copilot
<description> Ad-hoc development.
claude-ticket-system
.claude/tickets/ directory format and status management for local issue tracking
codex
Get alternative perspectives via OpenAI Codex on complex design decisions, architecture trade-offs, stuck debugging, or approach evaluation.
prose
|
agent-speak
Speak messages aloud using the published agent-speak CLI via npx. It uses ElevenLabs when configured and falls back to macOS say when available.
wagmi
React hooks for Ethereum and EVM blockchain interactions using Wagmi v3. Use when building React or Next.js apps with wallet connections, contract reads/writes, or blockchain state. Triggers on useAccount, useConnect, useContractRead, useContractWrite, WagmiProvider, ConnectKit, RainbowKit, or any React blockchain hooks. Do NOT use for Node scripts or non-React code (use viem skill instead).
viem
TypeScript patterns for low-level EVM blockchain interactions using Viem. Use when writing Node scripts, CLI tools, or backend services that read/write to Ethereum or EVM chains. Triggers on contract interactions, wallet operations, transaction signing, event watching, ABI encoding, or any non-React blockchain TypeScript code. Do NOT use for React/Next.js apps with hooks (use wagmi skill instead).
cloudflare-workers
Build and operate Cloudflare Workers applications end-to-end, including bootstrap, Wrangler setup, bindings (KV, R2, D1, Durable Objects, Queues, Workers AI, Vectorize), runtime APIs, framework integrations, testing, deployment, and observability. Use when users ask for Cloudflare Workers, Wrangler, edge functions, or Cloudflare Developer Platform integrations.
assinafy-api
>
social-carousel
|
ready-to
Analisa a codebase do estado atual até o deploy, identificando erros, bloqueios, documentação faltante e decisões de design pendentes. Produz um checklist estruturado em READY-TO.md via uma sessão interativa no estilo grill-me. Use quando o usuário disser "pronto pra deploy", "pronto pra produção", "ship it", "revisão pré-deploy", ou invocar /ready-to. Sempre em português brasileiro.
ollama-godmode
Jailbreak Ollama Cloud models: Parseltongue, GODMODE, ULTRAPLINIAN racing
godmode-agnostic
>
gerador-de-simulados
Gera simulados personalizados para concursos públicos com base no edital fornecido, utilizando questões reais de provas anteriores da mesma banca examinadora.
edital-verticalizado
Transforma editais de concurso público em edital verticalizado estruturado (tabela por tópico estudável). Aceita PDF, HTML, Markdown, DOCX, TXT ou texto colado. Entrega Markdown, CSV, XLSX ou JSON.
erzycall-outbound-call
>
erzycall-call-outcomes
Use when placing a phone call through ErzyCall, or when reading the result of one. Defines what success means before dialling, and how to tell whether a finished call actually achieved anything. Use whenever you are about to call create_call, or have a call ID and need to know what happened.
erzycall-campaign-runner
Use when calling more than one person through ErzyCall — a list, a batch, a follow-up round, or any repeated calling job. Covers preparing the list, pacing the run, waiting correctly, and deciding what to retry. Use whenever the task involves calling several people rather than one.
erzycall-contact-safety
Use before calling anyone through ErzyCall, and immediately after any call where the person reacted badly or asked not to be contacted. Covers who may be called, how often, at what hours, and how to record an opt-out so it is enforced. Use whenever you are about to dial a person or a list of people.
erzycall-budget-guard
Use before starting any batch of ErzyCall calls, and whenever the user asks about balance, spend, plan, or how much something will cost. Estimates the cost of a job before dialling, sets a stop rule, and prevents burning a month's minutes on a list that was never going to work.
erzycall-call-design
Use when writing the opening message or script for an ErzyCall outbound call, or when calls are connecting but not achieving anything. Covers how to open, how to handle confusion and silence, how to let someone opt out, and the specific mistakes that make people hang up.
