Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →onewave-ai/multi-agent-client-onboarding
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.
Passed 12 of 18 test cases with the skill, and 4 of 18 without it.
and 8 more in the full report
10 fixed5 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
What specific domain responsibilities are assigned to Agent 1 and Agent 2 during Phase 1 deployment?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns workflow mapping and bottleneck identification to the Workflow Auditor | Missed | Passed |
| Assigns tool inventory and tech debt mapping to the Tech Stack Mapper | Missed | Passed |
The instructions your model reads when the skill loads.
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.
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. +-------------------+
| COMMANDER AGENT |
| (Orchestrator) |
+--------+----------+
|
+--------------+--------------+
| | |
+--------v---+ +------v------+ +----v--------+
| AGENT 1 | | AGENT 2 | | AGENT 3 |
| Workflow | | Tech Stack | | Strategy |
| Auditor | | Mapper | | Drafter |
+--------+---+ +------+------+ +----+--------+
| | |
+--------------+--------------+
|
+--------v----------+
| SYNTHESIS PHASE |
| Merge findings |
+-------------------+
Accept a client name plus optional context. Parse these fields from the user message:
Client: <company name>
test cases passed, vs 4 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.