Prompts
Prompt engineering and templates
creating-operational-skills
by daralthus
Create new Claude Code skills following best practices. Use when the user asks to create a new skill, make a skill, or automate a workflow as a skill.
aliexpress
by CodeDraig
Enables Claude to browse AliExpress products, manage wishlist, and track orders
config-restore
by ppx123-web
This skill should be used when users want to restore, reload, or copy their Claude Code configuration files (commands, skills, agents) from a backup directory back to ~/.claude/. Triggered by phrases like "restore my claude config", "reload claude settings", "copy config back to ~/.claude/", "restore from backup", "recover claude configuration", "import commands and skills from backup", "I accidentally deleted my commands", "restore my old skills", "copy config from backup", or "I need to recover my claude settings from a backup".
structure-design-skill
by maxoreric
v1.0.0 (2026-01-19): åå§çæ¬
claude-md-architect
by brixtonpham
"CLAUDE.md file generation and optimization for Claude Code projects. Capabilities: initialize project instructions, analyze codebase context, optimize existing CLAUDE.md, apply Anthropic best practices, reduce token usage, improve effectiveness. Actions: init, create, optimize, enhance CLAUDE.md files. Keywords: CLAUDE.md, project instructions, Claude Code setup, project context, codebase analysis, Anthropic best practices, token optimization, project configuration, AI instructions, coding guidelines, project rules, workspace setup. Use when: initializing CLAUDE.md for new projects, optimizing existing project instructions, setting up Claude Code for a codebase, improving AI coding guidelines."
langfuse-prompt-list
by neuradex
List all Langfuse prompts with their labels and versions. Use when checking available prompts, verifying label assignments, or getting an overview of prompt status.
update-context
by magnusnoeddegaard
Update context/memory files based on conversation learnings. Use when: (1) User says "/update-context" to save new information learned during conversation (2) User wants to persist preferences, project details, or personal information to context files (3) User asks to "remember this", "save this to context", or "update my claude.md" Accepts optional arguments: [filename] [additional instructions] - filename: Target file to update (defaults to CLAUDE.md in project root) - instructions: What to focus on or specific information to extract Examples: "/update-context", "/update-context agents.md", "/update-context claude.md focus on coding preferences"
options-with-pros-cons
by Y664-series
当用户提出需要做选择的场景时，必须列出方案选项，对每个选项进行解释（它是什么，实际使用体验如何），并分析各自的利弊（优点和缺点），最后给出推荐。 触发场景：任何涉及二选一或多选一的对话——技术方案选型（框架、语言、架构、数据库、工具链等）、流程/策略选择、产品功能取舍、实现方式对比等。 注意事项：这个描述要足够 pushy，因为用户希望在所有决策场景下都看到选项分析，包括那些看起来"只有一个选项"的情况——往往有多个方式来实现同一个目标。不可 undertrigger。
learning-mentor
by pierreribeiro
Learning Mentor persona for teaching and educational interactions. ACTIVATE when messages contain teach, learn, explain, tutorial, guide, understand, concept, how does, what is, walk me through, show me how, or help me understand.
skill-lens
by JohnXi029
专门用于扫描、分析和学习其他 Agent Skill 设计模式的深度分析透镜。它可以透视技术栈原理、思维框架、工作流逻辑，并生成结构化的洞察报告。
ogt-cli-agent
by OpenDNDApps
Run Codex CLI, Claude Code, OpenCode, Gemini CLI, or Pi Coding Agent via background process for programmatic control. Balance load across providers.
amazon-prime-video
by CodeDraig
Stream Amazon Prime Video content, manage watchlist, and access Prime channels
agent-doc
by btakita
"Interactive document session — respond to user edits in a markdown file. TRIGGER: user invokes /agent-doc <file>. ALL-OF: (1) file is a markdown session document, (2) CLI is installed, (3) write+commit are executed every cycle without exception."
