AGENT SKILLS · EQUIPAGGIAMENTO / TerminalSkills

TerminalSkills · Agent Skills

1053 skills with substantive source documentation and an official publisher or observed installation demand. Read each skill’s original documentation through its card.

TerminalSkills

Community

oh-my-claudecode

Orchestrate multi-agent Claude Code teams — assign roles, coordinate parallel tasks, share context between agents, and manage team workflows. Use when: running multiple Claude Code agents simultaneously, building team-based AI development workflows, coordinating complex multi-agent coding projects.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

okr-planning

Guides OKR (Objectives and Key Results) planning: writing ambitious objectives with measurable key results, aligning teams, running the quarterly cycle, and scoring results. Use when a user asks to "write OKRs for next quarter", "review our OKRs", "turn these goals into key results", "run OKR planning", or "score our OKRs". Applies frameworks from John Doerr (Measure What Matters), Christina Wodtke (Radical Focus), and practices from Google and Intel.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

ollama

Runs LLMs locally with Ollama. Use when a user asks to run AI models locally, self-host a language model, use Gemma, Qwen, Llama or Mistral on their machine, run offline AI, build a local chatbot, avoid sending data to cloud AI providers, generate text without API costs, customize local models, or set up a private AI inference server. Covers model management, the native and OpenAI-compatible APIs, structured output, embeddings, Modelfile customization, context length and GPU configuration.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

onboarding-cro

Audits and redesigns what happens between account creation and a new user's first real result, so that more signups activate and come back. Use when someone says "activation rate is low", "users sign up and never return", "fix our onboarding flow", "first-run experience", "time to value", "empty states", "onboarding checklist", "aha moment", or "product tour". Finds the activation event in the product's own data with SQL, measures where new users stop, decides step by step what to remove, defaul

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

onedrive

Manage files and folders in OneDrive and OneDrive for Business via Microsoft Graph API. Use when someone asks to "upload to OneDrive", "sync files with OneDrive", "share OneDrive files", "manage OneDrive folders", "OneDrive API integration", "backup to OneDrive", or "automate file management in OneDrive". Covers file CRUD, sharing, sync, search, large file upload, thumbnails, and delta queries for change tracking.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

onenote

Create, read, and manage OneNote notebooks, sections, and pages via Microsoft Graph API. Use when someone asks to "create OneNote pages", "read OneNote notes", "automate OneNote", "save to OneNote", "extract OneNote content", "organize OneNote notebooks", or "OneNote API". Covers notebooks, sections, pages (create with HTML), content extraction, and search.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

onnx

Open Neural Network Exchange (ONNX) is a framework-neutral file format for machine-learning models, and ONNX Runtime is the engine that runs them on CPU, GPU and edge devices. Use when exporting a PyTorch or Hugging Face model to ONNX, running inference with onnxruntime, simplifying or quantizing a model, validating a .onnx file, or preparing a model for mobile.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

onyx-ai

Deploy and configure Onyx, a self-hosted AI chat platform with RAG and 25+ data connectors. Use when: setting up private ChatGPT alternative, connecting AI to company documents, building enterprise AI assistant with Confluence/Slack/Drive access.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

opa

Expert guidance for OPA (Open Policy Agent), the CNCF policy engine for unified authorization across the stack. Helps developers write Rego policies for Kubernetes admission control, API authorization, infrastructure-as-code validation, and data filtering — enforcing security policies as code.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

open-swe

Open SWE is LangChain's open-source asynchronous coding agent: a self-hosted service that takes tasks from a dashboard, GitHub, Slack or Linear, works in an isolated sandbox and opens pull requests. Use when a user asks to deploy or run Open SWE, set up its GitHub App and Slack bot, trigger it with @openswe, have it review pull requests, call it from CI with the oswe CLI, or customize its model, sandbox and prompts.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

open-webui

Open WebUI is a self-hosted web chat interface for local and cloud language models that connects to Ollama and any OpenAI-compatible API. Use when a user asks to install or deploy Open WebUI with Docker or pip, connect Open WebUI to Ollama, llama.cpp, vLLM or OpenAI, configure it with environment variables, create the admin account without a browser, call the Open WebUI API for chat completions or RAG, upload files to a knowledge base, export or sync custom models, or update and back up an Open

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openai-agents

The OpenAI Agents SDK is a Python framework (openai-agents) for building agents that call tools, hand work to other agents, run guardrails and stream results, with built-in tracing and MCP support. Use when building a multi-agent workflow with OpenAI models, adding function tools, handoffs, input guardrails or sessions, or when the user mentions openai-agents, Runner.run, or the Agents SDK (the successor to Swarm).

