- Home
- /
- Categories
- /
- Prompts
Prompts
Prompt engineering and templates
chat-reply
by paulo20223
Generate a reply for a Telegram chat using mtcute. Use when the user asks to draft a reply, respond to a chat, or wants to send a message. Trigger phrases include "reply to chat", "draft response", "respond in chat", "write reply", "answer in chat".
skill-creator
by kimasplund
Guide for manually creating custom skills from scratch with templates and validation. Use when designing NEW skills with specific requirements. For auto-generating skills from existing git repos, use /generate-skills instead.
codex
by VisualxIntelligence
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.
hybrid-decision-analysis.v1
by squirrel289
'Hybrid decision workflow that combines expert rubric design, explicit evidence capture, hard-constraint gating, scenario bakeoffs, and deterministic scoring. Use when selecting skills, tools, architectures, workflows, or build-vs-buy options and when you need consistent, reliable, and auditable recommendations.'
nano-banana-skill
by vishalx360
Generates, edits, and restores images using Google Gemini image models (Nano Banana). Use when the user wants to create images from text prompts, edit existing images with natural language, restore or enhance photos, or generate icons, patterns, diagrams, or visual content. Requires a GEMINI_API_KEY environment variable.
skill-creator
by JonasJoe233
创建新 skill、改进现有 skill、运行评估测试 skill 性能。 触发词:创建 skill、新建 skill、魔改 skill、优化 skill、测试 skill、create skill、improve skill、edit skill、optimize skill description。 确定性触发(直接执行):用户明确说要创建/修改/优化某个 skill。 非确定性触发(先问):用户说"把这个流程固化下来"——询问:"要把它做成一个 skill 吗?"
olakai-add-monitoring
by olakai-ai
Add Olakai monitoring to an existing AI agent or LLM integration. AUTO-INVOKE when user wants to: add monitoring to existing code, integrate observability into a working agent, instrument an existing AI system, add tracking to LLM calls, wrap OpenAI/Anthropic clients, add analytics to working AI code, or retrofit monitoring to production AI. TRIGGER KEYWORDS: olakai, add monitoring, integrate monitoring, instrument, wrap client, observability, SDK integration, @olakai/sdk, olakai-sdk, existing agent, existing code, add tracking, analytics, telemetry, retrofit monitoring, existing LLM, existing OpenAI, existing Anthropic. DO NOT load for: creating new agents from scratch (use olakai-create-agent), troubleshooting issues (use olakai-troubleshoot), or generating reports (use generate-analytics-reports).
init-plugin
by blueif16
插件结构知识库(仅供其他skills引用,不直接调用)
multi-ai-collab
by takuan-osho
Orchestrate multiple AI agents with specialized personas for cross-review and collaborative development
amtrak
by CodeDraig
Book train tickets, check schedules, manage reservations, and access Amtrak Guest Rewards
gcalendar
by Sytex
Manage Google Calendar events. Use when user asks about calendar, events, meetings, appointments, or schedule. Supports multiple Google accounts.
DevTaskFlow
by frostedbatleague736
用自然语言发起开发任务,AI 驱动的开发流水线。Describe your idea, get working software. 适合产品、运营、业务人员从 0 搭建项目。
novel-agent-system
by day2561124-art
長篇群像小說 AI 寫作代理系統規格。Use when building, operating, or extending a ChatGPT App / MCP based fiction-writing agent that combines CAG, RAG, error reports, feedback learning, layered memory, Neural Critic, and Canon Guard for chapter drafting, proofing, rewriting, and settlement.
metabot-basic
by metaid-developers
Create and manage MetaID wallets and accounts. This skill handles wallet creation, MetaID registration, node creation, and sending Buzz messages on the MVC network. Use when users want to: (1) Create a new MetaBot (MetaID Agent)/robot/proxy with a wallet, (2) Register a MetaID account, (3) Create MetaID nodes, (4) Send Buzz messages to the MVC network. Requires Node.js >= 18.x.x and TypeScript. Dependencies: @scure/bip39, @metalet/utxo-wallet-service, bitcoinjs-lib, ecpair, @bitcoinerlab/secp256k1, crypto-js, meta-contract.
