thinkingaiagenticengine/ae-cli

ae-workspace

Manage AE AgentSpaces with ae-cli: resolve current workspace context, list or update workspace profiles, transfer files, configure Agent/MCP/Skill/knowledge-base capabilities, manage shared-space members, inspect activities, or scope automations and archive…

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/thinkingaiagenticengine/ae-cli --skill ae-workspace

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

ae-workspace

Use ae-cli workspace for AgentSpace operations. Here, workspace_id and --workspace-id always mean AgentSpace.id; they never mean the legacy sandbox Workspace.id or a filesystem directory name.

Before composing a workspace command, read references/commands.md. It contains the command matrix, mutation prerequisites, and file-transfer rules.

Targeting

  1. Prefer an explicit --workspace-id supplied by the user or returned by workspace list.
  2. Inside a run, the CLI may use TE_AGENT_CURRENT_AGENT_SPACE_ID, derive the ID from the canonical /spaces/actived/<id>/.conversations/... runtime directory, or ask the server to resolve TE_AGENT_CONVERSATION_ID.
  3. When both workspace and conversation are available, send both so the server can reject a scope mismatch.
  4. Outside a run, if the target is unknown, run workspace list and select from real IDs. Never fall back to an account default.

Use workspace current to verify the resolved ID, space type, role, and capabilities before a multi-step mutation.

Safety

  • Read the latest record or revision before mutations that require --version.
  • Treat capability and membership changes as high-risk-write; preview them with --dry-run and obtain explicit confirmation before passing --yes.
  • Treat file and workspace deletion as high-risk-write.
  • Shared AgentSpace provisioning is administrator-owned. workspace create creates only a personal AgentSpace.
  • ae-cli sync and ae-cli model manage the legacy sandbox Workspace. In an AgentSpace runtime, use workspace capability commands instead.

Related domains

  • Memory: ae-cli memory ... uses the same strict AgentSpace target.
  • Automations: use ae-cli automation ... --agent-space-id ... and follow the ae-automation Skill.
  • Archived conversations: ae-cli agent +find-archived-conversations|+restore-conversation --workspace-id ....

Transition record

Transition status: transitional Owning module: te-claude AgentSpace Current transport: CLI-token REST under /api/cli/workspace/v1 Gateway target: TBD Review after: 2026-12-01 Exit condition: equivalent stable Gateway capabilities exist; keep only commands that still add orchestration, file handling, safety, or stable typed output.

from this repository

More skills

All skills
thinkingaiagenticengine
Community

ae-agent

AE Agent platform CLI for Agent, resource package import and export, notification, approval, archived conversation, model, MCP, Skill, attachment, and user-memory work. Use when managing these resources, browsing Agent markets, handling approval requests and tasks, restoring archived conversations, persisting user memory, or answering from user preferences, background, stable workflows, or historical conventions.

1h installs
1
GitHub stars
21
Updated
Oct 29
thinkingaiagenticengine
Community

ae-analysis

Use ae-cli for AE analysis-side data questions, asset operations, and asset governance: reports, analysis boards, BI dashboards, ad-hoc models, drilldown, detail data, alerts, clusters, tags, metrics, metadata discovery, project configuration, tracking plans, local input-file upload, governance asset lists/rules/lineage/impact/dependency, batch asset operations, projects, and resource links. Use when the user asks to review collected analysis questions or badcases, query data, explain a change,

1h installs
1
GitHub stars
21
Updated
Oct 29
thinkingaiagenticengine
Community

ae-analysis-global

Use when AE analysis requests mention query/current/service/deployment clusters, current cluster (当前集群), cluster info (集群信息/有哪些集群), global or multi-cluster data, all clusters/all servers, GLOBAL/SLAVE, query-cluster, clusterqueryscope, slaveclusterid, country/region/server/shard/site/market routing, or when cluster may mean query cluster rather than audience/user segment.

1h installs
1
GitHub stars
21
Updated
Oct 29
thinkingaiagenticengine
Community

ae-automation

Manage AE Agent and Agent team automations with ae-cli: create and edit schedules, enable or disable, run now, stop or retry executions, delete, inspect history and read execution results. Use for scheduled tasks and unattended recurring Agent work, from a local computer or an AE sandbox.

1h installs
1
GitHub stars
21
Updated
Oct 29