AgentScope-AI

Prepare an existing OpenClaw setup for import as an AgentTeams managed Worker. Analyze tool dependencies, adapt role instructions and scheduled jobs, and build a ZIP package containing the configuration and custom image requirements.

• Moving standalone OpenClaw into AgentTeams
• Reviewing required tool dependencies
• Adapting role instructions for a Worker

Configure external APIs and existing MCP tool servers through Higress AI Gateway. The skill covers YAML-based setup, credential updates, Worker access permissions, and connection checks before making tools available to the Workers that need them.

• Expose an external API as an MCP tool
• Update credentials for a tool server
• Grant or revoke Worker access to tools

Look up current AgentTeams membership, Worker runtime state, and identity details when the conversation lacks them. The skill uses the agt command-line tool to confirm coordinator identities, team context, and room information without relying on old records.

• Confirm a coordinator's Matrix ID
• Check team membership or standalone Worker context
• Look up room IDs for message routing

Deliver TeamHarness messages to the correct room, channel, or session using recorded reply routes. It covers task handoffs and requester reports, while defining when to reply directly or suppress acknowledgements that could cause message loops.

• Deliver progress reports to the original requester
• Hand off a request to a Matrix task room
• Send messages across rooms or channels

Keep Hermes Worker configuration and shared task files synchronized with MinIO, a central storage service. The skill covers immediate downloads, manual result uploads, and which configuration changes take effect on the next message or require a restart.

• Apply newly updated agent settings
• Retrieve urgent updates to shared task files
• Upload completed work to MinIO

Identify whether a Matrix chat room is a request source or a task workspace, then create or reuse a project-specific task room. The skill also handles worker invitation details and preserves information about where requests originated.

• Identify the purpose of a Matrix room
• Prepare a task room for a new project
• Reuse an existing room for the same project

Switch the Manager Agent's primary language model with a script that checks connectivity before saving configuration. You can also set how much context the model accepts and whether extended thinking is enabled.

• Change the Manager's saved primary model
• Correct a model's context window setting
• Disable extended thinking for a model

Manage human accounts in AgentTeams by adding users, assigning one of three permission levels, and choosing which agents they can contact. It also covers listing accounts, updating permissions, and removing access.

• Add a team member to AgentTeams
• Limit an external collaborator to selected Workers
• Update a user's permissions

Retrieve shared reference files and send work in progress using local shared paths. The skill also guides missing-file checks and distinguishes manual file transfers from synchronization already handled by task acceptance and submission.

• Retrieve shared project reference materials
• Send progress files before task submission
• Investigate missing shared task files

Call tools on configured MCP servers, which connect agents to external services, through the mcporter CLI. Inspect available tools and their inputs, retrieve API information, and check connections before deciding how to proceed.

• Look up a GitHub repository or issue status
• Gather information before assigning work
• Check an API connection after setup

Handle standalone administration tasks on a Tuwunel Matrix server, including registering users, creating rooms, managing membership, and uploading files. It also covers sending files to an administrator and identifies mention and room-joining requirements that affect Workers.

• Registering users on a Matrix server
• Creating rooms and managing membership
• Uploading files for an administrator

Manage AI agent Workers by creating roles, selecting runtimes, starting or stopping Workers, and updating their skills. It also covers runtime migration, direct mentions between Workers, and access to the QwenPaw console.

• Create a Worker with a defined role and skills
• Start, stop, or reset a Worker
• Add or remove Worker skills

Guides task delegation to Worker agents, completion handling, and recurring task management. It explains how to register assignments, synchronize task files and results, and choose the relevant procedure when checking worker availability or updating task state.

• Selecting an available Worker for a task
• Registering and delegating a one-off task
• Retrieving results after a completion report

Transfer files between agents through MinIO, a shared file store. The skill guides uploading materials for Workers, downloading their outputs, and notifying them to sync so that local files reflect shared updates.

• Share input files with Workers
• Download outputs uploaded by Workers
• Notify Workers after updating shared files

Guides the creation, import, and composition of agent teams with one Team Leader and multiple Workers. It explains member changes, delegation through the Leader, and where to manage each Worker's runtime settings and lifecycle.

• Creating or importing an agent team
• Adding or removing team Workers
• Delegating work through a Team Leader

Clarify responsibilities in a TeamHarness team, including planning, task execution, result acceptance, and runtime administration. Use the role boundaries to identify who owns each action and how participants should handle sensitive information.

• Assigning responsibilities across team roles
• Checking ownership of task review and acceptance
• Defining work boundaries for remote members

Change the language model used by a Worker Agent through the agt command-line tool. The controller resolves model settings, regenerates configuration, and recreates the container to apply the change without a manual restart.

• Change a Worker's language model
• Apply registered model settings automatically
• Check whether a model change was accepted

Find and install agent skills for specific tasks, from testing and development to design and documentation. Translate needs into search terms, present relevant options with installation commands, and check or update installed skills.

• Finding skills for unfamiliar tasks
• Installing a named skill from the market
• Comparing skills for a specific workflow

Coordinate changes to shared task folders with .processing marker files that indicate ongoing work. Managers and Workers check these markers before editing, synchronize files through MinIO, and remove markers after completing their changes.

• Coordinate Manager and Worker edits in a shared workspace
• Check for ongoing work before delegated Git operations
• Set an expiration time for a processing marker

Delegate Git operations to a Manager when a worker lacks credentials. The skill explains how to prepare command requests, receive results, and synchronize shared files, covering repository downloads, branches, commits, pushes, and other Git tasks.

• Request repository cloning or remote updates
• Delegate a branch, commit, and push workflow
• Ask the Manager to merge or reorganize commits

Publish HTTP apps or APIs running inside Worker containers through the Higress gateway. Configure exposed ports using the agt CLI or YAML, receive automatically generated domains for each port, and inspect or remove public access.

• Make a Worker's web app externally accessible
• Publish an API running in a Worker container
• Expose multiple ports on one Worker

Manage GitHub pull requests, which propose code changes, and issues through a central MCP server. Create and update records, add comments, request reviewers, check changed files and automated checks, and merge pull requests.

• Creating or updating pull requests
• Checking changed files and automated check status
• Requesting reviewers and adding review comments

Manage an assigned Worker task from acceptance through delivery using taskflow. Keep work and optional progress notes in the task directory, submit structured results with deliverable paths, and report completion or blockers to the coordinator.

• Accept an assigned task and read its requirements
• Organize deliverables and progress notes by task
• Submit results with completion or revision status

Guide agent replies in Matrix chat rooms, including when to mention a coordinator, report completion, raise blockers, or answer questions. The rules limit repetitive acknowledgments and stop exchanges that add no new task, question, or decision.

• Reporting task completion to a coordinator
• Raising blockers or questions that need action
• Reducing repetitive acknowledgments