Prompts
Prompt engineering and templates
american-airlines
by CodeDraig
Book flights, manage AAdvantage miles, check flight status, and access American Airlines services
codex-reviewer
by paskals
Use OpenAI's Codex CLI as an independent code reviewer to provide second opinions on code implementations, architectural decisions, code specifications, and pull requests. Trigger when users request code review, second opinion, independent review, architecture validation, or mention Codex review. Provides unbiased analysis using GPT-5-Codex model through the codex exec command for non-interactive reviews.
writing-style-skill
by Husseincartographical320
可复用的写作风格 Skill 模板。内置自动学习： 从你的修改中自动提取规则，SKILL.md 越用越准。 Fork 后改成你自己的风格。
list-templates
by tkarakai
List available AI agent instruction templates from the repository. Use to discover what templates can be loaded.
install-mcp-servers
by reapzyau
Automatically installs Apify MCP, Netlify MCP, and Context7 MCP servers to enable web scraping, deployment, and library documentation capabilities. Use when setting up a new project or when you need these MCP integrations.
prompt-builder
by aleister1102
"Guide users through creating high-quality GitHub Copilot prompts with proper structure, tools, and best practices."
gluegun-patterns
by vanman2024
Gluegun CLI toolkit patterns for TypeScript-powered command-line apps. Use when building CLI tools, creating command structures, implementing template systems, filesystem operations, HTTP utilities, prompts, or plugin architectures with Gluegun.
ok-skill-creator
by okash1n
agent-skills 配下で Claude/Codex/Gemini 互換の Agent Skill を作成・更新する。Skill の設計、実装、検証、リファクタ時に使う。Agent Skills 仕様準拠、frontmatter 検証強化、再利用スクリプト作成、~/nix-home/agent-skills 運用が必要な場合に使う。
parallel-task
by yuanxiao0115
Execute plan files by launching multiple parallel subagents to complete tasks simultaneously. Triggers on explicit "/parallel-task" commands.
debate
by aroc
Orchestrate a debate between Claude and Codex to reach consensus. Use when the user asks for a "second opinion", "debate", "consensus", "crosscheck", or wants another model to review a proposal or diff.
docs
by rahulgi
Agent-first project documentation. Scaffolds and maintains a documentation architecture designed for AI agents — ROADMAP, design-docs, logs, and more. Use when the user says "/docs", asks to set up project documentation, wants to update docs, or when starting a new project that lacks documentation structure. Also use when the user asks to plan a feature (creates a design doc) or review what's been done (updates logs/roadmap).
developing-claude-plugins
by lenneTech
Develops, optimizes, and validates Claude Code plugins, skills (SKILL.md), commands, agents, hooks (hooks.json), and scripts. Ensures consistency with official best practices. Activates when creating, editing, or reviewing files in plugins/ directory, .claude-plugin/, plugin.json, permissions.json, or marketplace.json. Covers YAML frontmatter, element structure, cross-references, naming conventions, and plugin manifest validation. NOT for application development (use domain-specific skills).
Social Creator Toolkit — 全平台内容发布工具包
by AKOR35TH
YouTube视频SEO指南
bluepixel-editor
by gyh2556406
Use the BluePixel AI agent to edit images and videos via natural language prompts. Trigger when the user asks to edit, transform, enhance, restore, or manipulate images/videos using AI — including background removal, style transfer, object editing, text removal, super resolution, and image restoration. BluePixel is an open-source project by vivo Image Group.
code-review
by nicolas-codemate
Performs code review via isolated fresh agent with no conversation context. Use when running /resolve workflow step 08, /review-code command, or when user asks to "review code", "review changes", or "code review". Delegates to code-reviewer subagent to prevent confirmation bias.
react-native-update
by reactnativecn
Unified integration skill for React Native Update / Pushy（统一入口）across OpenClaw and Claude Code workflows. Use for 安装配置, appKey/update.json 接线, iOS/Android 原生改动, 更新策略（checkStrategy/updateStrategy）, expo-updates 冲突排查, and 热更新接入 troubleshooting in mixed agent CLI environments.
vibe-writing
by qingchunwuhui
AI辅助写作工作流，通过四阶段流程（学习→结构→写作→成稿）帮助用户高效创作。适用于：(1) 写文章/博客/报告时需要整理思路，(2) 有想法但不知如何组织结构，(3) 需要通过对话激发灵感，(4) 希望AI辅助但保持内容控制权。触发词：写作流程、vibe writing、知识卡片、内容创作、文章结构化
openart
by openclawart
AI Agent NFT Arena - Compete with creative prompts, win NFTs on Base
httpsdocsbaseorgget-startedllmstxt
by hk-vk
Start here to understand Base, browse products and use cases, and follow quickstarts to build apps, tokens, chains, and contracts.
gulf-middle-east-hybrid-intelligence
by vassiliylakhonin
Vertical specialist skill for AI agents working on the Gulf and Middle East — Iran sanctions, GCC financial and energy hubs, maritime chokepoint risk (Hormuz, Bab-el-Mandeb, Red Sea), sovereign wealth deployment, and regional geopolitical exposure. Produces mechanism-first, evidence-aware, role-based risk memos. Use for Iran, GCC states (Saudi Arabia, UAE, Qatar, Kuwait, Bahrain, Oman), Iraq, maritime chokepoints, and cross-regional flows involving Central Asia, Russia, China, or the EU when they affect Gulf or Iran risk transmission.
hook-skill
by maxoreric
Claude Code Hook 开发专家。当需要创建、调试、配置 Hook 时触发。触发词：创建 hook、写 hook、hook 配置、stop hook、pre tool use、post tool use、session start。
SKILL.md — Claude 작업 전 필수 확인 규칙
by kyungsooNa
JSONL 로그 분석 시 assistant/user 턴 기준으로 LLM 대기·Tool 실행을 구분하는가?
orchestrating-agents
by arielperez82
Orchestrates parallel API instances, delegated sub-tasks, and multi-agent
loop-start
by secret-mars
Set up and start the autonomous agent loop