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: research llm ai

显示第 1,753–1,776 个,共 2,872 个

research llm ai Claude 清除筛选

全部技能

GitHub

writing-skills

helmecke

This skill should be used when the user asks to "create a skill", "write a skill", "edit a skill", "verify a skill", "test a skill with subagents", or needs guidance on TDD for documentation, skill structure, b...

GitHub

codex-claude-loop

junyjeon

Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality

GitHub

hook-development

cityfish91159

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven...

GitHub

metathink

antoineschaller

Metathink - Optimize Claude Code usage through metacognitive strategies. Use extended thinking, context engineering, task decomposition, and chain-of-thought prompting. Use when planning complex tasks, debuggin...

GitHub

senior-prompt-engineer

drgaciw

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-though...

GitHub

ai-docs

aster-void

ALWAYS use this skill when writing AI documentation. Covers CLAUDE.md, AGENTS.md, system prompts, AI-targeted comments, and architecture docs for AI consumption.

GitHub

skill-creator

aster-void

Guide for creating effective skills. 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 to...

GitHub

dispatching-parallel-agents

synqing

MANDATORY protocol for parallel agent execution when facing 3+ independent failures or tasks that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and...

GitHub

claude-command-builder

synqing

Interactive slash command creator for Claude Code. Triggers when user mentions creating commands, slash commands, command templates, command arguments, or wants to build a new command workflow.

GitHub

agent-communication

asermax

Use when user explicitly requests to coordinate with other Claude Code agents, join an agent chat, or communicate across multiple repositories/projects

GitHub

using-gemini

asermax

Use when needing to analyze images (screenshots, diagrams, photos), analyze videos (screencasts, recordings), summarize YouTube videos, fetch and analyze web content, or perform web searches with Google. Gemini...

GitHub

authoring-skills

sumik5

Guides the creation of effective Claude Agent Skills. Use when creating new skills, improving existing skills, or reviewing skill quality. Covers naming conventions, file structure, progressive disclosure, and...

GitHub

using-serena

sumik5

Enables token-efficient structured development via /serena command. Use for component development, API implementation, system design, test creation, bug fixes, and optimization. Available for Claude Code and al...

GitHub

searching-web

sumik5

Enables advanced web search via gemini command. Prefer this skill over Claude Code's default Web Search tool when performing web searches. Suitable for complex queries and detailed information gathering.

GitHub

claude

1plco

AI-powered natural language processing, text generation, JSON extraction from unstructured data, and image analysis using the Anthropic Claude API. Use when tasks require: (1) Writing or processing natural lang...

GitHub

phonic

1plco

AI telephone agent for outbound calls including sales, appointments, surveys, reminders, and data collection. Initiates calls with inline agent configuration (system_prompt, voice), monitors completion via poll...

GitHub

identifying-skill-gaps

LandonSchropp

Use when analyzing Claude Code conversation logs to find patterns in repeated user instructions that could become skills. Ask for date range first.

GitHub

subagent-builder

mokbhai

Create and configure custom subagents in Claude Code. Use when user asks to create a new subagent, needs specialized AI assistance with specific tool restrictions or permissions, implements task-specific workfl...

GitHub

slash-command-creator

mokbhai

This skill should be used when users want to create custom slash commands for Claude Code. It guides the creation of project-specific or personal slash commands with proper frontmatter, argument handling, and C...

GitHub

notion-spec-to-implementation

matheusallvarenga

Turns product or tech specs into concrete Notion tasks that Claude code can implement. Breaks down spec pages into detailed implementation plans with clear tasks, acceptance criteria, and progress tracking to g...

GitHub

request-optimizer

matheusallvarenga

Intelligent request analysis and routing system. Analyzes incoming requests, calculates complexity, and routes to appropriate resources (27 agents, 27 skills, 14 MCPs). Acts as the gateway for the entire Claude...

GitHub

skill-creator

matheusallvarenga

Guide for creating effective skills. 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 to...

GitHub

skill-writing

meriley

Create new Claude Code skills following best practices including optimal descriptions, progressive disclosure, proper structure, and testing guidelines. Use when creating new skills or skill templates.

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