メニュー
Upload and manage media in the Dataspheres AI library
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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 | library |
| description | Upload and manage media in the Dataspheres AI library |
| argument-hint | [action] [options] |
The media library stores images, documents, and other files scoped to a datasphere. Uploaded files get a public URL that can be embedded in pages, tasks, and newsletters.
upload_file(file_path="/path/to/screenshot.png", description="Q2 launch hero image")
# → {"url": "https://dataspheres.ai/api/media/...", "id": "med_...", "name": "screenshot.png"}
The returned url is ready to use in page content, task comments, or newsletter issues.
Supported types: images (PNG, JPG, GIF, WebP), PDFs, audio, video. Max file size depends on your plan.
list_library(limit=20)
# → [{"id": "med_...", "url": "...", "name": "...", "mimeType": "image/png", "createdAt": "..."}, ...]
Search by filename:
list_library(search="screenshot", limit=10)
delete_media(media_id="med_abc123")
# → None (204 No Content)
| Tool | Method | Endpoint | Notes |
|---|---|---|---|
upload_file | POST | /api/media/upload | Multipart form upload; uses direct httpx call |
list_library | GET | /api/v1/dataspheres/:uri/media | Requires active datasphere |
delete_media | DELETE | /api/v1/dataspheres/:uri/media/:mediaId | Permanent — no undo |
upload_file does not scope to a datasphere by URI in the path — the API uses the authenticated user's account to associate the upload. However, list_library and delete_media are datasphere-scoped.
After uploading, embed with an <img> tag in page content:
<img src="https://dataspheres.ai/api/media/abc..." alt="Q2 hero" />
For task comments (screenshots), pass the URL in the screenshots list when calling add_comment from the planner skill.
| Error | Cause | Fix |
|---|---|---|
| FileNotFoundError | file_path doesn't exist | Check the path with os.path.exists() |
| 401 | Invalid API key | Re-run dai login |
| 413 | File too large | Compress the file or upgrade your plan |
| 404 on list/delete | Datasphere URI not found | Run dai use <uri> with a valid URI |