/install fulcra-agent-teams
Fulcra Agent Teams
The primary role of this skill is to allow agents to store generated artifacts and coordinate with other agents using shared team spaces in Fulcra's versioned file storage.
1. Uploading User Artifacts
Agents can store generated assets or dashboards created for the user.
- Namespace:
agent/\x3Cagent-name>/artifact/(e.g.,agent/wazir/artifact/onboarding-dashboard.html) - Note: Always ask for explicit user approval before uploading anything to the artifact directory.
2. Team Coordination & Shared Memory
Agents can collaborate and share memory using a shared team/\x3Cteam-name>/ prefix in the Fulcra datastore.
SECURITY & AUTHORIZATION WARNING: Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.
Within a team's directory, the following structure is used:
team/\x3Cteam-name>/artifact/: Shared output files and deliverables created by the team.team/\x3Cteam-name>/progress.md: Tracks what team members have recently done and what they are planning to do next in terms of high-level tasks.team/\x3Cteam-name>/completed.md: A growing record of each high-level objective completed by the team.team/\x3Cteam-name>/member/\x3Cagent-name>/inbox/: A drop-zone where other agents or users can place tasks, messages, or context for a specific agent.team/\x3Cteam-name>/member/\x3Cagent-name>/archive/: Where an agent moves its inbox messages once they have been read and processed.
The Inbox Lifecycle
When collaborating, agents write markdown messages to one another's inboxes. To ensure messages sort chronologically and identify the sender, messages must be named using the convention: YYYYMMDD-HHMMSS_\x3Csender-name>_\x3Cshort-topic>.md (e.g., 20260608-232500_treecle_onboarding-status.md).
Thread Continuity: When replying to a message or posting an update about a task, you MUST reuse the exact same \x3Cshort-topic> component from the original message. This allows agents and users to track conversations and tasks across multiple inbox exchanges.
When the target agent processes its inbox, it must first upload the message to its archive/ directory, and then delete the original file from its inbox/. Because Fulcra's file system is versioned, it automatically keeps a perfect audit trail of when the file was created in the inbox and when it was completed (deleted).
Workflow
To perform team operations, agents must interact with the Fulcra CLI.
See the reference documentation for the exact commands needed to manage artifacts and inbox messaging:
- Read
references/fulcra-agent-teams-cli.mdfor exact file management and CLI execution steps.
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install fulcra-agent-teams - 安装完成后,直接呼叫该 Skill 的名称或使用
/fulcra-agent-teams触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
Fulcra Agent Teams 是什么?
Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 38 次。
如何安装 Fulcra Agent Teams?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install fulcra-agent-teams」即可一键安装,无需额外配置。
Fulcra Agent Teams 是免费的吗?
是的,Fulcra Agent Teams 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Fulcra Agent Teams 支持哪些平台?
Fulcra Agent Teams 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Fulcra Agent Teams?
由 Fulcra.ai(@fulcra)开发并维护,当前版本 v0.0.1。