Claude Code 플러그인
공개 Claude Code 마켓플레이스의 플러그인 6,118개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
공개 Claude Code 마켓플레이스의 플러그인 6,118개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
.claude-plugin/marketplace.json이 포함된 repo를 제출하면 모든 plugin을 목록에 추가합니다.
marketplace 제출Migrate, port, or rewrite a codebase or app to Rust from Python, JS/TS, Go, C/C++, Java, Ruby, or C#. Incremental, parity-proven, production-grade.
Timed online-assessment simulations with a deterministic timer and hidden-test grading, plus an interview mode. Original questions only.
productivityEvidence-backed writing principles and repository engineering for predictable, composable agent skills / 有证据支撑的可预测、可组合 Agent Skill 写作原则与仓库工程
workflowSafely reclaim disk space on a Mac: survey usage, auto-clear only pure caches, Trash anything riskier (reversible), ask before anything expensive, log every deletion.
productivityDrop a photo in Claude Code and get a video. Self-hosted LTX-2.3 (22B): text-to-video, image-to-video, keyframe interpolation, video-to-video, and IC-LoRA canny/depth/pose control, with synced audio. Deploys to your own Modal serverless GPU — a few cents a clip, no per-clip meter.
creativeWrite, structure, and revise Statements of Purpose, grad-school essays, fellowship statements, and MBA / MFA personal statements — built on genre-analysis research of real, successful SOPs.
Validates test quality beyond coverage: uses Claude subagents to generate intelligent mutations for source code, executes them via the project's native test runner, extracts survived mutants, generates mutation-todos.md with rationale, and persists run history to a SQLite logbook.
Use when the user needs ideas or a name — brainstorming, naming, developing an idea further, hybridizing ideas, stress-testing candidates, reframing a problem, or picking a final direction. Ideas persist in a per-topic logbook across sessions.
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.
Design and create a logbook — a shared, queryable, schema-stable working surface for agents and humans to append, annotate, and query across sessions.
Pre-launch security audit for web apps. Runs OWASP checks via shell scripts, then AI analyzes findings.
security字幕转文案:外文字幕翻译去广告,改成说得出口的中文逐字稿写入 Obsidian 待发布;默认保原意
逐字稿转文章:去口语化、加小标题、数据转表格、原稿留文末,产出 Obsidian Markdown 草稿
Apify 博主用法研究:搜索 YouTube、抓字幕、按发布日期整理链接并写入 Obsidian 待发布稿
YouTube 选题发现:搜索最近 48 小时新视频,话题聚类后写入 Obsidian 选题库
State machine design, changeset writing, engineering writing, and component API design skills.
engineeringBuild valid, fair educational assessments for any subject and grade: guided mode selection, test blueprint and topics-by-Bloom matrix, item drafting by format rules, per-item passports, a review checklist, and post-administration psychometrics (P-value, D-index, Rit, distractor analysis). Every generated item is flagged for mandatory human expert review.
The rep's daily loop: pre-call briefs, pipeline hygiene, account snapshots, post-call follow-ups.
The paper's canonical 7-role Data Journalist Agent pipeline
Consolidate scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at the top.
documentation