Menu
Configure the research agent template: niche, sources, scoring, delivery, approval policy, and recurring schedules.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Full interactive setup for the agentic CRM personal assistant template. Use at first boot or whenever the user asks to configure/reconfigure the assistant.
Discover, research, and CONNECT the tools a tool-agnostic personal assistant needs — email, calendar, contacts, meeting notes, messaging, CRM. CLI-first, research-driven, verified. Use during setup and whenever a workflow fails because a tool is missing or not authed.
You need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
You need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
You need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
You need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
| name | research-agent-setup |
| description | Configure the research agent template: niche, sources, scoring, delivery, approval policy, and recurring schedules. |
Interactive onboarding. Prompts the user for all configuration values and writes config.json.
On first boot, or when the user asks to configure or reconfigure the research agent.
Ask the user each question in order. Accept their answer before moving to the next. Write the completed config at the end.
.env, not config.Write or update:
IDENTITY.mdUSER.mdTOOLS.mdresearch/sources.jsonresearch/scoring-rubric.jsonconfig.jsonCrons -- install ALL of the template's shipped crons (do not reduce the set). The
template ships 5 crons in config.json; preserve every one, each with its full
skill-chain prompt and update-cron-fire call:
heartbeat (4h)daily-research-brief (0 9 * * * -- adjust only the hour to the user's chosen brief time from Q3)topic-briefing (0 18 * * *)weekly-trends-review (0 9 * * 1)research-quality-review (0 12 * * 5)Keep the shipped prompts verbatim. Only the daily-research-brief schedule changes to
match the user's preference -- do NOT drop the other crons or replace them with terse
run-only entries.
Write .env stub reminding user to add their API keys (if .env does not already exist).
Use research.delivery.destination and research.delivery.requires_approval for
delivery settings.
Never write secrets into committed files. Confirm: "Setup complete. Add your API keys to .env or org secrets. Your first run will fire at [next scheduled time]."