Kick off a multi-agent coordination task. Sends one email thread that CC's the whole team and lets them take turns.
Scanned 5/27/2026
Install via CLI
openskills install agenticmail/agenticmail---
description: Kick off a multi-agent coordination task. Sends one email thread that CC's the whole team and lets them take turns.
argument-hint: <task description>
allowed-tools: [mcp__agenticmail__list_agents, mcp__agenticmail__create_account, mcp__agenticmail__send_email, mcp__agenticmail__wait_for_email, mcp__agenticmail__list_inbox, mcp__agenticmail__read_email]
---
# /agenticmail-coordinate
Run a multi-agent task using the email thread pattern. This is how AgenticMail expects agents to coordinate. One thread, everyone on CC, agents take turns from context. Do not spawn native sub-agents to roleplay.
The user's task description is: $ARGUMENTS
## Steps
1. `mcp__agenticmail__list_agents` to see who exists. If the task needs specific roles that are not there, create them with `mcp__agenticmail__create_account` (give each one a clear role like "designer", "developer", "qa-reviewer").
2. Send one kickoff email with `mcp__agenticmail__send_email`. The first named actor goes on `to`. Everyone else, including the bridge identity, goes on `cc`. The body should:
* Name each teammate and what step they own
* Tell them to reply-all at each handoff
* Tell them to do real work with native tools (write files, run code) not paste source into emails
3. Watch the thread with `mcp__agenticmail__wait_for_email` filtered on the thread subject. Surface each reply to the user as it lands.
4. Stop when the last handoff lands or the user says enough.
## Why this works
Every local recipient is auto-woken by the mail server when the kickoff lands. Each agent reads the full thread, sees who is CC'd, decides if it is their turn, and either reply-all's or stays silent. Turn-taking is implicit from context. The thread is a searchable audit trail.
## Do not
* Do not pass `_account: "<someone-else>"` from the host session, that falsifies the From header.
* Do not call `Agent { subagent_type: "..." }` and tell it to act as the AgenticMail agent. Send mail to them instead.
* Do not compose their reply yourself and send it on their behalf. Let them reply.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.