onboarding-playbook-creation
Design structured customer onboarding workflows with phased checklists, email templates, success milestones, and ownership assignments. Use when the user requests onboarding playbook creation or provides relevant inputs for this workflow.
git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills /tmp/onboarding-playbook-creation && cp -r /tmp/onboarding-playbook-creation/customer-success/onboarding-playbook-creation ~/.claude/skills/onboarding-playbook-creationSKILL.md
# Onboarding Playbook Creation Build comprehensive onboarding playbooks that guide new customers from signup to first value and sustained adoption. This skill produces phased workflows with explicit milestones, task checklists, communication templates, and clear ownership so that every customer follows a repeatable path to success regardless of which CSM is assigned. ## Workflow 1. **Define success milestones** — Identify the 3-5 concrete outcomes that signal a customer has been successfully onboarded. These should be measurable product actions, not vague goals. Examples: "first report generated," "3+ team members active," "integration with primary data source complete." Tie each milestone to a business outcome the customer cares about to maintain alignment with their goals throughout the process. 2. **Map onboarding phases** — Structure the journey into distinct phases, each with a clear entry criteria, exit criteria, and expected duration. A standard B2B framework uses four phases: **Welcome** (Day 0-3) — account setup and introductions. **Setup** (Day 4-10) — technical configuration and data import. **First Value** (Day 11-20) — achieving the initial "aha moment" with the product. **Adoption** (Day 21-30) — expanding usage across the team and embedding into workflows. 3. **Create task checklists per phase** — Break each phase into specific, actionable tasks with owners (CSM, customer, SE, product). Each task should have an estimated duration, dependencies on prior tasks, and a definition of done. Include both internal tasks (create customer Slack channel, schedule kickoff) and customer-facing tasks (invite team members, connect data source). 4. **Design communication templates** — Write email and in-app message templates for each phase transition and key touchpoint. Include: welcome email, kickoff meeting agenda, mid-onboarding check-in, milestone celebration, risk alert (if a milestone is missed), and graduation email. Each template should have personalization tokens and conditional blocks based on customer segment. 5. **Set timeline and ownership** — Assign every task to a specific role and set due dates relative to the onboarding start date (Day 0). Create escalation rules for overdue tasks: 2 days overdue triggers a CSM nudge, 5 days overdue triggers a manager alert, 10 days overdue triggers a playbook reassessment call. Build in buffer for enterprise accounts that require procurement and security reviews. ## Usage Describe your product, customer segment, and onboarding goals. The agent will produce a complete playbook with phases, tasks, templates, and timelines. ``` Create a 30-day onboarding playbook for our B2B analytics platform. Target segment is mid-market (50-500 employees). Key success milestones: connect a data source, build first dashboard, share with 3+ team members. ``` ## Examples ### Example 1: 30-day B2B SaaS onboarding playbook **Input:** B2B analytics platform, mid-market segment, 30-day onboarding window. **Output:** #### Phase 1: Welcome (Day 0-3) | Task | Owner | Duration | Done When | |------|-------|----------|-----------| | Send welcome email with login credentials and quickstart guide | CSM | 15 min | Email delivered, customer opens | | Create internal customer channel (#cs-acme-corp) | CSM | 5 min | Channel exists with team added | | Schedule kickoff call for Day 2-3 | CSM | 10 min | Calendar invite accepted | | Conduct kickoff call: align on goals, introduce support channels, confirm timeline | CSM + Customer | 45 min | Meeting notes shared, milestones agreed | | Customer completes account profile and invites admin user | Customer | 20 min | Admin user active in product | #### Phase 2: Setup (Day 4-10) | Task | Owner | Duration | Done When | |------|-------|----------|-----------| | Connect primary data source (guided walkthrough) | Customer + SE | 1-2 hours | Data source shows "connected" status, initial sync complete | | Verify data integrity — spot-check 3 metrics against source | SE | 30 min | Metrics match within 2% tolerance | | Configure SSO/SAML if enterprise | SE | 1 hour | Team can login via company identity provider | | Send Day 7 check-in email: "How's setup going?" | CSM (automated) | — | Email sent, reply monitored | | Troubleshoot any integration blockers | SE | Varies | All blockers resolved, customer unblocked | #### Phase 3: First Value (Day 11-20) | Task | Owner | Duration | Done When | |------|-------|----------|-----------| | Build first dashboard using template library | Customer + CSM | 45 min | Dashboard created with live data | | CSM reviews dashboard and suggests improvements | CSM | 30 min | Customer confirms dashboard meets their needs | | Customer shares dashboard with 3 team members | Customer | 10 min | 3+ users have viewed the shared dashboard | | Send milestone email: "You built your first dashboard!" | CSM (automated) | — | Email delivered with next steps | | 15-minute adoption check-in call | CSM + Customer | 15 min | Usage patterns reviewed, expansion opportunities identified | #### Phase 4: Adoption (Day 21-30) | Task | Owner | Duration | Done When | |------|-------|----------|-----------| | Customer creates 2 additional dashboards independently | Customer | Self-paced | 3+ total dashboards exist | | Enable scheduled report delivery | Customer + CSM | 20 min | At least 1 scheduled report active | | Conduct graduation call: review milestones, transition to ongoing CS | CSM + Customer | 30 min | Customer confirms self-sufficiency, success plan created | | Internal handoff to ongoing CSM (if different from onboarding CSM) | CSM → CSM | 30 min | Handoff doc complete, new CSM introduced | | Send graduation email with advanced resources and community invite | CSM (automated) | — | Email delivered | ### Example 2: Developer tool self-serve onboarding checklist **Input:** Developer CLI tool, self-serve motion, no CSM involvement. **Output:** **In-App Onboarding Checklist (shown in dashboard sidebar)**
Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.
Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.
Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.
Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.
Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.
Design and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.
Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.