plugin auf.
Marketplace einreichenConvert long markdown files into world-class single-file interactive HTML — DOMAIN COMPLETE at v2.10.3 (5 skills). v2.10.3 adds md-slides, the slide-deck converter (arrow/Space/PgDn/Home/End/P navigation, presenter mode with clock + speaker notes + next-slide preview, URL-hash deep linking, @media print page-per-slide for browser-native PDF export; vanilla JS only; Prism.js opt-in via --syntax). Joins md-review (v2.10.2 code-review converter: 2-col diff, severity-tagged margin annotations, WCAG-1.4.1 badges, named reviewer footer), md-document (v2.10.1 long-form: sticky TOC, scrollspy, search, code-copy, Prism autoloader), markdown-html-orchestrator (v2.10.0 context: fork; deterministic doc-type classifier), and design-system (v2.10.0 onboarding wizard; WCAG-AA 12-token palette). 15 stdlib-only Python tools, 15 references, 4 template assets. Inspired by Thariq Shihipar's Claude Code HTML output essay.
Universal Claude Code workflow with specialized agents, skills, hooks, and mode commands for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
A markdown brain that gives your AI coding tools judgment and rigor. Skills: init, build, debug, performance, qa, interview, learn, signature, persona, route, lint, clarify, deepen, double-check, deprecate, roadmap, assess, constitution, living-docs, specify, blueprint, breakdown, checklist, analyze, converge, prototype, explain, prompt, quarantine, report, handoff, levelup, help + agents: architect, code-reviewer, refactorer, tech-scout. Experimental (v0.33.2).
研发流程与导航工具集：Delivery Secretary、BRD、UC、PRD、UI Design、Prototype、API、分层及有限变更 HLD/LLD Review、Code Writer、授权溯源 Code Review、Test、Runbook。命令：/testany-eng:guide, /testany-eng:delivery-secretary, /testany-eng:brd-interviewer, /testany-eng:uc-interviewer, /testany-eng:prd-writer, /testany-eng:prd-reviewer, /testany-eng:ui-designer, /testany-eng:prototype-designer, /testany-eng:prototype-reviewer, /testany-eng:api-writer, /testany-eng:api-reviewer, /testany-eng:guardrails-writer, /testany-eng:guardrails-reviewer, /testany-eng:hld-writer, /testany-eng:hld-reviewer, /testany-eng:test-strategy-writer, /testany-eng:test-strategy-reviewer, /testany-eng:lld-writer, /testany-eng:lld-reviewer, /testany-eng:code-writer, /testany-eng:code-reviewer, /testany-eng:test-spec-writer, /testany-eng:test-reviewer, /testany-eng:runbook-writer
Tiered AI code-review: triage -> relevant specialist reviewers -> synthesis. Built to catch what AI-written code actually ships with: code that ignores what the repository already knows, needless dependencies, over-engineering, hallucinated APIs.
Review a code change for correctness, security, maintainability, and test adequacy, and reach a defensible verdict. Use when reviewing a pull request, diff, patch, or AI-generated change; when scoping an oversized review into reviewable units; when writing or triaging review comments; when assigning reviewers or setting review policy; or when investigating why a defect escaped review. Covers change sizing and attention budgets, risk-tiered checklists, severity-labeled comments, verdict and residual-risk records, review metrics that resist gaming, and the measured limits of checklists and AI reviewers. Do not use for implementing the requested change, root-cause debugging of a failing test or incident (use systematic-debugging), security assessment of a whole system (use security-audit-methodology), designing new code securely (use secure-software-engineering), architecture review across systems (use software-architecture), or reverse-engineering an unfamiliar codebase (use software-arc
Hotspot-first deep code review: change map → risky hotspot selection → per-hotspot lens subagents → skeptic pass → comment budget. Surfaces at most 5 high-signal findings or questions per run.
