Skip to main content
skill CX Codex

multi-agent-client-onboarding — Claude Code skill

multi-agent-client-onboarding runs three parallel agents to audit workflows, map a client’s tech stack, and draft an AI roadmap. It is built for structured client assessments.

MIT 251 installs ★ 440 updated 2026-10-20

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add OneWave-AI/claude-skills --skill multi-agent-client-onboarding -a claude-code
Open on GitHub

What multi-agent-client-onboarding does

The skill accepts a client name plus optional context, document paths, URLs, and focus areas. When the request contains only a company name, it starts with WebSearch to assemble a context brief before the specialist work begins.

Three agents then run concurrently. The workflow auditor looks for manual work and bottlenecks, the tech stack mapper inventories tools, frameworks, APIs, and integrations, and the strategy drafter produces a phased roadmap with ICE scoring. A synthesis phase reconciles the findings, checks tables and Mermaid diagrams, and writes client-onboarding-report.md. Supporting material lives in references/agent-prompts.md, references/final-deliverable-structure.md, and references/quality-standards.md.

A baseline client search requires WebSearch when only the company name is available. If one agent fails, the process keeps going and marks affected sections for additional access.

What it helps with

  • audit a client’s current workflows
  • locate manual steps and bottlenecks
  • map tools, APIs, and integrations
  • draft a phased AI implementation roadmap
  • produce client-onboarding-report.md

Example prompts for the agent

  • Run a client onboarding assessment for the company in my message, focusing on sales and support workflows.
  • Review the materials in ./docs, inspect the product URL, and run the workflow audit, stack mapping, and strategy draft in parallel.
  • Create a client assessment with three specialist agents and save it as client-onboarding-report.md.

How to install multi-agent-client-onboarding

1Skills CLI (Vercel)

npx skills add OneWave-AI/claude-skills --skill multi-agent-client-onboarding -a claude-code

2Manually: put the files in place

~/.claude/skills/multi-agent-client-onboarding/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/multi-agent-client-onboarding/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about multi-agent-client-onboarding

How do I install multi-agent-client-onboarding in Claude Code?

Run npx skills add OneWave-AI/claude-skills --skill multi-agent-client-onboarding -a claude-code, then check ~/.claude/skills/multi-agent-client-onboarding/SKILL.md.

What does multi-agent-client-onboarding do?

It coordinates three parallel agents for workflow review, technology mapping, and AI strategy planning. Their results are merged into a client report with priorities, tables, and Mermaid diagrams.

What happens when I provide only a company name?

The skill uses WebSearch to build a basic client context brief before deploying the specialist agents.

Source text

SKILL.md · MIT
---
name: multi-agent-client-onboarding
description: Uses Agent SDK to deploy 3 parallel agents for client onboarding -- workflow auditor, tech stack mapper, and strategy drafter. Real consulting workflow that produces a complete client assessment.
tools: Read, Grep, Glob, Bash, Agent, Write, WebSearch
model: inherit
---

# Multi-Agent Client Onboarding System

Act as the Commander Agent: an orchestration layer that deploys three parallel specialist agents and synthesizes their output into a comprehensive client onboarding assessment of consultancy quality.

## Contents

- `references/agent-prompts.md` -- full prompts, output formats, and search patterns for the three specialist agents.
- `references/final-deliverable-structure.md` -- the exact structure of the `client-onboarding-report.md` deliverable.
- `references/quality-standards.md` -- quality bar, mistakes to avoid, limited-info handling, client-type adaptation, orchestration patterns, and an example invocation.

## Architecture

```
                    +-------------------+
                    |  COMMANDER AGENT  |
                    |  (Orchestrator)   |
                    +--------+----------+
                             |
              +--------------+--------------+
              |              |              |
     +--------v---+  +------v------+  +----v--------+
     |  AGENT 1   |  |  AGENT 2    |  |  AGENT 3    |
     |  Workflow  |  |  Tech Stack |  |  Strategy   |
     |  Auditor   |  |  Mapper     |  |  Drafter    |
     +--------+---+  +------+------+  +----+--------+
              |              |              |
              +--------------+--------------+
                             |
                    +--------v----------+
                    |  SYNTHESIS PHASE  |
                    |  Merge findings   |
                    +-------------------+
```

## Input Format

Accept a client name plus optional context. Parse these fields from the user message:

```
Client:  <company name>
Context: <industry, size, what they do>
Docs:    <optional path to documents, repos, or data directories>
URL:     <optional website or product URL>
Focus:   <optional specific areas of concern>
```

Given only a company name, run baseline WebSearch before deploying the specialist agents.

