antongulin/agenticflow-ai-skills

antongulin/agenticflow-ai-skills

Skill Claude CodeCodex

Create, run, and iterate on a single AgenticFlow AI agent — one chat endpoint, one assistant, one persona. Use when the user wants a customer-facing bot, a support assistant, a single task agent, or a prompt experiment. Choose this skill over agenticflow-workforce when there's no orchestration between roles (no…

antongulin/agenticflow-ai-skills

Skill Claude CodeCodex

Purchase and manage AgenticFlow AI built-in credits — the prepaid balance that covers agenticflow-agent and agenticflow-workforce runs. Covers af credit purchase/receipts/usage/plans, plan selection, payment card setup via af setup, usage monitoring (daily/user/agent breakdowns), auto-recharge configuration, and…

antongulin/agenticflow-ai-skills

Skill Claude CodeCodex

List, filter, and recommend LLM models available in the AgenticFlow AI workspace for use in agents and workforce nodes. Should trigger whenever the user mentions LLM models, choosing a provider/model for an agent, model capabilities (reasoning, speed, cost), model selection for specific tasks, or understanding which…

antongulin/agenticflow-ai-skills

Skill Claude CodeCodex

Attach external tool providers (Google Docs, Google Sheets, Slack, Notion, GitHub, Apify, etc.) to an AgenticFlow agent via MCP clients. Use when the user wants their agent to read or write external data, call third-party APIs, save outputs to a doc/sheet, or use any tool beyond the model's built-in knowledge. Covers…

antongulin/agenticflow-ai-skills

Skill Claude CodeCodex

A workforce is an AgenticFlow-native DAG of agents — typically trigger → coordinator agent → worker agents → output — that hand off structured results to each other. Use this when orchestration between roles matters.