Rechercher

PythonReactSEOPDF

Résultats pour « Claude »

Skills correspondant au nom, à la description ou à l’auteur GitHub.

Catégories: tools llm ai

2,353–2,376 sur 2,915

tools llm ai Claude Effacer les filtres

Explorer

GitHub

handoff

ramonclaudio

Session continuity for Claude Code. Gather context at start, archive state at end. Use when user mentions handoff, saving progress, or resuming work.

GitHub

claude-md

alexander-grieco

Write effective CLAUDE.md files that serve as persistent memory for Claude Code. Use when creating, reviewing, or improving project instructions for AI assistance. Triggers: CLAUDE.md, project instructions, mem...

GitHub

superclaude-enhancer

wade56754

SuperClaude 增强层 Skill,为其他 Skills 提供 SuperClaude 能力增强。 支持前置分析、后置审查、智能建议等增强模式。

GitHub

leo-wiggum

LeomaiaJr

Autonomous AI coding loop with PRD-based task tracking. Use when user says "leo-wiggum", "/leo-wiggum", "start leo loop", "autonomous coding", "run leo", or wants to implement a feature using iterative AI sessi...

GitHub

skill-creator

jayteealao

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

idea-exploration

nbbaier

Launch background Claude sessions to explore and analyze business ideas. Say "Idea: [description]" to trigger.

GitHub

ai-documentation-standards

randalmurphal

Write AI-readable documentation following concise-over-comprehensive principle, hierarchical CLAUDE.md/AGENTS.md inheritance (100-200 line rule), structured formats (tables over prose), parallel validation, and...

GitHub

mcp-integration

randalmurphal

Set up and use MCP (Model Context Protocol) servers to extend Claude Code capabilities including PRISM semantic memory, filesystem access, and database integration. Use when setting up MCP servers, debugging MC...

GitHub

agent-prompting

randalmurphal

Write effective prompts for Task tool sub-agents, slash commands, and system prompts. Covers Claude 4.x prompting patterns, context engineering, output format specification, and parallel delegation. Use when sp...

GitHub

ai-council

mkalhitti-cloud

Multi-AI collaboration protocol using shared file editing. Use when major decisions require diverse AI perspectives (Claude, Grok, Gemini, etc.) to debate and reach consensus. AIs write directly to debate files...

GitHub

skill-creator

moogah

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

worklog

lajarre

Generate a recap of recent Claude Code sessions with summaries of what was discussed and accomplished

GitHub

test-mcp-connector

StackOneHQ

ONLY trigger this skill when the user EXPLICITLY asks for MCP-based testing: **Required triggers (ALL must mention "MCP" explicitly):** - "test connector with mcp" - "test mcp connector" - "test [provider] wit...

GitHub

project-patterns

Keithagy

Project-specific architectural patterns and tribal knowledge. Copy this skill to your project's .claude/skills/ and customize with your team's conventions, decision trees, and critical pitfalls.

GitHub

kai-todo

robdtaylor

Manage Kai's task queue - capture topics to work on when Claude usage is available. Commands: - /kai-todo add - Add a new task to the queue - /kai-todo list - Show all queued tasks - /kai-todo next - Start wo...

GitHub

context

robdtaylor

Personal knowledge base integration via Obsidian vault. Provides semantic search, note retrieval, and context loading for Claude Code sessions. USE WHEN user says 'load context', 'search my notes', 'find in ob...

GitHub

agentobservability

robdtaylor

Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parall...

GitHub

research

robdtaylor

Multi-source parallel research using Perplexity, Gemini, and Claude. Three modes - Quick (1 query), Standard (3 queries), Extensive (8 queries). USE WHEN user says 'research', 'investigate', 'find out about', '...

GitHub

prompt-engineering

it-bens

Create, optimize, and debug high-performing prompts for Claude 4 models and GLM 4.7 (Z.ai) with production-ready templates and evidence-based techniques. Use this skill when the user asks to create a prompt, wr...

GitHub

cci

IdeaFlowCo

Search Claude Collective Intelligence knowledge base for solutions to problems. Use when the user asks about common issues, wants to find existing solutions, or mentions "CCI", "collective intelligence", or "kn...

GitHub

skill-creator

simula-labs

Create or update Claude Code skills. Use when user wants to create a new skill, update an existing skill, or needs guidance on skill design.

GitHub

full-stack-creator-and-doc-custodian

sergeville

Act as a versatile professional, seamlessly switching between Document Custodian (Signer), Software Programmer, and UX/UI Designer based on the user's task. This skill enables Claude to manage and certify offic...

GitHub

claude-command-development

LounisBou

Create slash commands for Claude Code with proper frontmatter, arguments, and bash execution. WHEN: MUST use when creating new slash commands. Invoke with "/claude-command-development" or "create a command", "n...

GitHub

claude-skill-development

LounisBou

Best practices for developing Claude Code skills with progressive disclosure and proper organization. WHEN: MUST use when improving existing skills. Invoke with "/claude-skill-development" or "improve skill", "...

Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.

Plus de filtres

Popularité

Tags populaires