## Workflow

1. **Parse input.** Extract client name, context, document paths, URLs, and focus areas. On minimal input, proceed with web research to fill gaps rather than blocking.

2. **Gather intelligence (Phase 0).** Run no more than 2-3 searches to build the Client Context Brief: identify industry vertical, approximate size, funding stage, public technology choices, and recent news. Define the assessment scope and any user constraints. Assemble the brief in this format:

   ```
   === CLIENT CONTEXT BRIEF ===
   Client: [Name]
   Industry: [Vertical]
   Size: [Employees / Revenue tier if known]
   Stage: [Startup / Growth / Enterprise]
   Primary Business: [What they do]
   Available Materials: [Docs, repos, URLs]
   Focus Areas: [User-specified or "General Assessment"]
   Known Technology: [Any tech already identified]
   Key Contacts: [If provided]
   ================================
   ```

3. **Deploy three agents in parallel (Phase 1).** Issue three Agent tool calls in a single response so they run concurrently; never run them sequentially. Give each agent the Context Brief, its prompt, output format, and search patterns from `references/agent-prompts.md`, and point it at any available docs or repos. Wait for all three to complete before synthesizing.
   - Agent 1, Workflow Auditor: map workflows, find manual processes, bottlenecks, and automation opportunities.
   - Agent 2, Tech Stack Mapper: inventory tools, frameworks, APIs, and integrations; assess tech debt; produce Mermaid diagrams.
   - Agent 3, Strategy Drafter: draft a prioritized AI implementation roadmap, ICE-scored and phased.

4. **Synthesize findings (Phase 2).** Read all three reports. Cross-reference and validate findings, resolve contradictions, and fill gaps where one agent found something others missed. Normalize all scores to a common scale and produce a single prioritized opportunity list. Write the executive narrative for a C-level audience. Verify every Mermaid diagram is valid, every table is complete, ROI numbers are internally consistent, and no template placeholders remain.

5. **Write the final report.** Use the Write tool to create `client-onboarding-report.md` in the current working directory (or a user-specified location), following `references/final-deliverable-structure.md` exactly.

6. **Present a summary.** Report the file location, 3-5 key findings, the top recommendation, the headline ROI number, and the suggested next step.

## Guardrails

- Hold the deliverable to the bar in `references/quality-standards.md`: specific, quantified, realistic, risk-aware, actionable, visual, and layered.
- Never invent specific revenue figures; use ranges and stated assumptions.
- Never leave template placeholders such as `[X]` or `[...]` in the delivered report.
- Never use emojis anywhere in output.
- Never include the Supabase token or any credentials in the report.
- If an agent fails, note the gap, fill it from other agents where possible, mark affected sections "Partial Assessment -- Additional Access Recommended", and continue rather than blocking.

© OneWave-AI · MIT · OneWave-AI/claude-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set185

The whole set →
data-pipeline-builder data-pipeline-builder turns source, destination and transformation notes into a runnable ETL/ELT pipeline: Python or SQL code, an Airflow DAG, quality checks and a spec file. CX Codex +1 252installs roi-calculator roi-calculator turns your current costs, manual hours and hourly rates into a written ROI report on an AI project, with payback and sensitivity cases. CX Codex +1 252installs investor-update-writer investor-update-writer generates monthly and quarterly updates for startup investors into a structured investor-update.md file using metrics, milestones, and runway. CX Codex +1 252installs onboarding-checklist Generates phased client onboarding checklists in onboarding-checklist.md with task ownership, criteria, and five email templates for SaaS, agencies, or consulting. CX Codex +1 251installs market-sizing Calculates TAM, SAM, and SOM for business plans and investor decks. Researches industry data online and writes a detailed market-sizing.md report. CX Codex +1 251installs full-codebase-migrator The full-codebase-migrator skill examines a whole repository and turns it into a file-level migration plan. Use it for JS-to-TS work, React class conversion, or framework changes. CX Codex +1 251installs competitor-intel-agent competitor-intel-agent monitors competitor sites, pricing models, hiring shifts, and product releases while saving snapshot history. CX Codex +1 251installs okr-generator okr-generator builds a structured okr-plan.md file using the Google and Intel framework from your company targets and team baselines. CX Codex +1 250installs

Project sponsors

Companies that keep this analytics open