davepoon Envelope Team
Design and generate .envelope.json AI agent team definition files — the open standard for building and deploying multi-agent teams on Envelope.
When to Use This Skill
- User asks to build, design, or generate an Envelope team
- User describes a workflow that could be automated by a team of AI agents
- User wants to create a
.envelope.jsonfile for deployment - User needs help with agent hierarchy, access policies, or gates
What This Skill Does
- Takes a natural-language description of the team's purpose
- Designs the agent hierarchy (supervisor → managers → workers)
- Generates a schema-valid
.envelope.jsonfile - Includes access policies, variables, secrets, and gates as appropriate
- Explains any schema concepts the user asks about
How to Use
Basic Usage
Build me an Envelope team for customer support triage — one supervisor,
two agents that read Zendesk tickets, and a Slack notifier for escalations.
Create an Envelope team definition for outbound sales — an SDR manager
overseeing two SDRs who work HubSpot leads and a RevOps analyst.
With human-in-the-loop gates
Build an Envelope team that drafts marketing emails and pauses for
human approval before sending.
Example
User: "Build me an Envelope team for content moderation — a supervisor and two reviewer agents that check posts against community guidelines."
Output:
{
"$schema": "https://schema.openenvelope.org/team/v1.json",
"name": "Content Moderation Team",
"slug": "content-moderation",
"version": "1.0.0",
"description": "A supervisor and two reviewer agents that check posts against community guidelines.",
"visibility": "team",
"category": "ops",
"requiredVariables": ["companyName"],
"requiredSecrets": ["MODERATION_API_KEY"],
"metadata": { "generatedBy": "Claude Code · openenvelope.org" },
"agents": [
{
"key": "supervisor",
"name": "Moderation Supervisor",
"role": "supervisor",
"capabilities": ["Route content to reviewer agents", "Aggregate decisions", "Escalate edge cases"],
"model": "anthropic:claude-sonnet-4-5",
"systemPrompt": "You supervise the content moderation team at {{companyName}}. Delegate each item to a reviewer and consolidate their verdicts."
},
{
"key": "policy-reviewer",
"name": "Policy Reviewer",
"role": "reviewer",
"capabilities": ["Check content against community guidelines", "Flag policy violations"],
"model": "anthropic:claude-haiku-3-5",
"systemPrompt": "You review content for policy violations at {{companyName}}. Return a verdict of approve, flag, or remove with a reason.",
"reportsToKey": "supervisor",
"accessPolicy": {
"accessPolicyVersion": "1",
"rules": [
{ "host": "api.moderation-service.com", "action": "allow" },
{ "host": "*", "action": "deny" }
]
}
},
{
"key": "spam-reviewer",
"name": "Spam Reviewer",
"role": "reviewer",
"capabilities": ["Detect spam, bot activity, and duplicate content"],
"model": "anthropic:claude-haiku-3-5",
"systemPrompt": "You detect spam and bot activity at {{companyName}}. Return a verdict of approve, flag, or remove with a confidence score.",
"reportsToKey": "supervisor"
}
]
}
Schema Reference
Top-level fields
| Field | Required | Description |
|---|---|---|
$schema |
yes | Always https://schema.openenvelope.org/team/v1.json |
name |
yes | Human-readable team name |
slug |
yes | URL-safe, lowercase, hyphens only |
version |
yes | Semver e.g. "1.0.0" |
description |
yes | What this team does |
visibility |
yes | "public" · "team" · "private" |
requiredVariables |
no | Non-sensitive config, interpolated via {{varName}} |
requiredSecrets |
no | API keys, stored encrypted, injected as ${SECRET_NAME} |
schedule |
no | Cron schedule { cron, timezone, task } |
agents |
yes | Agent definitions |
gates |
no | Human-in-the-loop checkpoints |
Agent fields
| Field | Required | Description |
|---|---|---|
key |
yes | Unique identifier within this file |
name |
yes | Display name |
role |
yes | Free-form e.g. "supervisor", "analyst", "sdr" |
capabilities |
yes | What this agent can do — used for delegation routing |
model |
yes | e.g. anthropic:claude-sonnet-4-5, anthropic:claude-haiku-3-5 |
systemPrompt |
yes | Agent instructions. Use {{varName}} and ${SECRET_NAME} |
reportsToKey |
no | key of manager agent. Omit for the top-level supervisor |
accessPolicy |
no | Outbound HTTP allowlist |
Hierarchy rule
Exactly one agent should have no reportsToKey — this is the supervisor that receives the initial task. All others reference their manager's key.
Access policy
"accessPolicy": {
"accessPolicyVersion": "1",
"rules": [
{ "host": "api.example.com", "action": "allow" },
{ "host": "*", "action": "deny" }
]
}
Human-in-the-loop gates
"gates": [
{
"name": "approval-check",
"type": "approval",
"trigger": { "afterAgent": "drafter" },
"onApprove": "continue",
"onReject": "halt"
}
]
Tips
- Use
anthropic:claude-sonnet-4-5for supervisors and managers;anthropic:claude-haiku-3-5for leaf agents doing repetitive work - Put anything org-specific (company name, support email, Slack channel) in
requiredVariables - End access policy rules with
{ "host": "*", "action": "deny" }for a strict allowlist - Add gates before any agent that sends emails, posts publicly, or makes purchases
- Validate before deploying:
npx @openenvelope/schema validate ./team.envelope.json
Links
- openenvelope.org — deploy and run teams
- schema.openenvelope.org/team/v1.json — JSON schema
- npmjs.com/package/@openenvelope/schema — TypeScript types + validator
- openenvelope.org/mcp — run teams via MCP from Claude.ai or ChatGPT
Source: davepoon/buildwithclaude → plugins/all-skills/skills/envelope-team/SKILL.md
Also appears in: davepoon/buildwithclaude/plugins/envelope-team/skills/envelope-team/SKILL.md