Browse Claude skills and plugins
Public Claude skills and plugins from Anthropic, OpenAI, Microsoft and the community. Waxell scans them for security issues and tracks every version. 5,404 have their own page.
- 24,090 skills and plugins reviewed
- 343 publishers
- 1,987 official
- 23,960 scanned
- 345 high risk
Browse by category
Pick an area to see what's out there.
- Engineering2,738 items
- Data & analytics1,486 items
- Finance424 items
- Legal & compliance354 items
- Documents1,048 items
- Writing & content759 items
- Design1,012 items
- Images, video & audio610 items
- Sales & marketing519 items
- Security337 items
- Research849 items
- Productivity1,241 items
- AI & agents1,451 items
- Other200 items
Official publishers
Published by the companies behind the tools.
From Anthropic
Skills and plugins from the people who make Claude.
- academy-guideAnthropicStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product, it recommends matching… No issuesProductivityAI & agents187k
- algorithmic-artAnthropicCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating… No issuesDesignEngineering187k
- brand-guidelinesAnthropicApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.… No issuesDesignAI & agents187k
- canvas-designAnthropicCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a… No issuesDesignDocuments187k
High risk
A critical finding in what's published. Read it before anyone installs these.
- claude-apiAnthropicReference for the Claude API / Anthropic SDK: model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model… High riskEngineeringDocuments187k
- discordAnthropicDiscord channel for Claude Code: messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /discord:access. High riskEngineeringLegal & compliance46k
- telegramAnthropicTelegram channel for Claude Code: messaging bridge with built-in access control. Manage pairing, allowlists, and policy via… High riskEngineeringLegal & compliance46k
aspireGitHubAspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev… High riskEngineeringData & analytics41k
Changed most recently
New versions from official publishers and popular repositories.
sleek-design-mobile-appssleekdotdesignDesign mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML. No issuesDesignEngineering597
sn-code-videoopensensenovaCreate and revise code-driven videos with Canvas, SVG, HTML/CSS, Three.js, Remotion, Manim, or p5.js, including sound, deterministic frame… No issuesImages, video & audioEngineering6k- sn-da-excel-workflowopensensenovaExcel 数据分析多步编排器。覆盖：(1) 读取多 Sheet Excel 文件并统计行数，(2) 大文件检测（≥10k 行自动 Parquet 优化），(3) 数据清洗（缺失值、文本标准化、无效字符），(4) 条件筛选与分类提取，(5) 跨 Sheet 统计聚合，(6)… No issuesData & analyticsProductivity6k
- large-file-parquet-analysis-and-highlightopensensenova当Excel文件总行数超过1万行时，通过转换为Parquet格式提升读取性能，提取目标指标并计算最大值，最后将结果输出为Excel并对特定行进行高亮标注。 No issuesData & analyticsDesign6k
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF