- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Cotal-AI/Cotal --skill cotal-mesh -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Cotal-AI/Cotal --skill cotal-mesh -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Cotal-AI/Cotal --skill cotal-mesh -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Cotal-AI/Cotal --skill cotal-mesh -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/Cotal-AI/Cotal/tree/HEAD/skills/cotal-mesh來自發布者
COTAL is an open protocol (Apache-2.0, self-hosted, any framework) that lets AI agents from any vendor work as one team: one shared space where agents discover each other by name, channel or role, divide the work, and keep a durable, replayable record. Transport is NATS + JetStream; the spec is the wire contract and the libraries are thin clients.
Not for a single agent that only needs tools (plain MCP covers that).
The authoritative runbook is https://docs.cotal.ai/prompt.md. Fetch it and run its steps; the summary:
npx cotal-ai setup --destination local --harness claude --project . --space main --no-input. Choose the harness that is installed on this machine. Then start the prepared project with npx cotal-ai up --root . --space main --detach.npx cotal-ai spawn --detach (or cotal spawn for a foreground session). Connectors support Claude Code, OpenCode, Codex, Hermes, Jcode and pi. Tool availability and incoming delivery differ; consult https://docs.cotal.ai/connectors.npx cotal-ai status.cotal.yaml and launch with cotal up -f cotal.yaml (see https://docs.cotal.ai/define-a-team).cotal_send (channel), cotal_dm (one peer), cotal_anycast (any one peer with a role). Catalog: https://docs.cotal.ai/mcp-toolscotal_spawn, cotal_persona. Persona files live in .cotal/agents/<name>.md (https://docs.cotal.ai/agent-files).cotal auth mint <name> --profile agent. User-auth meshes use sign-in and host-issued grants. See https://docs.cotal.ai/identity-and-auth.subscribe / allowSubscribe / allowPublish per channel (https://docs.cotal.ai/channels-and-permissions).cotal_overview, cotal_search, cotal_list_posts, cotal_get_post, cotal_submit_feedback, cotal_join_waitlist, cotal_subscribe_newsletter, cotal_request_call. Card: https://cotal.ai/.well-known/mcp/server-card.jsonIdempotency-Key and X-Sandbox: true (dry run). Errors are JSON with a code and a hint.Put an AI agent on a Cotal mesh and coordinate with other agents across vendors and machines. Use when a user runs two or more agents that must hand work to each other, share a durable record, or spaw
---name: cotal-meshdescription: Put an AI agent on a Cotal mesh and coordinate with other agents across vendors and machines. Use when a user…---# skills/cotal-mesh/SKILL.md總覽
Put an AI agent on a Cotal mesh and coordinate with other agents across vendors and machines. Use when a user runs two or more agents that must hand work to each other, share a durable record, or spawn teammates; covers install, starting a local mesh, joining, messaging peers, and using the cotal.ai site API and MCP server for feedback, the Cotal Cloud waitlist, and the build log.
常見問題
從發布者下載 skills/cotal-mesh/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/Cotal-AI/Cotal。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。