Menu
Manage active datasphere context and session state
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Local dev skill for the Dataspheres AI Content API. Wraps /api/v1/ REST endpoints for local-to-production content workflows. Use when the user wants to push pages, generate release notes from git log, list pages, or update content in a datasphere from their local machine.
Full newsletter lifecycle — create, configure all settings (frequency, personalization, AI model, web search, reply threading, plan mode wiring), manage subscribers, attach forms, draft and manage issues, preview personalized letters, enable private chat and email replies, and test in dev.
Drive the Dataspheres AI platform from Claude Code — read conversation history, post messages as the user (via API key), poll for ARI replies, read the Reality Engine debug log, update the plan and outcomes, and control orchestration flow. Use when you need Claude Code to interact with ARI or inspect/modify a running reality session.
Knowledge-graph tools for Dataspheres AI — build typed graphs, relate nodes with VISUAL or executable TASK edges, group into colored container bubbles, auto-detect article hero images, embed graphs in pages, run scheduled searches, and report.
Sequencers tools for Dataspheres AI
Manage Kanban tasks, plan modes, and project workflows in Dataspheres AI
| name | context |
| description | Manage active datasphere context and session state |
| argument-hint | [action] [options] |
All MCP tools operate against the active datasphere. The context skill lets you inspect and switch that context without leaving your IDE agent session.
get_active_datasphere()
# → {"active_datasphere": "my-ds", "details": {"id": "ds_...", "name": "My DS", "uri": "my-ds"}}
Returns {"active_datasphere": null, "message": "..."} if none is set.
set_active_datasphere(uri="other-datasphere")
# → {"active_datasphere": "other-datasphere", "name": "Other Datasphere"}
This updates the persisted state in ~/.dai-skills/state.db AND warms the ds_id cache so the next v2 API call doesn't need a round-trip to resolve the DB ID.
clear_context()
# → {"cleared": True}
Removes the active datasphere from state. Useful when switching between projects or at end of session.
get_history(limit=10)
# → list of recent tool invocations with timestamps
These tools mirror the CLI commands:
| Tool | CLI equivalent |
|---|---|
get_active_datasphere() | dai status |
set_active_datasphere(uri) | dai use <uri> |
clear_context() | dai use --clear |
get_history() | dai history |
| Tool | Endpoint | Notes |
|---|---|---|
get_active_datasphere | GET /api/v1/dataspheres/:uri | Reads state first; API call is best-effort |
set_active_datasphere | GET /api/v1/dataspheres/:uri | Validates URI exists before saving |
clear_context | — | Local state only, no API call |
get_history | — | Local state only, no API call |
| Error | Cause | Fix |
|---|---|---|
| "No active datasphere" | No datasphere set | set_active_datasphere(uri="<your-ds>") |
| 401 | Invalid API key | Re-run dai login --key dsk_xxx |
| 404 | URI not found | Check list_dataspheres() from the dataspheres skill |