一键导入
export
Export datasphere content to local workspace/ files
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Export datasphere content to local workspace/ files
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | export |
| description | Export datasphere content to local workspace/ files |
| argument-hint | [action] [options] |
The export skill pulls content from your active datasphere and writes it to a local workspace/ directory in the current working directory. Useful for backups, offline editing, or feeding content into other tools.
The workspace/ directory is automatically added to .gitignore if not already there.
export_page(slug="q2-update")
# → {"path": "/path/to/workspace/q2-update.md", "slug": "q2-update", "title": "Q2 Update"}
The page content (HTML) is saved as Markdown with the title as an <h1>. Specify a custom filename:
export_page(slug="q2-update", filename="q2_product_update.md")
export_tasks(format="json")
# → {"path": "/path/to/workspace/tasks.json", "count": 42, "format": "json"}
Export as CSV for spreadsheet use:
export_tasks(format="csv", filename="sprint_tasks.csv")
Filter to a specific plan mode (Kanban board):
export_tasks(plan_mode_id="<planModeId>", format="json")
| Tool | Method | Endpoint | Notes |
|---|---|---|---|
export_page | GET | /api/v1/dataspheres/:uri/pages/:slug | Writes to workspace/<filename>.md |
export_tasks | GET | /api/v2/dataspheres/:dsId/tasks | Writes to workspace/<filename>.json|csv |
export_tasks uses the DB ID internally (_ds_id()) for the v2 tasks endpoint.
All files land in <cwd>/workspace/:
workspace/
├── q2-update.md
├── tasks.json
└── sprint_tasks.csv
.md files contain raw HTML.plan_mode_id.list_library from the library skill to get media URLs.| Error | Cause | Fix |
|---|---|---|
| "No active datasphere" | No datasphere set | Run dai use <uri> |
| 404 on page | Slug not found | Check list_pages() from the pages skill |
| FileNotFoundError | workspace/ parent not writable | Check directory permissions |