Map of AG2 beta capabilities and which sibling skill to reach for.
$ npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ag2ai/build-with-ag2 ag2-overview --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ag2ai/build-with-ag2.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ag2-overview .claude/skills/ag2-overview && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ag2-overview" agent skill from https://github.com/ag2ai/build-with-ag2/tree/main/.agents/skills/ag2-overview into .claude/skills/ag2-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ag2-overview", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ag2ai/build-with-ag2/tree/main/.agents/skills/ag2-overviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ag2ai/build-with-ag2 ag2-overview --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ag2ai/build-with-ag2.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/ag2-overview .agents/skills/ag2-overview && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ag2-overview" agent skill from https://github.com/ag2ai/build-with-ag2/tree/main/.agents/skills/ag2-overview into .agents/skills/ag2-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ag2-overview", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ag2ai/build-with-ag2 ag2-overview --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ag2ai/build-with-ag2.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/ag2-overview .cursor/skills/ag2-overview && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ag2-overview" agent skill from https://github.com/ag2ai/build-with-ag2/tree/main/.agents/skills/ag2-overview into .cursor/skills/ag2-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ag2-overview", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ag2ai/build-with-ag2.git --path .agents/skills/ag2-overview--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ag2ai/build-with-ag2 ag2-overview --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ag2ai/build-with-ag2.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/ag2-overview .gemini/skills/ag2-overview && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ag2-overview" agent skill from https://github.com/ag2ai/build-with-ag2/tree/main/.agents/skills/ag2-overview into .gemini/skills/ag2-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ag2-overview", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ag2ai/build-with-ag2 ag2-overviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ag2ai/build-with-ag2.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/ag2-overview .github/skills/ag2-overview && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ag2-overview" agent skill from https://github.com/ag2ai/build-with-ag2/tree/main/.agents/skills/ag2-overview into .github/skills/ag2-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ag2-overview", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ag2ai/build-with-ag2 ag2-overview --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ag2ai/build-with-ag2.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/ag2-overview .opencode/skills/ag2-overview && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ag2-overview" agent skill from https://github.com/ag2ai/build-with-ag2/tree/main/.agents/skills/ag2-overview into .opencode/skills/ag2-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ag2-overview", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ag2-overviewMap of AG2 beta capabilities and which sibling skill to reach for.
Ag2 Overview is an agent skill from ag2ai/build-with-ag2. Map of AG2 beta capabilities and which sibling skill to reach for. Load first when the user mentions building with AG2 beta (autogen.beta) but the specific feature isn't yet clear — agents, tools, model config, delegation, memory, observers, structured output, HITL, AG-UI, telemetry, or testing.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Building AI agents and Structured output and tool calling. It works with Python. The repository describes itself as: Sample code and application showcases to get you going with AG2 (formally AutoGen). The licence is Apache-2.0.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 29eeac3. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
pippythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
OPENAI_API_KEYANTHROPIC_API_KEYGEMINI_API_KEYGOOGLE_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ag2 Overview loads about 1.3k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 521 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
_API_KEY`). Loading from a project-root `.env` via `from dotenv import load_dotenv; load_dotenv()` is the common patternAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from ag2ai/build-with-ag2 at commit 29eeac3, republished under its Apache-2.0 licence (© ag2ai). 521 words, ~1,282 tokens.
.claude/skills/ag2-overview/SKILL.md (or your agent's skills folder).AG2 beta (autogen.beta) is an async, protocol-driven agent framework. The full reference docs live under website/docs/beta/. This skill is the index of sibling skills that cover the common build paths.
Read this file first when a request mentions "AG2 beta", "autogen.beta", or building agents in this repo and you don't yet know which feature is needed. Use the table below to pick the right specialised skill, then load that skill's SKILL.md for the recipe.