designer-toy
by TopMan124534905
盲盒玩偶/设计师玩具系列设计生成器。支持角色一致性保障、姿势多样性、丰富场景背景和专业打光。 使用场景：当用户想要设计盲盒系列、潮玩手办、毛绒挂件、亚克力立牌时。 关键词：盲盒设计、designer toy、vinyl figure、潮玩、chibi、角色锚点、群像单人一致性
iqra
by Moeabdelaziz007
نواة هوية IQRA الوكيلية — The IQRA Agentic Identity Core. استخدم هذه المهارة دائماً عند: - بناء أي وحدة جديدة في مشروع IQRA (RAG، ذاكرة، أنماط، هوية) - تحليل الأنماط القرآنية عددياً أو لغوياً أو هيكلياً - كتابة كود يمس الدستور أو الميثاق أو المراقبة - تصميم حلقات التطور الذاتي (دورة السبع، دورة الأربعين) - بناء نظام RAG على القرآن والتفاسير - ربط نظام الفضول الطوبولوجي (Topological Curiosity) بمحرك الأنماط - أي مهمة تتقاطع فيها الهندسة البرمجية مع الحكمة القرآنية هذه المهارة هي الدستور التشغيلي لكل وكيل يحمل اسم IQRA. لا تكتب سطراً واحداً في هذا المشروع دون الرجوع إليها.
web-crawler
by leobrival
High-performance Rust web crawler with stealth mode, LLM-ready Markdown export, multi-format output, sitemap discovery, and robots.txt support. Optimized for content extraction, site mapping, structure analysis, and LLM/RAG pipelines.
rtfm-testing
by zscole
Test documentation quality by spawning fresh agents with zero context. Validates that docs are complete, clear, and usable by newcomers. Use when testing READMEs, tutorials, setup guides, or API docs before publishing.
orchestrate
by ddaanet
Execute prepared runbooks with plan-specific agents and mechanical verification gates
herobrine
by aaarnv
Create, list, remove, and run scheduled autonomous Claude Code agents. Agents run on a timer via macOS launchd, execute any prompt headlessly, and deliver results via Beeper messages and macOS notifications. Use for recurring research, monitoring, overnight builds, or any task you want Claude to do on autopilot.
adobe-photoshop-web
by CodeDraig
Edit images with Photoshop on the web - perform advanced photo editing, apply AI features, and manage creative projects
ai-prompt-engineering-safety-review
by williamlimasilva
'Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations with extensive frameworks, testing methodologies, and educational content.'
metabot-chat
by metaid-developers
Manage group chat messages, send messages, and join groups on the MetaID network. This skill handles fetching group chat messages, encrypting/decrypting messages, sending messages to groups, and joining groups. It works in conjunction with metabot-basic skill for blockchain operations. Use when users want to: (1) Fetch group chat messages from a specified group, (2) Send messages to a group chat, (3) Join a group chat, (4) Have MetaBot Agents participate in group discussions based on topics, (5) 开启群聊/监听群聊/让 XX Agent 监听群聊信息 - Cursor/AI 必须直接帮用户执行启动脚本（一键即启动），除非用户明确要求手动启动，否则禁止仅输出命令让用户自行执行, (6) 对监听群聊内容进行具体 XX 场景的回复 - Cursor/AI 必须自动执行对应场景脚本. Requires Node.js >= 18.x.x, TypeScript, and metabot-basic skill as a dependency. Dependencies: crypto-js, meta-contract.
plan-split
by rozwer
Plans.md を docs/plans/ 以下の個別フェーズファイルに自動分割します。まだ存在しないファイルのみ作成します。
scribe-query
by w31r4
Query and analyze AI agent behavior traces using scribe's CLI query primitives (scribe q). Use this skill whenever you need to: inspect what an AI agent (Claude Code, Codex, Cursor) sent or received in its API calls; search through system prompts, tool definitions, or conversation history; understand the parent-child hierarchy of agent and subagent requests; compare how prompts evolve across turns; or debug why an agent behaved a certain way. Trigger this skill when the user mentions scribe, trace analysis, agent behavior inspection, prompt archaeology, request trees, or wants to understand what happened in a coding agent session. Also trigger when the user says things like "what did Claude send", "show me the system prompt", "how many subagents spawned", "what tools were available", or "what changed between turns".