laravel
How to work effectively with Laravel, always use when developing Laravel features
testing
How to effectively test the application, always use when writing tests
pest
Pest framework syntax reference
react
How to work effectively with React, always use when developing frontend components
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
pint
Laravel Pint syntax reference
tailwind
How to work effectively with Tailwind CSS, always use when styling frontend features
shadcn
How to work effectively with shadcn/ui components, always use when adding UI components
wayfinder
How to work effectively with Laravel Wayfinder, always use when developing frontend features
inertia
How to work effectively with Inertia, always use when developing frontend features
sonos-control
[ARCHIVED - do not use] Former MCP-mode Sonos skill from the retired sonos_mcp project. For Sonos requests use the `sonos` CLI (github.com/slzatz/sonos_tool) and its skill instead.
sonos-direct-code
[ARCHIVED - do not use] Former direct-mode Sonos skill (sonos_tool.py dispatcher + tmux TUI) from the retired sonos_mcp project. For Sonos requests use the `sonos` CLI (github.com/slzatz/sonos_tool) and its skill instead.
tmux-tool
[ARCHIVED - do not use] tmux dispatcher that existed only for the retired sonos_mcp TUI search workflow. The tmux_tool wrapper has been removed.
telegram
This skill should be used when fetching, searching, downloading, or sending messages on Telegram. Use for queries like "show my Telegram messages", "search Telegram for...", "get unread messages", "send a message to...", or "add Telegram messages to my notes".
Start Orchestrator
Starts the Orchestrator 3 Stream application (backend + frontend) in background mode. Use when the user asks to start orchestrator, launch orchestrator, run orchestrator, or open the orchestrator UI. Supports --session and --cwd flags for backend.
creating-new-skills
Creates new Agent Skills for AI Agents following best practices and documentation. Use when the user wants prompts 'create a new skill ...' or 'use your meta skill to ...'.
viem-sweep
Comprehensive guide and reference for implementing advanced sweeping and transaction strategies (Legacy, Factory, Permit, Auth, EIP-7702) using viem v2. Use this skill when you need to implement token sweeping, wallet factories, gasless transfers, or account delegation.
hitpay
Integrate HitPay payment gateway for online payments in Next.js and JS/TS applications. Use when user says "Add HitPay", "HitPay checkout", "HitPay payments", "HitPay webhook", "HitPay QR code", "PayNow integration", or "HitPay integration".
ai-paper-writing
Best practices for writing AI research papers. Use when the project involves writing a research paper in AI field.
ai-research
Systematic AI research process. Use when the user is AI researcher and the project is involved in AI research project.
apply
Apply to Good Outcomes through an interactive semantic challenge. Use when a candidate wants to apply for AI-Assisted Full Stack Engineer or AI Engineer - ML & Classification Systems roles. Guides through gathering info, solving an embedding-based puzzle, and submitting the application.
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
config-backup
Use when users want to save, backup, copy, export, or version control their Claude Code configuration files (commands, skills, agents) from ~/.claude/ to another directory. Triggered by phrases like "save my claude settings", "backup my claude config", "sync claude configuration", "copy ~/.claude to somewhere", "export my commands and skills", or "archive claude settings before making changes".
config-restore
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".
idea
Record ideas and thoughts to Obsidian vault. Creates structured idea notes with problem analysis and tags. Use when user says "记录想法", "有个idea", "记一下", "记录疑问", or captures inspiration/questions about technical problems, architecture, or research.
photo-clipper
Crop photos intelligently based on natural language prompts using GPT-5 vision analysis. Use when the user asks to crop or trim a photo, remove parts of an image, focus on a specific subject, improve composition, or remove distractions from edges.
photo-color
Adjust photo brightness, contrast, and saturation based on natural language prompts using GPT-5 text analysis. Use when the user asks to adjust brightness, change contrast, modify saturation, apply a specific style, or fix photo issues like washed out colors.
todo
Systematic todo management approach. Analyze task clarity before adding; ask for details when needed to ensure actionability. Uses Obsidian's todo.md with three regions: Important (重要), Todo, Finish (完成). Trigger when user says "添加任务", "新任务", "记录待办", "管理任务" or needs task reasoning, priority judgment, or task breakdown.
talk-dig
Analyze academic talk posters to discover and summarize the speaker's relevant papers. Extracts speaker info and topic from poster images, searches for their papers online, and provides comprehensive summaries.
Page 1493 of 1704 · 85185 results
