agent-builderlisted

Build Anthropic Managed Agents through a non-technical conversation. The skill asks the user what kind of agent they want, which connectors and abilities it should have, and then silently translates that into Anthropic's Managed Agents REST API: creates the Agent, Environment, Vault and credentials, attaches MCP servers and Skills, opens a Session, and sends a first message. Hides the developer details. USE THIS SKILL WHEN user says "agent builder", "build an agent", "create an agent", "managed agent", "managed agents", "deploy an agent", "anthropic agent", "agent platform", "agents API", "agent session", "agent environment", "agent vault", "upload skill", "attach skill", "/v1/agents", "/v1/skills", or wants to spin up an autonomous agent that runs on Anthropic's managed infrastructure with connectors and skills.
naveedharri/benai-skills · ★ 65 · AI & Automation · score 75

Install: claude install-skill naveedharri/benai-skills

# Agent Builder Build Anthropic Managed Agents through a friendly, non-technical conversation. The user picks what they want; this skill quietly translates it into the right API calls. ## When This Skill Loads 1. Silently read every file in `references/`. Do not narrate this. 2. Do not list "Step 1, Step 2, …" in chat. Do not paste raw JSON, curl commands, or API field names into the user's view. Those exist only in the references for your own use. 3. Start the conversation with a single warm sentence, then drop straight into the first question via `AskUserQuestion`. Opener (example, vary as needed): > "Let's build your agent. A few quick questions and I'll set everything up for you." ## How To Drive The Conversation Every branching question MUST go through `AskUserQuestion`, never plain chat. Plain chat is reserved for short confirmations and the final summary. Use the descriptions inside each option to teach the concept (what a connector is, what a skill is, etc.) so the user never has to know the underlying terms. Run the questions in this order. Skip a question if the user already volunteered the answer earlier in the conversation. --- ### Q1. What kind of agent are you building? Use `AskUserQuestion`. Header: `Agent type`. Options (single-select): - **Research & analysis**. Reads sources on the web or in your tools, summarizes, finds patterns. - **Content creation**. Drafts posts, emails, scripts, documents. - **Operations & automation**. Handles tasks across