搜索

PythonReactSEOPDF

“Claude”的搜索结果

按技能名称、说明或 GitHub 作者匹配的结果。

分类目录

显示第 3,025–3,048 个,共 5,276 个

Claude 清除筛选

全部技能

GitHub

create-skill

Cygnusfear

This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

GitHub

agent-init

dyxushuai

Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an ex...

GitHub

tool-presets

89jobrien

Standardized tool set definitions for Claude Code agents ensuring consistent tool access across similar agent types

GitHub

analyzing-response-quality

C0ntr0lledCha0s

Expert at analyzing the quality of Claude's responses and outputs. Use when evaluating response completeness, accuracy, clarity, or effectiveness. Auto-invokes during self-reflection or when quality assessment...

GitHub

ui-spec-to-prompts

jscraik

Translate a UI spec into build-order prompts for UI generator tools (v0, Bolt, Claude). Use when a UI spec already exists and you need sequenced, self-contained prompts.

GitHub

ux-spec-to-prompts

jscraik

Use when translating UX specifications into build-order prompts for UI generation tools. Triggers when user has a UX spec, PRD, or detailed feature doc and needs sequential, self-contained prompts for tools lik...

GitHub

working-on-ancplua-plugins

ANcpLua

Primary instruction manual for working within the ancplua-claude-plugins monorepo. Use when creating, modifying, or debugging plugins in this repository.

GitHub

autonomous-ci

ANcpLua

Ensures Claude verifies both local tests AND remote CI before claiming completion. Use BEFORE any completion claims, commits, or pull requests. Mandatory verification with evidence.

GitHub

security-scanner

akira82-ai

安全扫描器。检测 Claude Code 自定义 skills 中的潜在恶意代码。当用户提到"安全扫描"、"检测恶意代码"、"skill 安全"或需要扫描 skill 时使用。

GitHub

update-docs

Cygnusfear

Update all documentation in .plans, CLAUDE.md files, docs, and .tasks to match current codebase state. Use when user asks to update docs, refresh documentation, sync docs with code, or validate documentation ac...

GitHub

file-name-wizard

Cygnusfear

Audit all filename and naming conventions in the codebase against CLAUDE.md standards and common patterns. Use when user asks to check naming conventions, audit filenames, find naming inconsistencies, or valida...

GitHub

docs-agent

CleanExpo

Maintains documentation files (README.md, .claude/claude.md, .claude/agent.md, API docs) for Unite-Hub. Ensures docs stay in sync with codebase changes. Uses Haiku model for cost-effective documentation generat...

GitHub

sync-docs

barleytea

Synchronize documentation and skills with codebase changes. Analyzes recent git changes and suggests updates to README, CLAUDE.md, and skills to keep documentation in sync.

GitHub

skill-iterator

Petrus-Han

Guide for iterating and improving skills. Use when updating an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

GitHub

zellij-worktree

barleytea

Zellij git worktree workflow guide including keybindings (Ctrl+o g/G), pane/session modes, worktree switcher, and parallel development with Claude Code

GitHub

opus-extended-thinking

frankxai

Leverage Claude Opus 4.5's extended thinking capabilities for deep reasoning, complex analysis, and multi-step synthesis. Use when problems require thorough deliberation before response.

GitHub

local-testing

devnogari

Use when testing features with local backend integration - runs codebase E2E tests by default, uses Claude in Chrome only when explicitly requested with --browser flag

GitHub

claude-code-frontmatter

ryugen04

Use when creating or editing Claude Code skills, agents (subagents), or slash commands. Provides complete YAML frontmatter property reference.

GitHub

mcp-manager

rysweet

Conversational interface for managing MCP (Model Context Protocol) server configurations in Claude Code

GitHub

claude-reflection

vamseeachanta

Self-improvement and learning skill that helps Claude learn from user interactions, corrections, and preferences

GitHub

git-worktree-workflow

vamseeachanta

Use git worktrees for parallel Claude Code workflows. Run multiple Claude instances on different features simultaneously without merge conflicts. Use for parallel development, multi-branch testing, and subagent...

GitHub

mcp-builder

vamseeachanta

Guide for building high-quality Model Context Protocol (MCP) servers that allow LLMs to interact with external services. Use when creating new MCP integrations, tools, or servers for Claude or other AI systems.

GitHub

repo-readiness

vamseeachanta

Prepare any repository for new work by analyzing CLAUDE.md, file structure, mission/objectives, and establishing work readiness state. Auto-executes before new tasks to provide context.

GitHub

agent-orchestration

vamseeachanta

Orchestrate AI agents using Claude Flow, swarm coordination, and multi-agent workflows. Use for complex tasks requiring multiple specialized agents, parallel execution, or coordinated problem-solving.

默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。

更多筛选

热度筛选

热门标签