ticket-creator
by Sylla-BV
This skill should be used when the user asks to "create a ticket", "create a Linear ticket", "make a ticket", "write a ticket", "create an issue", "file a bug", "create a feature ticket", "write a bug report", "I need a ticket for...", "there's a bug in...", "turn this into a ticket", "write this up as a ticket", or wants to create any Linear issue for implementation.
audible
by CodeDraig
Browse and manage Audible audiobook library, discover new titles, and track listening progress
article-figure-spot
by invalidandnull
Scans full article text, finds every position that needs a figure, then either inserts inline image-generation prompts for the author to use or runs image generation for all spots and saves files. Use when the user wants to "add figures to article", "find where to put images", "generate all illustrations for this doc", or "文章配图"/"插图位置".
multirepo-space
by Tacuchi
Scaffold and manage multi-repo workspaces for AI coding agents. Delegates to the multirepo-space CLI (bundled). Use when user says "create workspace", "setup multirepo", "multi-repo workspace", "add repo to workspace", "remove repo from workspace", "workspace status", "check workspace health", "init multi-repo", "orchestrate repos", "link repositories". Also use when user has multiple repos and needs a central coordination point for AI agents (Claude Code, Codex, Gemini CLI).
insight-from-chat
by shadowcz007
从聊天或用户反馈中挖掘洞察:由 Agent 传入上下文,由模型自行判断反馈类别,并产出情绪倾向、需求与痛点、业务/产品机会的结构化摘要。触发示例:「从聊天挖洞察」「用户反馈分析」「痛点挖掘」「需求洞察」「insight from chat」。
template-skill
by straub
A template for creating new agent skills. Replace this description with a clear explanation of what your skill does and when agents should use it. Include specific keywords that help agents identify relevant tasks.
cross-star-analysis
by freeyiyi1993
十字星 · 5 格结构化分析 skill:输入一个对象(技术 / 产品 / 方法 / 概念 / 人物 / 事件),按二维坐标系强制拆成 5 格输出——中心 (What) + 上方 (父亲 / 起源 / Why) + 下方 (儿子 / 演进 / Future) + 左方 (变革派兄弟) + 右方 (保守派兄弟),附 mermaid quadrantChart 可视化。轻量、不调外网、靠模型已有知识 + 上下文,默认产出 md artifact 到 ~/obsidian_vault/wiki/cross-star/{slug}.md,可选生成 HTML 单页。 适合「调研一个 X 但只想要一页结构化认知」「写作 / arch review / 面试讲项目的开篇骨架」「想同时压住时间和竞品两条主线但又不想跑深度调研」。 支持参数:--html(同时产出 HTML 可视化版)、--interactive(逐格反问共建模式)、--update(强制走更新模式 + changelog)、--brief / --deep(控制每格字数)。 触发词:「十字星」「/十字星」「cross-star」「用十字星分析 X」「十字星拆解 X」「按十字星看 X」「五格分析 X」「这玩意儿用十字星过一下」「父子兄弟分析」「画一张十字星」。 也用于用户引用 [[cross-star-analysis]] 笔记、或在写作 / arch-review 开篇想要一张「时间轴 ⊥ 竞品轴」的结构图时主动触发。 不要在以下场景触发:(1) 用户只是问"X 是什么"——那是普通 Q&A,不需要 5 格强加;(2) 用户已经在用 [[fuxi-bagua]] 跑深度调研——别套娃;(3) 团队脑暴 / 多人共创——走六顶思考帽;(4) 要穷举可能性——用 MECE / 鱼骨;(5) 人物思维顾问——走 [[perspective]] 或 [[huashu-nuwa]]。
AEGIS — Skill Context
by Coussecousse
Scopes : wazuh rabbitmq middleware slm llm rag soar monitoring vault docker ci docs security
project-spinup
by JHaugaard
"Generate complete project foundations with personalized claude.md, Docker setup, and project structure. Supports Guided Setup or Quick Start."
agent-creator
by agdev
Expert guidance for creating effective Claude Code agents (subagents). Use when users want to create a new agent, update an existing agent, or learn agent design best practices. Covers agent architecture, prompt engineering, tool selection, model choice, and common pitfalls. Integrates with skill-creator when agent needs accompanying skills.