全部 Agent Skills
41,263 个结果
- Canvas DesignAnthropic官方依据设计理念生成 .png 与 .pdf 格式的海报、艺术作品等静态视觉设计,要求原创而非模仿现有艺术家作品。
- Claude APIAnthropic官方Claude Code 内置技能,提供 Claude API 与 Managed Agents 参考资料及 SDK 文档,覆盖 8 种语言。
- Doc CoauthoringAnthropic官方以结构化流程引导协作撰写技术规格、提案和决策文档,覆盖背景信息传递、迭代修改与读者视角校验。
- DOCXAnthropic官方Anthropic 官方 Word 文档技能,支持创建、读取、编辑 .docx/.dotx 文件,可处理目录、页码、修订与批注。
- Frontend DesignAnthropic官方在新建或改造前端界面时提供视觉设计指引,涵盖审美方向与字体排版,帮助避免模板化的默认样式。
- MCP BuilderAnthropic官方指导构建 MCP 服务器,让大模型通过工具接入外部 API 与服务,支持 Python FastMCP 和 TypeScript SDK。
- PDFAnthropic官方Anthropic 官方 PDF 技能,覆盖文本与表格提取、合并拆分、旋转、加水印、表单填写、加解密和扫描件 OCR。
- PPTXAnthropic官方Anthropic 官方 PowerPoint 技能,用于创建、解析和编辑 .pptx/.potx 演示文稿,支持模板、版式与演讲者备注。
- Skill CreatorAnthropic官方用于新建、修改和改进技能的元技能,可运行评测、做性能基准对比,并优化 description 以提高触发准确率。
- Web Artifacts BuilderAnthropic官方以 React、Tailwind CSS、shadcn/ui 构建多组件 claude.ai Artifact,用于需状态管理或路由的页面。
- Webapp TestingAnthropic官方基于 Playwright 与本地 Web 应用交互和测试,可验证前端功能、调试界面行为、截取浏览器截图并查看日志。
- XLSXAnthropic官方Anthropic 官方电子表格技能,处理 .xlsx、.xlsm、.csv、.tsv 文件的读写、公式、格式、图表与脏数据清洗。
- Superpowersobra (Jesse Vincent, Prime Radiant)技能合集基于可组合技能的软件开发方法论,引导代理先澄清需求并写实施计划,再按 TDD 与子代理驱动开发执行。
- Scientific Agent SkillsK-Dense技能合集面向科研的技能库,含 177 个技能和 100 多个科学数据库,覆盖生物、化学、医学与药物发现。
- vercel-labs/agent-skillsVercel技能合集Vercel 发布的技能合集,包含 React/Next.js 性能优化规则、Web 设计规范审查和 Vercel 项目成本与性能审计。
- Hugging Face SkillsHugging Face技能合集Hugging Face 发布的 AI/ML 任务技能,覆盖数据集创建、模型训练与评测,入门技能 hf-cli 用于 Hub 常用操作。
- Trail of Bits SkillsTrail of Bits技能合集Trail of Bits 的 Claude Code 插件市场,提供安全研究、漏洞检测和审计工作流技能,Codex 也可直接加载。
- Gemini API skillsGoogle (google-gemini GitHub org)技能合集google-gemini 组织发布的技能库,帮助代理按当前 SDK 编写 Gemini API、Live API 和视频生成相关代码。
- AccessibilityMicrosoft官方Primary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.
- Agent CustomizationMicrosoft官方**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized…
- Agent Host E2e TestsMicrosoft官方Use when writing, recording, updating, validating, or troubleshooting Agent Host end-to-end and real-provider integration tests under src/vs/platform/agentHost/test/node/e2e and providerIntegration. Covers adding a cross-provider test, re-recording fixtures after an SDK bump, required cross-platform Azure validation, gating non-deterministic or platform-specific tests, and diagnosing replay…
- Agent Sessions LayoutMicrosoft官方Agents workbench layout — covers the fixed layout structure, grid configuration, part visibility, editor modal, titlebar, sidebar footer, and implementation requirements. Use when implementing features or fixing issues in the Agents workbench layout.
- Author ContributionsMicrosoft官方Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.
- Azure PipelinesMicrosoft官方Use when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes without waiting for full CI runs.