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openai-codex-cli

OpenAI Codex CLI is an open-source terminal coding agent that reads your repository, edits files and runs commands inside an OS-enforced sandbox. Use when someone asks to "install Codex CLI", "run codex in CI", "use codex exec", "set Codex approval and sandbox modes", "write AGENTS.md for Codex", "review my diff with Codex", or "configure ~/.codex/config.toml".

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openai-realtime

Build voice agents with the OpenAI Realtime API, a speech-to-speech interface that takes audio in and streams spoken answers back over WebRTC, WebSocket or SIP. Use when a user asks to build a voice assistant, stream microphone audio to gpt-realtime-2.1, handle interruptions and function calls in a phone-style conversation, answer SIP calls, mint ephemeral browser keys, or migrate off the removed beta (gpt-4o-realtime-preview, OpenAI-Beta header).

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openai-sdk

Integrate OpenAI APIs into applications. Use when a user asks to add GPT or ChatGPT to an app, generate text with OpenAI, build a chatbot, use GPT-6 or reasoning models, generate embeddings, use function calling, stream responses, get structured JSON, moderate content, generate images, transcribe audio, or migrate from the Assistants API, Chat Completions, DALL-E or Whisper. Covers the Responses API, tools, streaming, vision, embeddings, moderation, image generation and transcription.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openapi-spec

OpenAPI is the standard format for describing HTTP APIs in YAML or JSON, from which docs, typed clients and mock servers can be generated. Use this skill to write an OpenAPI 3.1 spec, lint it with Redocly CLI, generate TypeScript types and a typed fetch client, build HTML docs, and keep a spec valid. Use when someone says "write an OpenAPI spec", "document my REST API", "generate a client from openapi.yaml" or "lint my swagger file".

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openclaw

Deploy and manage OpenClaw, a self-hosted gateway bridging messaging platforms to AI coding agents. Use when a user asks to set up OpenClaw, connect WhatsApp or Telegram or Discord to an AI agent, configure multi-agent routing, schedule cron jobs in OpenClaw, set up webhooks, manage OpenClaw channels, pair a messaging account, configure heartbeats, spawn sub-agents, or troubleshoot OpenClaw gateway issues. Covers installation, channel setup, agent configuration, cron scheduling, webhooks, and su

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

opencode

OpenCode is an open-source AI coding agent that runs in the terminal, reads a codebase, edits files and runs shell commands using any of 75+ model providers or a local model. Use it to set up OpenCode, write opencode.json, choose models and providers, restrict permissions, create custom agents and slash commands, add MCP servers, or script it with opencode run in CI. Trigger phrases: "install opencode", "configure opencode.json", "use opencode with Ollama", "opencode run in CI", "opencode plan m

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

opencv

OpenCV is an open-source computer vision library for image processing, video analysis, feature detection, camera calibration and DNN inference, with Python, C++ and JavaScript bindings. Use when asked to resize, blur, threshold or detect edges in images, find contours, read or write video, run an ONNX object detector, or build an OpenCV pipeline with cv2.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

opendataloader-pdf

OpenDataLoader PDF converts PDF files into Markdown, JSON with bounding boxes, HTML or plain text, and can add accessibility tags to untagged PDFs. It runs locally on Java with a CLI and Python, Node.js and Java APIs. Use when a user asks to parse PDFs for RAG, convert a PDF to Markdown, extract tables or headings with page coordinates, OCR scanned PDFs, or produce Tagged PDFs.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openhands

OpenHands is an open-source autonomous coding agent that edits files, runs shell commands and works through multi-step software tasks with any LLM, from a terminal UI, a headless CI mode, a self-hosted web control center (Agent Canvas) or a Python SDK. Use when a user wants a model-agnostic, self-hostable coding agent: "run OpenHands on this repo", "fix this bug with OpenHands headless in CI", "set up OpenHands with a local Ollama model", "script an agent with the OpenHands SDK", "add an MCP ser

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openrouter

OpenRouter is a unified API gateway that reaches hundreds of LLMs from OpenAI, Anthropic, Google, Meta and others through one OpenAI-compatible endpoint and one API key. Use when a user wants to call several models from one codebase, add model fallbacks, route to the cheapest or fastest provider, compare model cost and latency, use free models, or cap spend per key.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openscreen

Create stunning screen recordings and product demos with OpenScreen — open-source, no watermarks, free for commercial use. Use when: recording product demos, creating tutorial videos, building marketing content, screen recording with post-processing effects.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

openspec

OpenSpec is a command-line tool plus a set of slash commands that make an AI coding agent write a reviewable plan — proposal, requirements with scenarios, design and task list — before it changes any code. Use when a user asks to set up spec-driven development, run openspec init, propose a change with /opsx:propose, write a spec before coding, validate or archive an OpenSpec change, or keep requirements in the repository for Claude Code, Codex, Gemini CLI or Cursor.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

Apache-2.02 File

Vedi dettagli →