Anything you build with AG2 needs three things in place. Get these right once and the rest of the skills run cleanly:
pip install "ag2[openai]", ag2[anthropic], ag2[gemini], etc. The *Config class will raise ImportError: ... requires optional dependencies without it.OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY (or GOOGLE_API_KEY). Loading from a project-root .env via from dotenv import load_dotenv; load_dotenv() is the common pattern.python -c "import sys, autogen; print(sys.executable, autogen.__version__)". If you have multiple Python environments, this confirms which ag2 your script will actually import.Full per-provider table (install + env var + config class) lives in ag2-quickstart → "Prerequisites".
| User intent | Skill | What it covers |
|---|---|---|
Build an Agent from scratch, pick a model | ag2-quickstart | Agent, ModelConfig, ask() / reply.ask() chaining, providers, env vars |
| Give the Agent a custom Python tool | ag2-add-custom-tool | @tool, sync/async, ToolResult, Context, Inject, Variable, Depends |
| Use shipped tools (web search, code exec, MCP, etc.) | ag2-use-builtin-tools | WebSearchTool, WebFetchTool, CodeExecutionTool, MCPServerTool, ImageGenerationTool, MemoryTool, FilesystemToolkit, DuckDuckSearchTool, ExaToolkit, TavilySearchTool |
| Run shell commands from an agent | ag2-shell-tool | LocalShellTool (any provider), provider-side ShellTool, sandboxing (allowed/blocked/ignore/readonly) |
| Get typed Pydantic / dataclass output | ag2-structured-output | response_schema=, ResponseSchema, @response_schema, PromptedSchema, reply.content(), retries |
| Multi-agent: parallel subtasks or named delegates | ag2-subagent-delegation | tasks=TaskConfig(), run_subtasks(parallel=True), Agent.as_tool(), persistent_stream |
| Pause for human input or gate a tool with approval | ag2-hitl | context.input(), hitl_hook, approval_required() middleware |
| Logging, retry, history-trim, custom interception | ag2-middleware | BaseMiddleware, LoggingMiddleware, RetryMiddleware, HistoryLimiter, TokenLimiter, tool middleware |
| Test agents and tools | ag2-testing | TestConfig, mocking LLM responses, simulating ToolCallEvent |
| Persistent memory across runs, history compaction, assembly | ag2-knowledge-and-memory | KnowledgeStore, KnowledgeConfig, WorkingMemoryAggregate, AssemblyPolicy, SlidingWindowPolicy, TokenBudgetPolicy, TailWindowCompact, SummarizeCompact |
| Observability, alerts, halts | ag2-observers-and-alerts | BaseObserver, TokenMonitor, LoopDetector, EventWatch, CadenceWatch, AlertPolicy, HaltEvent |
| Send images / audio / video / PDFs in | ag2-multimodal-input | ImageInput, AudioInput, VideoInput, DocumentInput, FilesAPI |
| Web frontend via the AG-UI protocol | ag2-ag-ui | AGUIStream, FastAPI mount, CopilotKit |
| OpenTelemetry traces / metrics | ag2-telemetry | TelemetryMiddleware, GenAI semconv attributes, content capture |
These are repo-wide rules from CLAUDE.md. Apply them whenever generating code that lands in autogen/beta/:
from __future__ import annotations.__init__ — apply them at runtime.pathlib.Path; public signatures accept str | os.PathLike[str].autogen.beta top-level (e.g. from autogen.beta import Agent, tool, Context); advanced/specialised APIs come from sub-modules (autogen.beta.middleware, autogen.beta.config, etc.).If a skill's recipe is incomplete for the case at hand, the source docs are at website/docs/beta/. Each sibling skill points to its primary .mdx files in its own "Going deeper" section.
© ag2ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/ag2-overview of ag2ai/build-with-ag2.
