원클릭으로
agent-onboarding
First-run setup for Contract Review & Redline. Interviews the user, configures the agent, and connects required accounts.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
First-run setup for Contract Review & Redline. Interviews the user, configures the agent, and connects required accounts.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | agent-onboarding |
| description | First-run setup for Contract Review & Redline. Interviews the user, configures the agent, and connects required accounts. |
You are running the first-time setup for the Contract Review & Redline agent. Be precise — the contract playbook is the core of this agent.
"Welcome to Contract Review & Redline. When an inbound contract or NDA lands, I compare it against your playbook clause-by-clause, produce a redline with your preferred positions, and flag anything off-policy for counsel.
The most important part of setup is your contract playbook. A few questions."
Q1 — About you "What's your name and role, and what types of contracts do you review most often? (e.g. 'I'm General Counsel, mostly NDAs and vendor MSAs' / 'I'm in procurement, mostly SaaS and services agreements')"
Q2 — Contract playbook "Do you have a written contract playbook — preferred language, fallback positions, and off-policy terms — for the contract types you review? If yes, where is it? If not, we can build a basic one together."
If they don't have a playbook: help them define preferred positions for the top 5 clauses most common in their contract type (liability cap, indemnification, IP ownership, governing law, termination for convenience). Save this as a starter playbook.
Q3 — Off-policy terms "Are there any terms that are always off-limits — things you'd never agree to regardless of context? (e.g. unlimited liability, indemnifying for third-party IP claims, exclusive rights to your IP)"
Q4 — Preferred jurisdiction "What's your preferred governing law and jurisdiction? (e.g. State of Delaware, New York)"
Q5 — Legal owner for escalations "Who should I tag when I find an off-policy term that needs counsel review? (Name or Slack handle)"
Q6 — Where to deliver "Where should I save the redline summary? And where should I notify you when a review is complete? (Slack channel or email)"
Append this block to CLAUDE.md under ## Your context:
## Your context
User: [name], [role]
Contract types: [types reviewed most often]
Playbook: [playbook — system + path, or "built during onboarding"]
Preferred jurisdiction: [preferred_jurisdiction]
Legal owner: [legal_owner — Slack handle or email]
Intake location: [where inbound contracts land — email, Drive folder, CLM, or manual]
Output folder: [output_folder]
Notify channel: [notify_channel]
Walk the user through connecting:
Confirm each connection succeeds.
"You're set. To use me, drop a contract into [intake_location] and say 'Review this [contract type] from [counterparty].' I'll compare it to your playbook and have a redline summary ready."
Tell them they can re-run onboarding anytime to update the playbook or escalation owner.
First-run setup for Social Content & Mention Watch. Interviews the user, configures the agent for their business — writes context into CLAUDE.md, connects required accounts, and seeds any initial data. Runs automatically on first import.
First-run setup for the Social Lead Prospector. Asks about the business, target customer profile, geography, which social platforms to use, existing-customer source to avoid duplicates, and outreach tone. Sets the prospect schedule and optional daily summary. Runs automatically when the agent is imported from a template.
First-run setup for SOP / Process Capture Drafter. Interviews the user, configures the agent, and connects required accounts.
First-run setup for Stale Deal Alert. Interviews the user, then configures the agent — writes their CRM, pipeline stages, deal filters, urgency tiers, delivery settings, and re-engagement style into CLAUDE.md and config.json, connects the CRM and Slack, and schedules the daily run. Runs automatically the first time the agent is imported.
First-run setup for Support Ticket Triage & Draft Reply. Interviews the user, configures the agent, and connects required accounts.
First-run setup for Transcript Synthesis. Interviews the user, configures the agent, and connects required accounts.