Topic: claude-code
35,830 skills in this topic.
-
pdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
OpenCoworkAI/open-cowork 828
-
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
OpenCoworkAI/open-cowork 828
-
image-crop-rotate
Image processing skill for cropping images to 50% from center and rotating them 90 degrees clockwise. This skill should be used when users request image cropping to center, image rotation, or both operations combined on image files.
instavm/coderunner 815
-
pdf-text-replace
Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.
instavm/coderunner 815
-
playwright-debug
voicetreelab/voicetree 783
-
playwright-debug
This skill should be used when the user asks to "debug the electron app", "connect playwright to VoiceTree", "take screenshots of the running app", "interact with the live UI", "inspect the running application", or "test UI elements live". Provides step-by-step instructions for connecting Playwright MCP to a running Electron app for live debugging and automation.
voicetreelab/voicetree 783
-
using-git-worktrees
当需要开始与当前工作区隔离的功能开发或执行实现计划之前使用——创建具有智能目录选择和安全验证的隔离 git 工作树
jnMetaCode/superpowers-zh 771
-
receiving-code-review
收到代码审查反馈后、实施建议之前使用,尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证,而非敷衍附和或盲目执行
jnMetaCode/superpowers-zh 771
-
chinese-code-review
中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈
jnMetaCode/superpowers-zh 771
-
mcp-builder
MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力
jnMetaCode/superpowers-zh 771
-
chinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
jnMetaCode/superpowers-zh 771
-
chinese-documentation
中文技术文档写作规范——排版、术语、结构一步到位,告别机翻味
jnMetaCode/superpowers-zh 771
-
finishing-a-development-branch
当实现完成、所有测试通过、需要决定如何集成工作时使用——通过提供合并、PR 或清理等结构化选项来引导开发工作的收尾
jnMetaCode/superpowers-zh 771
-
chinese-git-workflow
适配国内 Git 平台和团队习惯的工作流规范——Gitee、Coding、极狐 GitLab 全覆盖
jnMetaCode/superpowers-zh 771
-
executing-plans
当你有一份书面实现计划需要在单独的会话中执行,并设有审查检查点时使用
jnMetaCode/superpowers-zh 771
-
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用
jnMetaCode/superpowers-zh 771
-
brainstorming
在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。
jnMetaCode/superpowers-zh 771
-
workflow-runner
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key,使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。
jnMetaCode/superpowers-zh 771
-
writing-plans
当你有规格说明或需求用于多步骤任务时使用,在动手写代码之前
jnMetaCode/superpowers-zh 771
-
test-driven-development
在实现任何功能或修复 bug 时使用,在编写实现代码之前
jnMetaCode/superpowers-zh 771
-
systematic-debugging
遇到任何 bug、测试失败或异常行为时使用,在提出修复方案之前执行
jnMetaCode/superpowers-zh 771
-
subagent-driven-development
当在当前会话中执行包含独立任务的实现计划时使用
jnMetaCode/superpowers-zh 771
-
requesting-code-review
完成任务、实现重要功能或合并前使用,用于验证工作成果是否符合要求
jnMetaCode/superpowers-zh 771
-
verification-before-completion
在宣称工作完成、已修复或测试通过之前使用,在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功;始终用证据支撑断言
jnMetaCode/superpowers-zh 771