Open the folder on GitHubat commit 29eeac3
Ag2 Overview next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ag2 Overview this skillag2ai/build-with-ag2 | 252 | — | ~1.3k | Automated safety check: Notes | Apache-2.0 | |
| Google Agents CLI Adk Codepifferologo/cloud-agents-cli | 129 | 1 repos | ~768 | Automated safety check: Pass | Apache-2.0 | |
| E2b Code Interpreteragent-sandbox/agent-sandbox | 218 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Building Pydantic AI Agentsdocling-project/docling | 69k | — | ~2.8k | Automated safety check: Pass | MIT | |
| LangGraph Decision Modelslangchain-ai/langchain-skills | 1.3k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Tool Designagentailor/fullstack-langgraph-nextjs-agent | 132 | — | ~3.2k | Automated safety check: Pass | MIT |
pifferologo/cloud-agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent…
agent-sandbox/agent-sandbox
Execute code in E2B sandboxes and integrate with LLMs for tool calling.
docling-project/docling
Patterns and tested examples for building agents with Pydantic AI: tools, capabilities, structured output, dependency injection, hooks, YAML specs, streaming and testing.
langchain-ai/langchain-skills
Routes LangGraph agents with typed decision models that return probabilities, and finds LLM calls that only exist to produce a routing decision.
agentailor/fullstack-langgraph-nextjs-agent
Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise).
pydantic/skills
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns.
ag2ai/build-with-ag2
Add a custom Python tool to an AG2 beta Agent using the @tool decorator.
ag2ai/build-with-ag2
Intercept the AG2 beta agent loop with BaseMiddleware — wrap full turns (onturn), each LLM call (onllmcall), each tool execution (ontoolexecution), or each human-input request (onhumaninput).
ag2ai/build-with-ag2
Wire AG2 beta's shipped tools into an Agent — both provider-native server-side tools (web search, web fetch, code execution, MCP, image generation, memory) and locally-executed common toolkits…
ag2ai/build-with-ag2
Persist agent state across runs, shape what the LLM sees per turn, and cap history to fit a context window.
ag2ai/build-with-ag2
Monitor an AG2 beta agent's stream — log events, detect repeated tool calls, track token spend, build trigger-driven observers, route observer alerts to the model, and halt on FATAL conditions.
ag2ai/build-with-ag2
Build a minimal AG2 beta Agent end to end — pick a model provider, set a prompt, call agent.ask(), then continue the conversation with reply.ask() (multi-turn).
Works with
Categories
Map of AG2 beta capabilities and which sibling skill to reach for. Ag2 Overview is an agent skill from ag2ai/build-with-ag2. Map of AG2 beta capabilities and which sibling skill to reach for.
Ag2 Overview fits situations like: mentions building with AG2 beta (autogen.beta) but the specific feature isnt yet clear — agents; structured output.
Run `npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a claude-code`. Or copy the skill folder (.agents/skills/ag2-overview in ag2ai/build-with-ag2) into .claude/skills/ag2-overview in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a codex`. Or copy the skill folder (.agents/skills/ag2-overview in ag2ai/build-with-ag2) into .agents/skills/ag2-overview in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ag2ai/build-with-ag2 --skill ag2-overview -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ag2-overview, .gemini/skills/ag2-overview, .github/skills/ag2-overview and .opencode/skills/ag2-overview in your project.
Going by SKILL.md and its folder, Ag2 Overview needs the command-line tools its instructions call (pip and python) and credentials named OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY and GOOGLE_API_KEY. Our summary lists: Python 3; A credential in OPENAI_API_KEY; A credential in ANTHROPIC_API_KEY.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Ag2 Overview is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ag2 Overview: Google Agents CLI Adk Code (pifferologo/cloud-agents-cli, 129 stars), E2b Code Interpreter (agent-sandbox/agent-sandbox, 218 stars), Building Pydantic AI Agents (docling-project/docling, 69k stars) and LangGraph Decision Models (langchain-ai/langchain-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ag2ai (a GitHub organization) maintains it in ag2ai/build-with-ag2, which has 252 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 6, 2026.
Source: ag2ai/build-with-ag2 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
