GitHub
creating-wizards
Meta-skill for building multi-step AskUserQuestion wizard flows. Use when designing onboarding, configuration, or any multi-question user interaction.
Skills IA research llm ai
Découvrez les skills research llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: research llm ai
research llm ai Effacer les filtres
Explorer
GitHub
forging-skills
Prevents skill atrophy by periodically halting for user code writing and review. Use when senior engineers want to stay hands-on while leveraging agentic AI.
GitHub
agent-memory
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'...
GitHub
nanobanana-prompt-writer
Nano Banana（Gemini のネイティブ画像生成）向けに、用途（ロゴ/EC物撮り/サムネ/ステッカー/文字入り/ミニマル/差分編集/参照画像固定など）をヒアリングし、 "タグ盛り"ではなく撮影・制作ブリーフ形式で一貫性の高い高品質...
GitHub
agent-memory
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'...
GitHub
skill-skillsmith
ユーザーの入力（やりたい作業・標準化したい手順・テンプレ要求）から、Claude Code Skills（Agent Skills）のフォルダ構成とSKILL.md一式を生成する。 「〜のSkillを作って」「Claude Code skillsを書いて」「この作業をスキ...
GitHub
mcp-builder
指南：创建高质量的 MCP（模型上下文协议）服务器，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python（FastMCP）还是 Node/TypeScript（MCP SDK）。
GitHub
skill-creator
创建有效技能的指南。当用户想要创建新技能（或更新现有技能）来扩展Claude在专门知识、工作流程或工具集成方面的能力时，应该使用此技能。
GitHub
prompt-engineering-patterns
掌握高级提示工程技术，以最大化生产环境中LLM的性能、可靠性和可控性。在优化提示、改进LLM输出或设计生产提示模板时使用。
GitHub
doc-learner
智能文档学习和内容模仿技能。当需要：(1) 分析和学习优秀文档的结构、风格和写作模式，(2) 从文档中提炼关键要素和模板，(3) 基于学习内容生成模仿材料，或 (4) 创建新的提示词或技术文档时使用此技能。支持提示词工程、技术...
GitHub
subagent-creator
创建具有自定义系统提示和工具配置的专业化 Claude Code 子代理。当用户要求创建新的子代理、自定义代理、专业助手，或为 Claude Code 配置特定任务的 AI 工作流时使用。
GitHub
checkpoint-manager
Skill for tracking and managing task progress. Checks pending tasks at conversation start, proposes task creation for new requests, suggests completion reports when work is done. Integrates with checkpoint syst...
GitHub
backend-controller-pattern-integration
Provides NestJS Controller patterns for Integration endpoints. This skill should be used when building endpoints for external integrations like Google Sheets or Webhooks.
GitHub
service-pattern
Provides general guidance for implementing service layers in backend applications. This skill should be used when designing service architectures, implementing CRUD operations, or organizing orchestration servi...
GitHub
skill-creation
How to create new agent skills for this project. Use when proposing a new skill, documenting repeated patterns, or formalizing domain knowledge. Keywords: skill, SKILL.md, agent, create skill, new skill, meta.
GitHub
using-superpowers
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWri...
GitHub
orchestrator-agent
The Orchestrator Agent - Master coordinator for the Nebuchadnezzar v4.1 Pipeline OS. Manages the Four Pillars: Expert CRUD, Observability, ADHD Execution Loop, and Learning Propagation. This agent ensures all d...
GitHub
ai-native-workflow
Jeff Su's AI-Native Workflow framework (4 Habits) mapped onto Nebuchadnezzar v3.4 pipeline infrastructure. Use when: (1) "swipe file" or "what worked before" - retrieve proven email patterns by stage (2) "task...
GitHub
discovery-sales-expert
Unified discovery and sales execution expert consolidating 38 Questions, CVM White Glove methodology, email patterns, and stage playbooks. Use when: discovery calls, pipeline execution, email drafting, stage tr...
GitHub
meta-unify-core
Core configuration engine for meta-unify plugin. Parses user configuration requests, translates between Claude and Codex formats, and generates appropriate configuration files for both systems. Invoked by meta-...
GitHub
subagents-reference
Claude Code subagents configuration reference. Use when creating custom subagents, understanding agent types, configuring agent prompts, or extending the Task tool with specialized agents.
GitHub
skills-reference
Claude Code skills (Agent Skills) configuration reference. Use when creating skills, understanding skill activation, SKILL.md format, user-invoked vs model-invoked skills, or skill best practices.
GitHub
settings-reference
Claude Code settings configuration reference. Use when configuring Claude Code behavior, understanding settings hierarchy, or customizing project/user settings.
GitHub
test-app
Run integration tests on the Claude Code Orchestrator app. Use this skill to interact with the running app - click buttons, type text, take screenshots, and verify UI state. (project)
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.